From d9d9537d33a07d1bdf7dcb96297ffccd4356c3eb Mon Sep 17 00:00:00 2001 From: qhy <2728290997@qq.com> Date: Thu, 12 Feb 2026 10:47:21 +0800 Subject: [PATCH] baseline --- .gitignore | 3 +- run_all_case.sh | 114 + run_all_cases_20260211_194859.log | 2468 +++++++++++++++++ unitree_g1_pack_camera/case1/output.log | 127 + unitree_g1_pack_camera/case2/output.log | 127 + unitree_g1_pack_camera/case3/output.log | 127 + unitree_g1_pack_camera/case4/output.log | 127 + .../case1/output.log | 118 + .../case2/output.log | 118 + .../case3/output.log | 118 + .../case4/output.log | 118 + unitree_z1_dual_arm_stackbox/case1/output.log | 115 + unitree_z1_dual_arm_stackbox/case2/output.log | 115 + unitree_z1_dual_arm_stackbox/case3/output.log | 115 + unitree_z1_dual_arm_stackbox/case4/output.log | 115 + .../case1/output.log | 127 + .../case2/output.log | 127 + .../case3/output.log | 127 + .../case4/output.log | 127 + unitree_z1_stackbox/case1/output.log | 130 + unitree_z1_stackbox/case2/output.log | 130 + unitree_z1_stackbox/case3/output.log | 130 + unitree_z1_stackbox/case4/output.log | 130 + 23 files changed, 5052 insertions(+), 1 deletion(-) create mode 100644 run_all_case.sh create mode 100644 run_all_cases_20260211_194859.log create mode 100644 unitree_g1_pack_camera/case1/output.log create mode 100644 unitree_g1_pack_camera/case2/output.log create mode 100644 unitree_g1_pack_camera/case3/output.log create mode 100644 unitree_g1_pack_camera/case4/output.log create mode 100644 unitree_z1_dual_arm_cleanup_pencils/case1/output.log create mode 100644 unitree_z1_dual_arm_cleanup_pencils/case2/output.log create mode 100644 unitree_z1_dual_arm_cleanup_pencils/case3/output.log create mode 100644 unitree_z1_dual_arm_cleanup_pencils/case4/output.log create mode 100644 unitree_z1_dual_arm_stackbox/case1/output.log create mode 100644 unitree_z1_dual_arm_stackbox/case2/output.log create mode 100644 unitree_z1_dual_arm_stackbox/case3/output.log create mode 100644 unitree_z1_dual_arm_stackbox/case4/output.log create mode 100644 unitree_z1_dual_arm_stackbox_v2/case1/output.log create mode 100644 unitree_z1_dual_arm_stackbox_v2/case2/output.log create mode 100644 unitree_z1_dual_arm_stackbox_v2/case3/output.log create mode 100644 unitree_z1_dual_arm_stackbox_v2/case4/output.log create mode 100644 unitree_z1_stackbox/case1/output.log create mode 100644 unitree_z1_stackbox/case2/output.log create mode 100644 unitree_z1_stackbox/case3/output.log create mode 100644 unitree_z1_stackbox/case4/output.log diff --git a/.gitignore b/.gitignore index ea715de..f0e85ae 100644 --- a/.gitignore +++ b/.gitignore @@ -55,7 +55,7 @@ coverage.xml *.pot # Django stuff: -*.log + local_settings.py db.sqlite3 @@ -129,3 +129,4 @@ Data/utils.py Experiment/checkpoint Experiment/log ckpts/unifolm_wma_dual.ckpt +*.0 \ No newline at end of file diff --git a/run_all_case.sh b/run_all_case.sh new file mode 100644 index 0000000..6252554 --- /dev/null +++ b/run_all_case.sh @@ -0,0 +1,114 @@ +#!/bin/bash + +# 自动执行所有场景的所有case +# 总共5个场景，每个场景4个case，共20个case +# 设置环境变量（离线模式） +export HF_HUB_OFFLINE=1 +export TRANSFORMERS_OFFLINE=1 + +# 颜色定义 +RED='\033[0;31m' +GREEN='\033[0;32m' +YELLOW='\033[1;33m' +BLUE='\033[0;34m' +NC='\033[0m' # No Color + +# 定义所有场景 +SCENARIOS=( + "unitree_g1_pack_camera" + "unitree_z1_dual_arm_cleanup_pencils" + "unitree_z1_dual_arm_stackbox" + "unitree_z1_dual_arm_stackbox_v2" + "unitree_z1_stackbox" +) + +# 定义case数量 +CASES=(1 2 3 4) + +# 记录开始时间 +START_TIME=$(date +%s) +LOG_FILE="run_all_cases_$(date +%Y%m%d_%H%M%S).log" + +echo -e "${BLUE}========================================${NC}" +echo -e "${BLUE}开始执行所有场景的case${NC}" +echo -e "${BLUE}总共: ${#SCENARIOS[@]} 个场景 x ${#CASES[@]} 个case = $((${#SCENARIOS[@]} * ${#CASES[@]})) 个任务${NC}" +echo -e "${BLUE}日志文件: ${LOG_FILE}${NC}" +echo -e "${BLUE}========================================${NC}" +echo "" + +# 初始化计数器 +TOTAL_CASES=$((${#SCENARIOS[@]} * ${#CASES[@]})) +CURRENT_CASE=0 +SUCCESS_COUNT=0 +FAIL_COUNT=0 + +# 记录失败的case +declare -a FAILED_CASES + +# 遍历所有场景 +for scenario in "${SCENARIOS[@]}"; do + echo -e "${YELLOW}>>> 场景: ${scenario}${NC}" + + # 遍历所有case + for case_num in "${CASES[@]}"; do + CURRENT_CASE=$((CURRENT_CASE + 1)) + case_dir="${scenario}/case${case_num}" + script_path="${case_dir}/run_world_model_interaction.sh" + + echo -e "${BLUE}[${CURRENT_CASE}/${TOTAL_CASES}] 执行: ${case_dir}${NC}" + + # 检查脚本是否存在 + if [ ! -f "${script_path}" ]; then + echo -e "${RED}错误: 脚本不存在 ${script_path}${NC}" + FAIL_COUNT=$((FAIL_COUNT + 1)) + FAILED_CASES+=("${case_dir} (脚本不存在)") + continue + fi + + # 执行脚本 + echo "开始时间: $(date '+%Y-%m-%d %H:%M:%S')" + + if bash "${script_path}" >> "${LOG_FILE}" 2>&1; then + echo -e "${GREEN}✓ 成功: ${case_dir}${NC}" + SUCCESS_COUNT=$((SUCCESS_COUNT + 1)) + else + echo -e "${RED}✗ 失败: ${case_dir}${NC}" + FAIL_COUNT=$((FAIL_COUNT + 1)) + FAILED_CASES+=("${case_dir}") + fi + + echo "结束时间: $(date '+%Y-%m-%d %H:%M:%S')" + echo "" + done + + echo "" +done + +# 计算总耗时 +END_TIME=$(date +%s) +DURATION=$((END_TIME - START_TIME)) +HOURS=$((DURATION / 3600)) +MINUTES=$(((DURATION % 3600) / 60)) +SECONDS=$((DURATION % 60)) + +# 输出总结 +echo -e "${BLUE}========================================${NC}" +echo -e "${BLUE}执行完成！${NC}" +echo -e "${BLUE}========================================${NC}" +echo -e "总任务数: ${TOTAL_CASES}" +echo -e "${GREEN}成功: ${SUCCESS_COUNT}${NC}" +echo -e "${RED}失败: ${FAIL_COUNT}${NC}" +echo -e "总耗时: ${HOURS}小时 ${MINUTES}分钟 ${SECONDS}秒" +echo -e "详细日志: ${LOG_FILE}" +echo "" + +# 如果有失败的case，列出来 +if [ ${FAIL_COUNT} -gt 0 ]; then + echo -e "${RED}失败的case列表:${NC}" + for failed_case in "${FAILED_CASES[@]}"; do + echo -e "${RED} - ${failed_case}${NC}" + done + echo "" +fi + +echo -e "${BLUE}========================================${NC}" diff --git a/run_all_cases_20260211_194859.log b/run_all_cases_20260211_194859.log new file mode 100644 index 0000000..a0b0dee --- /dev/null +++ b/run_all_cases_20260211_194859.log @@ -0,0 +1,2468 @@ +2026-02-11 19:49:03.885238: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. +2026-02-11 19:49:03.934263: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered +2026-02-11 19:49:03.934309: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered +2026-02-11 19:49:03.935622: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered +2026-02-11 19:49:03.943041: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. +To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. +2026-02-11 19:49:04.852993: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT +Global seed set to 123 +INFO:mainlogger:LatentVisualDiffusion: Running in v-prediction mode +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +AE working on z of shape (1, 4, 32, 32) = 4096 dimensions. +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +>>> model checkpoint loaded. +>>> Load pre-trained model ... +INFO:root:***** Configing Data ***** +>>> unitree_z1_stackbox: 1 data samples loaded. +>>> unitree_z1_stackbox: data stats loaded. +>>> unitree_z1_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox: data stats loaded. +>>> unitree_z1_dual_arm_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox_v2: data stats loaded. +>>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated. +>>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated. +>>> unitree_g1_pack_camera: 1 data samples loaded. +>>> unitree_g1_pack_camera: data stats loaded. +>>> unitree_g1_pack_camera: normalizer initiated. +>>> Dataset is successfully loaded ... +>>> Generate 16 frames under each generation ... +DEBUG:h5py._conv:Creating converter from 3 to 5 +DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13 +DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9 +DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096 + 0%| | 0/11 [00:00>> Step 0: generating actions ... +>>> Step 0: interacting with world model ... +DEBUG:PIL.Image:Importing BlpImagePlugin +DEBUG:PIL.Image:Importing BmpImagePlugin +DEBUG:PIL.Image:Importing BufrStubImagePlugin +DEBUG:PIL.Image:Importing CurImagePlugin +DEBUG:PIL.Image:Importing DcxImagePlugin +DEBUG:PIL.Image:Importing DdsImagePlugin +DEBUG:PIL.Image:Importing EpsImagePlugin +DEBUG:PIL.Image:Importing FitsImagePlugin +DEBUG:PIL.Image:Importing FitsStubImagePlugin +DEBUG:PIL.Image:Importing FliImagePlugin +DEBUG:PIL.Image:Importing FpxImagePlugin +DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing FtexImagePlugin +DEBUG:PIL.Image:Importing GbrImagePlugin +DEBUG:PIL.Image:Importing GifImagePlugin +DEBUG:PIL.Image:Importing GribStubImagePlugin +DEBUG:PIL.Image:Importing Hdf5StubImagePlugin +DEBUG:PIL.Image:Importing IcnsImagePlugin +DEBUG:PIL.Image:Importing IcoImagePlugin +DEBUG:PIL.Image:Importing ImImagePlugin +DEBUG:PIL.Image:Importing ImtImagePlugin +DEBUG:PIL.Image:Importing IptcImagePlugin +DEBUG:PIL.Image:Importing JpegImagePlugin +DEBUG:PIL.Image:Importing Jpeg2KImagePlugin +DEBUG:PIL.Image:Importing McIdasImagePlugin +DEBUG:PIL.Image:Importing MicImagePlugin +DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing MpegImagePlugin +DEBUG:PIL.Image:Importing MpoImagePlugin +DEBUG:PIL.Image:Importing MspImagePlugin +DEBUG:PIL.Image:Importing PalmImagePlugin +DEBUG:PIL.Image:Importing PcdImagePlugin +DEBUG:PIL.Image:Importing PcxImagePlugin +DEBUG:PIL.Image:Importing PdfImagePlugin +DEBUG:PIL.Image:Importing PixarImagePlugin +DEBUG:PIL.Image:Importing PngImagePlugin +DEBUG:PIL.Image:Importing PpmImagePlugin +DEBUG:PIL.Image:Importing PsdImagePlugin +DEBUG:PIL.Image:Importing QoiImagePlugin +DEBUG:PIL.Image:Importing SgiImagePlugin +DEBUG:PIL.Image:Importing SpiderImagePlugin +DEBUG:PIL.Image:Importing SunImagePlugin +DEBUG:PIL.Image:Importing TgaImagePlugin +DEBUG:PIL.Image:Importing TiffImagePlugin +DEBUG:PIL.Image:Importing WebPImagePlugin +DEBUG:PIL.Image:Importing WmfImagePlugin +DEBUG:PIL.Image:Importing XbmImagePlugin +DEBUG:PIL.Image:Importing XpmImagePlugin +DEBUG:PIL.Image:Importing XVThumbImagePlugin + 9%|▉ | 1/11 [01:12<12:09, 72.95s/it] 18%|█▊ | 2/11 [02:26<10:58, 73.19s/it] 27%|██▋ | 3/11 [03:39<09:45, 73.21s/it] 36%|███▋ | 4/11 [04:52<08:32, 73.21s/it] 45%|████▌ | 5/11 [06:05<07:19, 73.22s/it] 55%|█████▍ | 6/11 [07:19<06:06, 73.20s/it] 64%|██████▎ | 7/11 [08:32<04:52, 73.16s/it] 73%|███████▎ | 8/11 [09:45<03:39, 73.14s/it] 82%|████████▏ | 9/11 [10:58<02:26, 73.13s/it] 91%|█████████ | 10/11 [12:11<01:13, 73.15s/it] 100%|██████████| 11/11 [13:24<00:00, 73.18s/it] 100%|██████████| 11/11 [13:24<00:00, 73.17s/it] +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 1: generating actions ... +>>> Step 1: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 2: generating actions ... +>>> Step 2: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 3: generating actions ... +>>> Step 3: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 4: generating actions ... +>>> Step 4: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 5: generating actions ... +>>> Step 5: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 6: generating actions ... +>>> Step 6: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 7: generating actions ... +>>> Step 7: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 8: generating actions ... +>>> Step 8: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 9: generating actions ... +>>> Step 9: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 10: generating actions ... +>>> Step 10: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> + +real 15m0.258s +user 65m49.394s +sys 0m45.300s +2026-02-11 20:04:06.049535: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. +2026-02-11 20:04:06.099186: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered +2026-02-11 20:04:06.099232: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered +2026-02-11 20:04:06.100544: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered +2026-02-11 20:04:06.108023: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. +To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. +2026-02-11 20:04:07.025500: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT +Global seed set to 123 +INFO:mainlogger:LatentVisualDiffusion: Running in v-prediction mode +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +AE working on z of shape (1, 4, 32, 32) = 4096 dimensions. +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +>>> model checkpoint loaded. +>>> Load pre-trained model ... +INFO:root:***** Configing Data ***** +>>> unitree_z1_stackbox: 1 data samples loaded. +>>> unitree_z1_stackbox: data stats loaded. +>>> unitree_z1_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox: data stats loaded. +>>> unitree_z1_dual_arm_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox_v2: data stats loaded. +>>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated. +>>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated. +>>> unitree_g1_pack_camera: 1 data samples loaded. +>>> unitree_g1_pack_camera: data stats loaded. +>>> unitree_g1_pack_camera: normalizer initiated. +>>> Dataset is successfully loaded ... +>>> Generate 16 frames under each generation ... +DEBUG:h5py._conv:Creating converter from 3 to 5 +DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13 +DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9 +DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096 + 0%| | 0/11 [00:00>> Step 0: generating actions ... +>>> Step 0: interacting with world model ... +DEBUG:PIL.Image:Importing BlpImagePlugin +DEBUG:PIL.Image:Importing BmpImagePlugin +DEBUG:PIL.Image:Importing BufrStubImagePlugin +DEBUG:PIL.Image:Importing CurImagePlugin +DEBUG:PIL.Image:Importing DcxImagePlugin +DEBUG:PIL.Image:Importing DdsImagePlugin +DEBUG:PIL.Image:Importing EpsImagePlugin +DEBUG:PIL.Image:Importing FitsImagePlugin +DEBUG:PIL.Image:Importing FitsStubImagePlugin +DEBUG:PIL.Image:Importing FliImagePlugin +DEBUG:PIL.Image:Importing FpxImagePlugin +DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing FtexImagePlugin +DEBUG:PIL.Image:Importing GbrImagePlugin +DEBUG:PIL.Image:Importing GifImagePlugin +DEBUG:PIL.Image:Importing GribStubImagePlugin +DEBUG:PIL.Image:Importing Hdf5StubImagePlugin +DEBUG:PIL.Image:Importing IcnsImagePlugin +DEBUG:PIL.Image:Importing IcoImagePlugin +DEBUG:PIL.Image:Importing ImImagePlugin +DEBUG:PIL.Image:Importing ImtImagePlugin +DEBUG:PIL.Image:Importing IptcImagePlugin +DEBUG:PIL.Image:Importing JpegImagePlugin +DEBUG:PIL.Image:Importing Jpeg2KImagePlugin +DEBUG:PIL.Image:Importing McIdasImagePlugin +DEBUG:PIL.Image:Importing MicImagePlugin +DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing MpegImagePlugin +DEBUG:PIL.Image:Importing MpoImagePlugin +DEBUG:PIL.Image:Importing MspImagePlugin +DEBUG:PIL.Image:Importing PalmImagePlugin +DEBUG:PIL.Image:Importing PcdImagePlugin +DEBUG:PIL.Image:Importing PcxImagePlugin +DEBUG:PIL.Image:Importing PdfImagePlugin +DEBUG:PIL.Image:Importing PixarImagePlugin +DEBUG:PIL.Image:Importing PngImagePlugin +DEBUG:PIL.Image:Importing PpmImagePlugin +DEBUG:PIL.Image:Importing PsdImagePlugin +DEBUG:PIL.Image:Importing QoiImagePlugin +DEBUG:PIL.Image:Importing SgiImagePlugin +DEBUG:PIL.Image:Importing SpiderImagePlugin +DEBUG:PIL.Image:Importing SunImagePlugin +DEBUG:PIL.Image:Importing TgaImagePlugin +DEBUG:PIL.Image:Importing TiffImagePlugin +DEBUG:PIL.Image:Importing WebPImagePlugin +DEBUG:PIL.Image:Importing WmfImagePlugin +DEBUG:PIL.Image:Importing XbmImagePlugin +DEBUG:PIL.Image:Importing XpmImagePlugin +DEBUG:PIL.Image:Importing XVThumbImagePlugin + 9%|▉ | 1/11 [01:14<12:22, 74.22s/it] 18%|█▊ | 2/11 [02:28<11:09, 74.33s/it] 27%|██▋ | 3/11 [03:42<09:54, 74.32s/it] 36%|███▋ | 4/11 [04:57<08:40, 74.32s/it] 45%|████▌ | 5/11 [06:11<07:25, 74.28s/it] 55%|█████▍ | 6/11 [07:25<06:10, 74.19s/it] 64%|██████▎ | 7/11 [08:39<04:56, 74.11s/it] 73%|███████▎ | 8/11 [09:53<03:42, 74.07s/it] 82%|████████▏ | 9/11 [11:07<02:28, 74.06s/it] 91%|█████████ | 10/11 [12:21<01:14, 74.01s/it] 100%|██████████| 11/11 [13:35<00:00, 73.98s/it] 100%|██████████| 11/11 [13:35<00:00, 74.12s/it] +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 1: generating actions ... +>>> Step 1: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 2: generating actions ... +>>> Step 2: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 3: generating actions ... +>>> Step 3: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 4: generating actions ... +>>> Step 4: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 5: generating actions ... +>>> Step 5: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 6: generating actions ... +>>> Step 6: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 7: generating actions ... +>>> Step 7: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 8: generating actions ... +>>> Step 8: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 9: generating actions ... +>>> Step 9: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 10: generating actions ... +>>> Step 10: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> + +real 15m13.215s +user 66m8.595s +sys 0m45.545s +2026-02-11 20:19:19.271045: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. +2026-02-11 20:19:19.320688: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered +2026-02-11 20:19:19.320734: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered +2026-02-11 20:19:19.322059: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered +2026-02-11 20:19:19.329606: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. +To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. +2026-02-11 20:19:20.248938: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT +Global seed set to 123 +INFO:mainlogger:LatentVisualDiffusion: Running in v-prediction mode +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +AE working on z of shape (1, 4, 32, 32) = 4096 dimensions. +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +>>> model checkpoint loaded. +>>> Load pre-trained model ... +INFO:root:***** Configing Data ***** +>>> unitree_z1_stackbox: 1 data samples loaded. +>>> unitree_z1_stackbox: data stats loaded. +>>> unitree_z1_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox: data stats loaded. +>>> unitree_z1_dual_arm_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox_v2: data stats loaded. +>>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated. +>>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated. +>>> unitree_g1_pack_camera: 1 data samples loaded. +>>> unitree_g1_pack_camera: data stats loaded. +>>> unitree_g1_pack_camera: normalizer initiated. +>>> Dataset is successfully loaded ... +>>> Generate 16 frames under each generation ... +DEBUG:h5py._conv:Creating converter from 3 to 5 +DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13 +DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9 +DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096 + 0%| | 0/11 [00:00>> Step 0: generating actions ... +>>> Step 0: interacting with world model ... +DEBUG:PIL.Image:Importing BlpImagePlugin +DEBUG:PIL.Image:Importing BmpImagePlugin +DEBUG:PIL.Image:Importing BufrStubImagePlugin +DEBUG:PIL.Image:Importing CurImagePlugin +DEBUG:PIL.Image:Importing DcxImagePlugin +DEBUG:PIL.Image:Importing DdsImagePlugin +DEBUG:PIL.Image:Importing EpsImagePlugin +DEBUG:PIL.Image:Importing FitsImagePlugin +DEBUG:PIL.Image:Importing FitsStubImagePlugin +DEBUG:PIL.Image:Importing FliImagePlugin +DEBUG:PIL.Image:Importing FpxImagePlugin +DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing FtexImagePlugin +DEBUG:PIL.Image:Importing GbrImagePlugin +DEBUG:PIL.Image:Importing GifImagePlugin +DEBUG:PIL.Image:Importing GribStubImagePlugin +DEBUG:PIL.Image:Importing Hdf5StubImagePlugin +DEBUG:PIL.Image:Importing IcnsImagePlugin +DEBUG:PIL.Image:Importing IcoImagePlugin +DEBUG:PIL.Image:Importing ImImagePlugin +DEBUG:PIL.Image:Importing ImtImagePlugin +DEBUG:PIL.Image:Importing IptcImagePlugin +DEBUG:PIL.Image:Importing JpegImagePlugin +DEBUG:PIL.Image:Importing Jpeg2KImagePlugin +DEBUG:PIL.Image:Importing McIdasImagePlugin +DEBUG:PIL.Image:Importing MicImagePlugin +DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing MpegImagePlugin +DEBUG:PIL.Image:Importing MpoImagePlugin +DEBUG:PIL.Image:Importing MspImagePlugin +DEBUG:PIL.Image:Importing PalmImagePlugin +DEBUG:PIL.Image:Importing PcdImagePlugin +DEBUG:PIL.Image:Importing PcxImagePlugin +DEBUG:PIL.Image:Importing PdfImagePlugin +DEBUG:PIL.Image:Importing PixarImagePlugin +DEBUG:PIL.Image:Importing PngImagePlugin +DEBUG:PIL.Image:Importing PpmImagePlugin +DEBUG:PIL.Image:Importing PsdImagePlugin +DEBUG:PIL.Image:Importing QoiImagePlugin +DEBUG:PIL.Image:Importing SgiImagePlugin +DEBUG:PIL.Image:Importing SpiderImagePlugin +DEBUG:PIL.Image:Importing SunImagePlugin +DEBUG:PIL.Image:Importing TgaImagePlugin +DEBUG:PIL.Image:Importing TiffImagePlugin +DEBUG:PIL.Image:Importing WebPImagePlugin +DEBUG:PIL.Image:Importing WmfImagePlugin +DEBUG:PIL.Image:Importing XbmImagePlugin +DEBUG:PIL.Image:Importing XpmImagePlugin +DEBUG:PIL.Image:Importing XVThumbImagePlugin + 9%|▉ | 1/11 [01:14<12:22, 74.28s/it] 18%|█▊ | 2/11 [02:28<11:09, 74.38s/it] 27%|██▋ | 3/11 [03:43<09:55, 74.45s/it] 36%|███▋ | 4/11 [04:57<08:41, 74.43s/it] 45%|████▌ | 5/11 [06:11<07:25, 74.25s/it] 55%|█████▍ | 6/11 [07:26<06:11, 74.31s/it] 64%|██████▎ | 7/11 [08:40<04:57, 74.26s/it] 73%|███████▎ | 8/11 [09:54<03:43, 74.34s/it] 82%|████████▏ | 9/11 [11:08<02:28, 74.29s/it] 91%|█████████ | 10/11 [12:23<01:14, 74.26s/it] 100%|██████████| 11/11 [13:37<00:00, 74.39s/it] 100%|██████████| 11/11 [13:37<00:00, 74.34s/it] +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 1: generating actions ... +>>> Step 1: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 2: generating actions ... +>>> Step 2: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 3: generating actions ... +>>> Step 3: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 4: generating actions ... +>>> Step 4: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 5: generating actions ... +>>> Step 5: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 6: generating actions ... +>>> Step 6: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 7: generating actions ... +>>> Step 7: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 8: generating actions ... +>>> Step 8: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 9: generating actions ... +>>> Step 9: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 10: generating actions ... +>>> Step 10: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> + +real 15m15.291s +user 65m30.562s +sys 0m45.706s +2026-02-11 20:34:34.563818: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. +2026-02-11 20:34:34.613426: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered +2026-02-11 20:34:34.613485: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered +2026-02-11 20:34:34.614802: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered +2026-02-11 20:34:34.622286: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. +To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. +2026-02-11 20:34:35.540506: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT +Global seed set to 123 +INFO:mainlogger:LatentVisualDiffusion: Running in v-prediction mode +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +AE working on z of shape (1, 4, 32, 32) = 4096 dimensions. +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +>>> model checkpoint loaded. +>>> Load pre-trained model ... +INFO:root:***** Configing Data ***** +>>> unitree_z1_stackbox: 1 data samples loaded. +>>> unitree_z1_stackbox: data stats loaded. +>>> unitree_z1_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox: data stats loaded. +>>> unitree_z1_dual_arm_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox_v2: data stats loaded. +>>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated. +>>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated. +>>> unitree_g1_pack_camera: 1 data samples loaded. +>>> unitree_g1_pack_camera: data stats loaded. +>>> unitree_g1_pack_camera: normalizer initiated. +>>> Dataset is successfully loaded ... +>>> Generate 16 frames under each generation ... +DEBUG:h5py._conv:Creating converter from 3 to 5 +DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13 +DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9 +DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096 + 0%| | 0/11 [00:00>> Step 0: generating actions ... +>>> Step 0: interacting with world model ... +DEBUG:PIL.Image:Importing BlpImagePlugin +DEBUG:PIL.Image:Importing BmpImagePlugin +DEBUG:PIL.Image:Importing BufrStubImagePlugin +DEBUG:PIL.Image:Importing CurImagePlugin +DEBUG:PIL.Image:Importing DcxImagePlugin +DEBUG:PIL.Image:Importing DdsImagePlugin +DEBUG:PIL.Image:Importing EpsImagePlugin +DEBUG:PIL.Image:Importing FitsImagePlugin +DEBUG:PIL.Image:Importing FitsStubImagePlugin +DEBUG:PIL.Image:Importing FliImagePlugin +DEBUG:PIL.Image:Importing FpxImagePlugin +DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing FtexImagePlugin +DEBUG:PIL.Image:Importing GbrImagePlugin +DEBUG:PIL.Image:Importing GifImagePlugin +DEBUG:PIL.Image:Importing GribStubImagePlugin +DEBUG:PIL.Image:Importing Hdf5StubImagePlugin +DEBUG:PIL.Image:Importing IcnsImagePlugin +DEBUG:PIL.Image:Importing IcoImagePlugin +DEBUG:PIL.Image:Importing ImImagePlugin +DEBUG:PIL.Image:Importing ImtImagePlugin +DEBUG:PIL.Image:Importing IptcImagePlugin +DEBUG:PIL.Image:Importing JpegImagePlugin +DEBUG:PIL.Image:Importing Jpeg2KImagePlugin +DEBUG:PIL.Image:Importing McIdasImagePlugin +DEBUG:PIL.Image:Importing MicImagePlugin +DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing MpegImagePlugin +DEBUG:PIL.Image:Importing MpoImagePlugin +DEBUG:PIL.Image:Importing MspImagePlugin +DEBUG:PIL.Image:Importing PalmImagePlugin +DEBUG:PIL.Image:Importing PcdImagePlugin +DEBUG:PIL.Image:Importing PcxImagePlugin +DEBUG:PIL.Image:Importing PdfImagePlugin +DEBUG:PIL.Image:Importing PixarImagePlugin +DEBUG:PIL.Image:Importing PngImagePlugin +DEBUG:PIL.Image:Importing PpmImagePlugin +DEBUG:PIL.Image:Importing PsdImagePlugin +DEBUG:PIL.Image:Importing QoiImagePlugin +DEBUG:PIL.Image:Importing SgiImagePlugin +DEBUG:PIL.Image:Importing SpiderImagePlugin +DEBUG:PIL.Image:Importing SunImagePlugin +DEBUG:PIL.Image:Importing TgaImagePlugin +DEBUG:PIL.Image:Importing TiffImagePlugin +DEBUG:PIL.Image:Importing WebPImagePlugin +DEBUG:PIL.Image:Importing WmfImagePlugin +DEBUG:PIL.Image:Importing XbmImagePlugin +DEBUG:PIL.Image:Importing XpmImagePlugin +DEBUG:PIL.Image:Importing XVThumbImagePlugin + 9%|▉ | 1/11 [01:14<12:25, 74.52s/it] 18%|█▊ | 2/11 [02:29<11:15, 75.00s/it] 27%|██▋ | 3/11 [03:44<09:59, 74.99s/it] 36%|███▋ | 4/11 [04:59<08:43, 74.74s/it] 45%|████▌ | 5/11 [06:13<07:26, 74.48s/it] 55%|█████▍ | 6/11 [07:27<06:12, 74.56s/it] 64%|██████▎ | 7/11 [08:42<04:57, 74.46s/it] 73%|███████▎ | 8/11 [09:56<03:43, 74.48s/it] 82%|████████▏ | 9/11 [11:10<02:28, 74.32s/it] 91%|█████████ | 10/11 [12:23<01:13, 73.94s/it] 100%|██████████| 11/11 [13:36<00:00, 73.64s/it] 100%|██████████| 11/11 [13:36<00:00, 74.25s/it] +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 1: generating actions ... +>>> Step 1: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 2: generating actions ... +>>> Step 2: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 3: generating actions ... +>>> Step 3: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 4: generating actions ... +>>> Step 4: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 5: generating actions ... +>>> Step 5: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 6: generating actions ... +>>> Step 6: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 7: generating actions ... +>>> Step 7: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 8: generating actions ... +>>> Step 8: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 9: generating actions ... +>>> Step 9: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 10: generating actions ... +>>> Step 10: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> + +real 15m13.379s +user 65m31.865s +sys 0m45.108s +2026-02-11 20:49:47.965949: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. +2026-02-11 20:49:48.015942: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered +2026-02-11 20:49:48.015997: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered +2026-02-11 20:49:48.017330: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered +2026-02-11 20:49:48.024854: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. +To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. +2026-02-11 20:49:48.943205: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT +Global seed set to 123 +INFO:mainlogger:LatentVisualDiffusion: Running in v-prediction mode +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +AE working on z of shape (1, 4, 32, 32) = 4096 dimensions. +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +>>> model checkpoint loaded. +>>> Load pre-trained model ... +INFO:root:***** Configing Data ***** +>>> unitree_z1_stackbox: 1 data samples loaded. +>>> unitree_z1_stackbox: data stats loaded. +>>> unitree_z1_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox: data stats loaded. +>>> unitree_z1_dual_arm_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox_v2: data stats loaded. +>>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated. +>>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated. +>>> unitree_g1_pack_camera: 1 data samples loaded. +>>> unitree_g1_pack_camera: data stats loaded. +>>> unitree_g1_pack_camera: normalizer initiated. +>>> Dataset is successfully loaded ... +>>> Generate 16 frames under each generation ... +DEBUG:h5py._conv:Creating converter from 3 to 5 +DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13 +DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9 +DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096 + 0%| | 0/8 [00:00>> Step 0: generating actions ... +>>> Step 0: interacting with world model ... +DEBUG:PIL.Image:Importing BlpImagePlugin +DEBUG:PIL.Image:Importing BmpImagePlugin +DEBUG:PIL.Image:Importing BufrStubImagePlugin +DEBUG:PIL.Image:Importing CurImagePlugin +DEBUG:PIL.Image:Importing DcxImagePlugin +DEBUG:PIL.Image:Importing DdsImagePlugin +DEBUG:PIL.Image:Importing EpsImagePlugin +DEBUG:PIL.Image:Importing FitsImagePlugin +DEBUG:PIL.Image:Importing FitsStubImagePlugin +DEBUG:PIL.Image:Importing FliImagePlugin +DEBUG:PIL.Image:Importing FpxImagePlugin +DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing FtexImagePlugin +DEBUG:PIL.Image:Importing GbrImagePlugin +DEBUG:PIL.Image:Importing GifImagePlugin +DEBUG:PIL.Image:Importing GribStubImagePlugin +DEBUG:PIL.Image:Importing Hdf5StubImagePlugin +DEBUG:PIL.Image:Importing IcnsImagePlugin +DEBUG:PIL.Image:Importing IcoImagePlugin +DEBUG:PIL.Image:Importing ImImagePlugin +DEBUG:PIL.Image:Importing ImtImagePlugin +DEBUG:PIL.Image:Importing IptcImagePlugin +DEBUG:PIL.Image:Importing JpegImagePlugin +DEBUG:PIL.Image:Importing Jpeg2KImagePlugin +DEBUG:PIL.Image:Importing McIdasImagePlugin +DEBUG:PIL.Image:Importing MicImagePlugin +DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing MpegImagePlugin +DEBUG:PIL.Image:Importing MpoImagePlugin +DEBUG:PIL.Image:Importing MspImagePlugin +DEBUG:PIL.Image:Importing PalmImagePlugin +DEBUG:PIL.Image:Importing PcdImagePlugin +DEBUG:PIL.Image:Importing PcxImagePlugin +DEBUG:PIL.Image:Importing PdfImagePlugin +DEBUG:PIL.Image:Importing PixarImagePlugin +DEBUG:PIL.Image:Importing PngImagePlugin +DEBUG:PIL.Image:Importing PpmImagePlugin +DEBUG:PIL.Image:Importing PsdImagePlugin +DEBUG:PIL.Image:Importing QoiImagePlugin +DEBUG:PIL.Image:Importing SgiImagePlugin +DEBUG:PIL.Image:Importing SpiderImagePlugin +DEBUG:PIL.Image:Importing SunImagePlugin +DEBUG:PIL.Image:Importing TgaImagePlugin +DEBUG:PIL.Image:Importing TiffImagePlugin +DEBUG:PIL.Image:Importing WebPImagePlugin +DEBUG:PIL.Image:Importing WmfImagePlugin +DEBUG:PIL.Image:Importing XbmImagePlugin +DEBUG:PIL.Image:Importing XpmImagePlugin +DEBUG:PIL.Image:Importing XVThumbImagePlugin + 12%|█▎ | 1/8 [01:15<08:48, 75.51s/it] 25%|██▌ | 2/8 [02:30<07:32, 75.39s/it] 38%|███▊ | 3/8 [03:46<06:16, 75.35s/it] 50%|█████ | 4/8 [05:00<05:00, 75.01s/it] 62%|██████▎ | 5/8 [06:14<03:44, 74.68s/it] 75%|███████▌ | 6/8 [07:28<02:28, 74.40s/it] 88%|████████▊ | 7/8 [08:42<01:14, 74.19s/it] 100%|██████████| 8/8 [09:55<00:00, 73.95s/it] 100%|██████████| 8/8 [09:55<00:00, 74.47s/it] +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 1: generating actions ... +>>> Step 1: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 2: generating actions ... +>>> Step 2: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 3: generating actions ... +>>> Step 3: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 4: generating actions ... +>>> Step 4: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 5: generating actions ... +>>> Step 5: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 6: generating actions ... +>>> Step 6: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 7: generating actions ... +>>> Step 7: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> + +real 11m31.593s +user 48m36.594s +sys 0m41.776s +2026-02-11 21:01:19.535243: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. +2026-02-11 21:01:19.585230: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered +2026-02-11 21:01:19.585275: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered +2026-02-11 21:01:19.586600: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered +2026-02-11 21:01:19.594107: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. +To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. +2026-02-11 21:01:20.510688: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT +Global seed set to 123 +INFO:mainlogger:LatentVisualDiffusion: Running in v-prediction mode +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +AE working on z of shape (1, 4, 32, 32) = 4096 dimensions. +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +>>> model checkpoint loaded. +>>> Load pre-trained model ... +INFO:root:***** Configing Data ***** +>>> unitree_z1_stackbox: 1 data samples loaded. +>>> unitree_z1_stackbox: data stats loaded. +>>> unitree_z1_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox: data stats loaded. +>>> unitree_z1_dual_arm_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox_v2: data stats loaded. +>>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated. +>>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated. +>>> unitree_g1_pack_camera: 1 data samples loaded. +>>> unitree_g1_pack_camera: data stats loaded. +>>> unitree_g1_pack_camera: normalizer initiated. +>>> Dataset is successfully loaded ... +>>> Generate 16 frames under each generation ... +DEBUG:h5py._conv:Creating converter from 3 to 5 +DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13 +DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9 +DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096 + 0%| | 0/8 [00:00>> Step 0: generating actions ... +>>> Step 0: interacting with world model ... +DEBUG:PIL.Image:Importing BlpImagePlugin +DEBUG:PIL.Image:Importing BmpImagePlugin +DEBUG:PIL.Image:Importing BufrStubImagePlugin +DEBUG:PIL.Image:Importing CurImagePlugin +DEBUG:PIL.Image:Importing DcxImagePlugin +DEBUG:PIL.Image:Importing DdsImagePlugin +DEBUG:PIL.Image:Importing EpsImagePlugin +DEBUG:PIL.Image:Importing FitsImagePlugin +DEBUG:PIL.Image:Importing FitsStubImagePlugin +DEBUG:PIL.Image:Importing FliImagePlugin +DEBUG:PIL.Image:Importing FpxImagePlugin +DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing FtexImagePlugin +DEBUG:PIL.Image:Importing GbrImagePlugin +DEBUG:PIL.Image:Importing GifImagePlugin +DEBUG:PIL.Image:Importing GribStubImagePlugin +DEBUG:PIL.Image:Importing Hdf5StubImagePlugin +DEBUG:PIL.Image:Importing IcnsImagePlugin +DEBUG:PIL.Image:Importing IcoImagePlugin +DEBUG:PIL.Image:Importing ImImagePlugin +DEBUG:PIL.Image:Importing ImtImagePlugin +DEBUG:PIL.Image:Importing IptcImagePlugin +DEBUG:PIL.Image:Importing JpegImagePlugin +DEBUG:PIL.Image:Importing Jpeg2KImagePlugin +DEBUG:PIL.Image:Importing McIdasImagePlugin +DEBUG:PIL.Image:Importing MicImagePlugin +DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing MpegImagePlugin +DEBUG:PIL.Image:Importing MpoImagePlugin +DEBUG:PIL.Image:Importing MspImagePlugin +DEBUG:PIL.Image:Importing PalmImagePlugin +DEBUG:PIL.Image:Importing PcdImagePlugin +DEBUG:PIL.Image:Importing PcxImagePlugin +DEBUG:PIL.Image:Importing PdfImagePlugin +DEBUG:PIL.Image:Importing PixarImagePlugin +DEBUG:PIL.Image:Importing PngImagePlugin +DEBUG:PIL.Image:Importing PpmImagePlugin +DEBUG:PIL.Image:Importing PsdImagePlugin +DEBUG:PIL.Image:Importing QoiImagePlugin +DEBUG:PIL.Image:Importing SgiImagePlugin +DEBUG:PIL.Image:Importing SpiderImagePlugin +DEBUG:PIL.Image:Importing SunImagePlugin +DEBUG:PIL.Image:Importing TgaImagePlugin +DEBUG:PIL.Image:Importing TiffImagePlugin +DEBUG:PIL.Image:Importing WebPImagePlugin +DEBUG:PIL.Image:Importing WmfImagePlugin +DEBUG:PIL.Image:Importing XbmImagePlugin +DEBUG:PIL.Image:Importing XpmImagePlugin +DEBUG:PIL.Image:Importing XVThumbImagePlugin + 12%|█▎ | 1/8 [01:16<08:54, 76.34s/it] 25%|██▌ | 2/8 [02:32<07:37, 76.28s/it] 38%|███▊ | 3/8 [03:48<06:21, 76.24s/it] 50%|█████ | 4/8 [05:04<05:04, 76.15s/it] 62%|██████▎ | 5/8 [06:21<03:48, 76.24s/it] 75%|███████▌ | 6/8 [07:36<02:32, 76.08s/it] 88%|████████▊ | 7/8 [08:52<01:15, 75.93s/it] 100%|██████████| 8/8 [10:09<00:00, 76.12s/it] 100%|██████████| 8/8 [10:09<00:00, 76.14s/it] +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 1: generating actions ... +>>> Step 1: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 2: generating actions ... +>>> Step 2: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 3: generating actions ... +>>> Step 3: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 4: generating actions ... +>>> Step 4: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 5: generating actions ... +>>> Step 5: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 6: generating actions ... +>>> Step 6: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 7: generating actions ... +>>> Step 7: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> + +real 11m45.279s +user 47m55.345s +sys 2m55.266s +2026-02-11 21:13:04.812376: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. +2026-02-11 21:13:04.862167: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered +2026-02-11 21:13:04.862223: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered +2026-02-11 21:13:04.863549: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered +2026-02-11 21:13:04.871078: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. +To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. +2026-02-11 21:13:05.785070: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT +Global seed set to 123 +INFO:mainlogger:LatentVisualDiffusion: Running in v-prediction mode +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +AE working on z of shape (1, 4, 32, 32) = 4096 dimensions. +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +>>> model checkpoint loaded. +>>> Load pre-trained model ... +INFO:root:***** Configing Data ***** +>>> unitree_z1_stackbox: 1 data samples loaded. +>>> unitree_z1_stackbox: data stats loaded. +>>> unitree_z1_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox: data stats loaded. +>>> unitree_z1_dual_arm_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox_v2: data stats loaded. +>>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated. +>>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated. +>>> unitree_g1_pack_camera: 1 data samples loaded. +>>> unitree_g1_pack_camera: data stats loaded. +>>> unitree_g1_pack_camera: normalizer initiated. +>>> Dataset is successfully loaded ... +>>> Generate 16 frames under each generation ... +DEBUG:h5py._conv:Creating converter from 3 to 5 +DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13 +DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9 +DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096 + 0%| | 0/8 [00:00>> Step 0: generating actions ... +>>> Step 0: interacting with world model ... +DEBUG:PIL.Image:Importing BlpImagePlugin +DEBUG:PIL.Image:Importing BmpImagePlugin +DEBUG:PIL.Image:Importing BufrStubImagePlugin +DEBUG:PIL.Image:Importing CurImagePlugin +DEBUG:PIL.Image:Importing DcxImagePlugin +DEBUG:PIL.Image:Importing DdsImagePlugin +DEBUG:PIL.Image:Importing EpsImagePlugin +DEBUG:PIL.Image:Importing FitsImagePlugin +DEBUG:PIL.Image:Importing FitsStubImagePlugin +DEBUG:PIL.Image:Importing FliImagePlugin +DEBUG:PIL.Image:Importing FpxImagePlugin +DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing FtexImagePlugin +DEBUG:PIL.Image:Importing GbrImagePlugin +DEBUG:PIL.Image:Importing GifImagePlugin +DEBUG:PIL.Image:Importing GribStubImagePlugin +DEBUG:PIL.Image:Importing Hdf5StubImagePlugin +DEBUG:PIL.Image:Importing IcnsImagePlugin +DEBUG:PIL.Image:Importing IcoImagePlugin +DEBUG:PIL.Image:Importing ImImagePlugin +DEBUG:PIL.Image:Importing ImtImagePlugin +DEBUG:PIL.Image:Importing IptcImagePlugin +DEBUG:PIL.Image:Importing JpegImagePlugin +DEBUG:PIL.Image:Importing Jpeg2KImagePlugin +DEBUG:PIL.Image:Importing McIdasImagePlugin +DEBUG:PIL.Image:Importing MicImagePlugin +DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing MpegImagePlugin +DEBUG:PIL.Image:Importing MpoImagePlugin +DEBUG:PIL.Image:Importing MspImagePlugin +DEBUG:PIL.Image:Importing PalmImagePlugin +DEBUG:PIL.Image:Importing PcdImagePlugin +DEBUG:PIL.Image:Importing PcxImagePlugin +DEBUG:PIL.Image:Importing PdfImagePlugin +DEBUG:PIL.Image:Importing PixarImagePlugin +DEBUG:PIL.Image:Importing PngImagePlugin +DEBUG:PIL.Image:Importing PpmImagePlugin +DEBUG:PIL.Image:Importing PsdImagePlugin +DEBUG:PIL.Image:Importing QoiImagePlugin +DEBUG:PIL.Image:Importing SgiImagePlugin +DEBUG:PIL.Image:Importing SpiderImagePlugin +DEBUG:PIL.Image:Importing SunImagePlugin +DEBUG:PIL.Image:Importing TgaImagePlugin +DEBUG:PIL.Image:Importing TiffImagePlugin +DEBUG:PIL.Image:Importing WebPImagePlugin +DEBUG:PIL.Image:Importing WmfImagePlugin +DEBUG:PIL.Image:Importing XbmImagePlugin +DEBUG:PIL.Image:Importing XpmImagePlugin +DEBUG:PIL.Image:Importing XVThumbImagePlugin + 12%|█▎ | 1/8 [01:15<08:45, 75.11s/it] 25%|██▌ | 2/8 [02:30<07:31, 75.30s/it] 38%|███▊ | 3/8 [03:45<06:16, 75.32s/it] 50%|█████ | 4/8 [05:01<05:01, 75.29s/it] 62%|██████▎ | 5/8 [06:16<03:46, 75.38s/it] 75%|███████▌ | 6/8 [07:32<02:30, 75.48s/it] 88%|████████▊ | 7/8 [08:47<01:15, 75.39s/it] 100%|██████████| 8/8 [10:02<00:00, 75.30s/it] 100%|██████████| 8/8 [10:02<00:00, 75.33s/it] +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 1: generating actions ... +>>> Step 1: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 2: generating actions ... +>>> Step 2: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 3: generating actions ... +>>> Step 3: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 4: generating actions ... +>>> Step 4: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 5: generating actions ... +>>> Step 5: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 6: generating actions ... +>>> Step 6: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 7: generating actions ... +>>> Step 7: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> + +real 11m37.624s +user 48m24.273s +sys 0m41.670s +2026-02-11 21:24:42.443699: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. +2026-02-11 21:24:42.494143: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered +2026-02-11 21:24:42.494201: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered +2026-02-11 21:24:42.495506: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered +2026-02-11 21:24:42.503003: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. +To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. +2026-02-11 21:24:43.415898: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT +Global seed set to 123 +INFO:mainlogger:LatentVisualDiffusion: Running in v-prediction mode +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +AE working on z of shape (1, 4, 32, 32) = 4096 dimensions. +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +>>> model checkpoint loaded. +>>> Load pre-trained model ... +INFO:root:***** Configing Data ***** +>>> unitree_z1_stackbox: 1 data samples loaded. +>>> unitree_z1_stackbox: data stats loaded. +>>> unitree_z1_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox: data stats loaded. +>>> unitree_z1_dual_arm_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox_v2: data stats loaded. +>>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated. +>>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated. +>>> unitree_g1_pack_camera: 1 data samples loaded. +>>> unitree_g1_pack_camera: data stats loaded. +>>> unitree_g1_pack_camera: normalizer initiated. +>>> Dataset is successfully loaded ... +>>> Generate 16 frames under each generation ... +DEBUG:h5py._conv:Creating converter from 3 to 5 +DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13 +DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9 +DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096 + 0%| | 0/8 [00:00>> Step 0: generating actions ... +>>> Step 0: interacting with world model ... +DEBUG:PIL.Image:Importing BlpImagePlugin +DEBUG:PIL.Image:Importing BmpImagePlugin +DEBUG:PIL.Image:Importing BufrStubImagePlugin +DEBUG:PIL.Image:Importing CurImagePlugin +DEBUG:PIL.Image:Importing DcxImagePlugin +DEBUG:PIL.Image:Importing DdsImagePlugin +DEBUG:PIL.Image:Importing EpsImagePlugin +DEBUG:PIL.Image:Importing FitsImagePlugin +DEBUG:PIL.Image:Importing FitsStubImagePlugin +DEBUG:PIL.Image:Importing FliImagePlugin +DEBUG:PIL.Image:Importing FpxImagePlugin +DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing FtexImagePlugin +DEBUG:PIL.Image:Importing GbrImagePlugin +DEBUG:PIL.Image:Importing GifImagePlugin +DEBUG:PIL.Image:Importing GribStubImagePlugin +DEBUG:PIL.Image:Importing Hdf5StubImagePlugin +DEBUG:PIL.Image:Importing IcnsImagePlugin +DEBUG:PIL.Image:Importing IcoImagePlugin +DEBUG:PIL.Image:Importing ImImagePlugin +DEBUG:PIL.Image:Importing ImtImagePlugin +DEBUG:PIL.Image:Importing IptcImagePlugin +DEBUG:PIL.Image:Importing JpegImagePlugin +DEBUG:PIL.Image:Importing Jpeg2KImagePlugin +DEBUG:PIL.Image:Importing McIdasImagePlugin +DEBUG:PIL.Image:Importing MicImagePlugin +DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing MpegImagePlugin +DEBUG:PIL.Image:Importing MpoImagePlugin +DEBUG:PIL.Image:Importing MspImagePlugin +DEBUG:PIL.Image:Importing PalmImagePlugin +DEBUG:PIL.Image:Importing PcdImagePlugin +DEBUG:PIL.Image:Importing PcxImagePlugin +DEBUG:PIL.Image:Importing PdfImagePlugin +DEBUG:PIL.Image:Importing PixarImagePlugin +DEBUG:PIL.Image:Importing PngImagePlugin +DEBUG:PIL.Image:Importing PpmImagePlugin +DEBUG:PIL.Image:Importing PsdImagePlugin +DEBUG:PIL.Image:Importing QoiImagePlugin +DEBUG:PIL.Image:Importing SgiImagePlugin +DEBUG:PIL.Image:Importing SpiderImagePlugin +DEBUG:PIL.Image:Importing SunImagePlugin +DEBUG:PIL.Image:Importing TgaImagePlugin +DEBUG:PIL.Image:Importing TiffImagePlugin +DEBUG:PIL.Image:Importing WebPImagePlugin +DEBUG:PIL.Image:Importing WmfImagePlugin +DEBUG:PIL.Image:Importing XbmImagePlugin +DEBUG:PIL.Image:Importing XpmImagePlugin +DEBUG:PIL.Image:Importing XVThumbImagePlugin + 12%|█▎ | 1/8 [01:15<08:46, 75.28s/it] 25%|██▌ | 2/8 [02:30<07:32, 75.34s/it] 38%|███▊ | 3/8 [03:45<06:15, 75.08s/it] 50%|█████ | 4/8 [04:59<04:58, 74.69s/it] 62%|██████▎ | 5/8 [06:13<03:43, 74.43s/it] 75%|███████▌ | 6/8 [07:27<02:28, 74.27s/it] 88%|████████▊ | 7/8 [08:41<01:14, 74.21s/it] 100%|██████████| 8/8 [09:55<00:00, 74.13s/it] 100%|██████████| 8/8 [09:55<00:00, 74.43s/it] +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 1: generating actions ... +>>> Step 1: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 2: generating actions ... +>>> Step 2: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 3: generating actions ... +>>> Step 3: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 4: generating actions ... +>>> Step 4: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 5: generating actions ... +>>> Step 5: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 6: generating actions ... +>>> Step 6: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 7: generating actions ... +>>> Step 7: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> + +real 11m32.306s +user 48m37.680s +sys 0m41.716s +2026-02-11 21:36:14.761055: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. +2026-02-11 21:36:14.811056: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered +2026-02-11 21:36:14.811115: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered +2026-02-11 21:36:14.812480: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered +2026-02-11 21:36:14.820115: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. +To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. +2026-02-11 21:36:15.736583: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT +Global seed set to 123 +INFO:mainlogger:LatentVisualDiffusion: Running in v-prediction mode +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +AE working on z of shape (1, 4, 32, 32) = 4096 dimensions. +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +>>> model checkpoint loaded. +>>> Load pre-trained model ... +INFO:root:***** Configing Data ***** +>>> unitree_z1_stackbox: 1 data samples loaded. +>>> unitree_z1_stackbox: data stats loaded. +>>> unitree_z1_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox: data stats loaded. +>>> unitree_z1_dual_arm_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox_v2: data stats loaded. +>>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated. +>>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated. +>>> unitree_g1_pack_camera: 1 data samples loaded. +>>> unitree_g1_pack_camera: data stats loaded. +>>> unitree_g1_pack_camera: normalizer initiated. +>>> Dataset is successfully loaded ... +>>> Generate 16 frames under each generation ... +DEBUG:h5py._conv:Creating converter from 3 to 5 +DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13 +DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9 +DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096 + 0%| | 0/7 [00:00>> Step 0: generating actions ... +>>> Step 0: interacting with world model ... +DEBUG:PIL.Image:Importing BlpImagePlugin +DEBUG:PIL.Image:Importing BmpImagePlugin +DEBUG:PIL.Image:Importing BufrStubImagePlugin +DEBUG:PIL.Image:Importing CurImagePlugin +DEBUG:PIL.Image:Importing DcxImagePlugin +DEBUG:PIL.Image:Importing DdsImagePlugin +DEBUG:PIL.Image:Importing EpsImagePlugin +DEBUG:PIL.Image:Importing FitsImagePlugin +DEBUG:PIL.Image:Importing FitsStubImagePlugin +DEBUG:PIL.Image:Importing FliImagePlugin +DEBUG:PIL.Image:Importing FpxImagePlugin +DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing FtexImagePlugin +DEBUG:PIL.Image:Importing GbrImagePlugin +DEBUG:PIL.Image:Importing GifImagePlugin +DEBUG:PIL.Image:Importing GribStubImagePlugin +DEBUG:PIL.Image:Importing Hdf5StubImagePlugin +DEBUG:PIL.Image:Importing IcnsImagePlugin +DEBUG:PIL.Image:Importing IcoImagePlugin +DEBUG:PIL.Image:Importing ImImagePlugin +DEBUG:PIL.Image:Importing ImtImagePlugin +DEBUG:PIL.Image:Importing IptcImagePlugin +DEBUG:PIL.Image:Importing JpegImagePlugin +DEBUG:PIL.Image:Importing Jpeg2KImagePlugin +DEBUG:PIL.Image:Importing McIdasImagePlugin +DEBUG:PIL.Image:Importing MicImagePlugin +DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing MpegImagePlugin +DEBUG:PIL.Image:Importing MpoImagePlugin +DEBUG:PIL.Image:Importing MspImagePlugin +DEBUG:PIL.Image:Importing PalmImagePlugin +DEBUG:PIL.Image:Importing PcdImagePlugin +DEBUG:PIL.Image:Importing PcxImagePlugin +DEBUG:PIL.Image:Importing PdfImagePlugin +DEBUG:PIL.Image:Importing PixarImagePlugin +DEBUG:PIL.Image:Importing PngImagePlugin +DEBUG:PIL.Image:Importing PpmImagePlugin +DEBUG:PIL.Image:Importing PsdImagePlugin +DEBUG:PIL.Image:Importing QoiImagePlugin +DEBUG:PIL.Image:Importing SgiImagePlugin +DEBUG:PIL.Image:Importing SpiderImagePlugin +DEBUG:PIL.Image:Importing SunImagePlugin +DEBUG:PIL.Image:Importing TgaImagePlugin +DEBUG:PIL.Image:Importing TiffImagePlugin +DEBUG:PIL.Image:Importing WebPImagePlugin +DEBUG:PIL.Image:Importing WmfImagePlugin +DEBUG:PIL.Image:Importing XbmImagePlugin +DEBUG:PIL.Image:Importing XpmImagePlugin +DEBUG:PIL.Image:Importing XVThumbImagePlugin + 14%|█▍ | 1/7 [01:15<07:34, 75.70s/it] 29%|██▊ | 2/7 [02:31<06:18, 75.65s/it] 43%|████▎ | 3/7 [03:46<05:02, 75.52s/it] 57%|█████▋ | 4/7 [05:02<03:46, 75.47s/it] 71%|███████▏ | 5/7 [06:17<02:30, 75.40s/it] 86%|████████▌ | 6/7 [07:32<01:15, 75.37s/it] 100%|██████████| 7/7 [08:48<00:00, 75.38s/it] 100%|██████████| 7/7 [08:48<00:00, 75.44s/it] +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 1: generating actions ... +>>> Step 1: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 2: generating actions ... +>>> Step 2: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 3: generating actions ... +>>> Step 3: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 4: generating actions ... +>>> Step 4: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 5: generating actions ... +>>> Step 5: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 6: generating actions ... +>>> Step 6: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> + +real 10m26.533s +user 43m2.531s +sys 0m41.416s +2026-02-11 21:46:41.375935: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. +2026-02-11 21:46:41.426557: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered +2026-02-11 21:46:41.426614: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered +2026-02-11 21:46:41.427937: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered +2026-02-11 21:46:41.435507: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. +To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. +2026-02-11 21:46:42.361310: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT +Global seed set to 123 +INFO:mainlogger:LatentVisualDiffusion: Running in v-prediction mode +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +AE working on z of shape (1, 4, 32, 32) = 4096 dimensions. +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +>>> model checkpoint loaded. +>>> Load pre-trained model ... +INFO:root:***** Configing Data ***** +>>> unitree_z1_stackbox: 1 data samples loaded. +>>> unitree_z1_stackbox: data stats loaded. +>>> unitree_z1_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox: data stats loaded. +>>> unitree_z1_dual_arm_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox_v2: data stats loaded. +>>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated. +>>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated. +>>> unitree_g1_pack_camera: 1 data samples loaded. +>>> unitree_g1_pack_camera: data stats loaded. +>>> unitree_g1_pack_camera: normalizer initiated. +>>> Dataset is successfully loaded ... +>>> Generate 16 frames under each generation ... +DEBUG:h5py._conv:Creating converter from 3 to 5 +DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13 +DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9 +DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096 + 0%| | 0/7 [00:00>> Step 0: generating actions ... +>>> Step 0: interacting with world model ... +DEBUG:PIL.Image:Importing BlpImagePlugin +DEBUG:PIL.Image:Importing BmpImagePlugin +DEBUG:PIL.Image:Importing BufrStubImagePlugin +DEBUG:PIL.Image:Importing CurImagePlugin +DEBUG:PIL.Image:Importing DcxImagePlugin +DEBUG:PIL.Image:Importing DdsImagePlugin +DEBUG:PIL.Image:Importing EpsImagePlugin +DEBUG:PIL.Image:Importing FitsImagePlugin +DEBUG:PIL.Image:Importing FitsStubImagePlugin +DEBUG:PIL.Image:Importing FliImagePlugin +DEBUG:PIL.Image:Importing FpxImagePlugin +DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing FtexImagePlugin +DEBUG:PIL.Image:Importing GbrImagePlugin +DEBUG:PIL.Image:Importing GifImagePlugin +DEBUG:PIL.Image:Importing GribStubImagePlugin +DEBUG:PIL.Image:Importing Hdf5StubImagePlugin +DEBUG:PIL.Image:Importing IcnsImagePlugin +DEBUG:PIL.Image:Importing IcoImagePlugin +DEBUG:PIL.Image:Importing ImImagePlugin +DEBUG:PIL.Image:Importing ImtImagePlugin +DEBUG:PIL.Image:Importing IptcImagePlugin +DEBUG:PIL.Image:Importing JpegImagePlugin +DEBUG:PIL.Image:Importing Jpeg2KImagePlugin +DEBUG:PIL.Image:Importing McIdasImagePlugin +DEBUG:PIL.Image:Importing MicImagePlugin +DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing MpegImagePlugin +DEBUG:PIL.Image:Importing MpoImagePlugin +DEBUG:PIL.Image:Importing MspImagePlugin +DEBUG:PIL.Image:Importing PalmImagePlugin +DEBUG:PIL.Image:Importing PcdImagePlugin +DEBUG:PIL.Image:Importing PcxImagePlugin +DEBUG:PIL.Image:Importing PdfImagePlugin +DEBUG:PIL.Image:Importing PixarImagePlugin +DEBUG:PIL.Image:Importing PngImagePlugin +DEBUG:PIL.Image:Importing PpmImagePlugin +DEBUG:PIL.Image:Importing PsdImagePlugin +DEBUG:PIL.Image:Importing QoiImagePlugin +DEBUG:PIL.Image:Importing SgiImagePlugin +DEBUG:PIL.Image:Importing SpiderImagePlugin +DEBUG:PIL.Image:Importing SunImagePlugin +DEBUG:PIL.Image:Importing TgaImagePlugin +DEBUG:PIL.Image:Importing TiffImagePlugin +DEBUG:PIL.Image:Importing WebPImagePlugin +DEBUG:PIL.Image:Importing WmfImagePlugin +DEBUG:PIL.Image:Importing XbmImagePlugin +DEBUG:PIL.Image:Importing XpmImagePlugin +DEBUG:PIL.Image:Importing XVThumbImagePlugin + 14%|█▍ | 1/7 [01:16<07:38, 76.39s/it] 29%|██▊ | 2/7 [02:33<06:23, 76.69s/it] 43%|████▎ | 3/7 [03:50<05:07, 76.87s/it] 57%|█████▋ | 4/7 [05:07<03:50, 76.91s/it] 71%|███████▏ | 5/7 [06:23<02:33, 76.80s/it] 86%|████████▌ | 6/7 [07:40<01:16, 76.77s/it] 100%|██████████| 7/7 [08:57<00:00, 76.85s/it] 100%|██████████| 7/7 [08:57<00:00, 76.81s/it] +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 1: generating actions ... +>>> Step 1: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 2: generating actions ... +>>> Step 2: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 3: generating actions ... +>>> Step 3: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 4: generating actions ... +>>> Step 4: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 5: generating actions ... +>>> Step 5: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 6: generating actions ... +>>> Step 6: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> + +real 10m36.315s +user 42m52.218s +sys 0m42.198s +2026-02-11 21:57:17.623993: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. +2026-02-11 21:57:17.673835: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered +2026-02-11 21:57:17.673891: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered +2026-02-11 21:57:17.675211: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered +2026-02-11 21:57:17.682716: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. +To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. +2026-02-11 21:57:18.593525: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT +Global seed set to 123 +INFO:mainlogger:LatentVisualDiffusion: Running in v-prediction mode +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +AE working on z of shape (1, 4, 32, 32) = 4096 dimensions. +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +>>> model checkpoint loaded. +>>> Load pre-trained model ... +INFO:root:***** Configing Data ***** +>>> unitree_z1_stackbox: 1 data samples loaded. +>>> unitree_z1_stackbox: data stats loaded. +>>> unitree_z1_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox: data stats loaded. +>>> unitree_z1_dual_arm_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox_v2: data stats loaded. +>>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated. +>>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated. +>>> unitree_g1_pack_camera: 1 data samples loaded. +>>> unitree_g1_pack_camera: data stats loaded. +>>> unitree_g1_pack_camera: normalizer initiated. +>>> Dataset is successfully loaded ... +>>> Generate 16 frames under each generation ... +DEBUG:h5py._conv:Creating converter from 3 to 5 +DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13 +DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9 +DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096 + 0%| | 0/7 [00:00>> Step 0: generating actions ... +>>> Step 0: interacting with world model ... +DEBUG:PIL.Image:Importing BlpImagePlugin +DEBUG:PIL.Image:Importing BmpImagePlugin +DEBUG:PIL.Image:Importing BufrStubImagePlugin +DEBUG:PIL.Image:Importing CurImagePlugin +DEBUG:PIL.Image:Importing DcxImagePlugin +DEBUG:PIL.Image:Importing DdsImagePlugin +DEBUG:PIL.Image:Importing EpsImagePlugin +DEBUG:PIL.Image:Importing FitsImagePlugin +DEBUG:PIL.Image:Importing FitsStubImagePlugin +DEBUG:PIL.Image:Importing FliImagePlugin +DEBUG:PIL.Image:Importing FpxImagePlugin +DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing FtexImagePlugin +DEBUG:PIL.Image:Importing GbrImagePlugin +DEBUG:PIL.Image:Importing GifImagePlugin +DEBUG:PIL.Image:Importing GribStubImagePlugin +DEBUG:PIL.Image:Importing Hdf5StubImagePlugin +DEBUG:PIL.Image:Importing IcnsImagePlugin +DEBUG:PIL.Image:Importing IcoImagePlugin +DEBUG:PIL.Image:Importing ImImagePlugin +DEBUG:PIL.Image:Importing ImtImagePlugin +DEBUG:PIL.Image:Importing IptcImagePlugin +DEBUG:PIL.Image:Importing JpegImagePlugin +DEBUG:PIL.Image:Importing Jpeg2KImagePlugin +DEBUG:PIL.Image:Importing McIdasImagePlugin +DEBUG:PIL.Image:Importing MicImagePlugin +DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing MpegImagePlugin +DEBUG:PIL.Image:Importing MpoImagePlugin +DEBUG:PIL.Image:Importing MspImagePlugin +DEBUG:PIL.Image:Importing PalmImagePlugin +DEBUG:PIL.Image:Importing PcdImagePlugin +DEBUG:PIL.Image:Importing PcxImagePlugin +DEBUG:PIL.Image:Importing PdfImagePlugin +DEBUG:PIL.Image:Importing PixarImagePlugin +DEBUG:PIL.Image:Importing PngImagePlugin +DEBUG:PIL.Image:Importing PpmImagePlugin +DEBUG:PIL.Image:Importing PsdImagePlugin +DEBUG:PIL.Image:Importing QoiImagePlugin +DEBUG:PIL.Image:Importing SgiImagePlugin +DEBUG:PIL.Image:Importing SpiderImagePlugin +DEBUG:PIL.Image:Importing SunImagePlugin +DEBUG:PIL.Image:Importing TgaImagePlugin +DEBUG:PIL.Image:Importing TiffImagePlugin +DEBUG:PIL.Image:Importing WebPImagePlugin +DEBUG:PIL.Image:Importing WmfImagePlugin +DEBUG:PIL.Image:Importing XbmImagePlugin +DEBUG:PIL.Image:Importing XpmImagePlugin +DEBUG:PIL.Image:Importing XVThumbImagePlugin + 14%|█▍ | 1/7 [01:15<07:33, 75.59s/it] 29%|██▊ | 2/7 [02:31<06:17, 75.59s/it] 43%|████▎ | 3/7 [03:46<05:01, 75.44s/it] 57%|█████▋ | 4/7 [05:01<03:46, 75.39s/it] 71%|███████▏ | 5/7 [06:17<02:30, 75.35s/it] 86%|████████▌ | 6/7 [07:32<01:15, 75.32s/it] 100%|██████████| 7/7 [08:47<00:00, 75.24s/it] 100%|██████████| 7/7 [08:47<00:00, 75.34s/it] +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 1: generating actions ... +>>> Step 1: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 2: generating actions ... +>>> Step 2: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 3: generating actions ... +>>> Step 3: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 4: generating actions ... +>>> Step 4: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 5: generating actions ... +>>> Step 5: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 6: generating actions ... +>>> Step 6: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> + +real 10m25.792s +user 43m2.308s +sys 0m41.819s +2026-02-11 22:07:43.398736: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. +2026-02-11 22:07:43.448264: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered +2026-02-11 22:07:43.448321: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered +2026-02-11 22:07:43.449636: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered +2026-02-11 22:07:43.457127: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. +To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. +2026-02-11 22:07:44.370935: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT +Global seed set to 123 +INFO:mainlogger:LatentVisualDiffusion: Running in v-prediction mode +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +AE working on z of shape (1, 4, 32, 32) = 4096 dimensions. +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +>>> model checkpoint loaded. +>>> Load pre-trained model ... +INFO:root:***** Configing Data ***** +>>> unitree_z1_stackbox: 1 data samples loaded. +>>> unitree_z1_stackbox: data stats loaded. +>>> unitree_z1_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox: data stats loaded. +>>> unitree_z1_dual_arm_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox_v2: data stats loaded. +>>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated. +>>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated. +>>> unitree_g1_pack_camera: 1 data samples loaded. +>>> unitree_g1_pack_camera: data stats loaded. +>>> unitree_g1_pack_camera: normalizer initiated. +>>> Dataset is successfully loaded ... +>>> Generate 16 frames under each generation ... +DEBUG:h5py._conv:Creating converter from 3 to 5 +DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13 +DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9 +DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096 + 0%| | 0/7 [00:00>> Step 0: generating actions ... +>>> Step 0: interacting with world model ... +DEBUG:PIL.Image:Importing BlpImagePlugin +DEBUG:PIL.Image:Importing BmpImagePlugin +DEBUG:PIL.Image:Importing BufrStubImagePlugin +DEBUG:PIL.Image:Importing CurImagePlugin +DEBUG:PIL.Image:Importing DcxImagePlugin +DEBUG:PIL.Image:Importing DdsImagePlugin +DEBUG:PIL.Image:Importing EpsImagePlugin +DEBUG:PIL.Image:Importing FitsImagePlugin +DEBUG:PIL.Image:Importing FitsStubImagePlugin +DEBUG:PIL.Image:Importing FliImagePlugin +DEBUG:PIL.Image:Importing FpxImagePlugin +DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing FtexImagePlugin +DEBUG:PIL.Image:Importing GbrImagePlugin +DEBUG:PIL.Image:Importing GifImagePlugin +DEBUG:PIL.Image:Importing GribStubImagePlugin +DEBUG:PIL.Image:Importing Hdf5StubImagePlugin +DEBUG:PIL.Image:Importing IcnsImagePlugin +DEBUG:PIL.Image:Importing IcoImagePlugin +DEBUG:PIL.Image:Importing ImImagePlugin +DEBUG:PIL.Image:Importing ImtImagePlugin +DEBUG:PIL.Image:Importing IptcImagePlugin +DEBUG:PIL.Image:Importing JpegImagePlugin +DEBUG:PIL.Image:Importing Jpeg2KImagePlugin +DEBUG:PIL.Image:Importing McIdasImagePlugin +DEBUG:PIL.Image:Importing MicImagePlugin +DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing MpegImagePlugin +DEBUG:PIL.Image:Importing MpoImagePlugin +DEBUG:PIL.Image:Importing MspImagePlugin +DEBUG:PIL.Image:Importing PalmImagePlugin +DEBUG:PIL.Image:Importing PcdImagePlugin +DEBUG:PIL.Image:Importing PcxImagePlugin +DEBUG:PIL.Image:Importing PdfImagePlugin +DEBUG:PIL.Image:Importing PixarImagePlugin +DEBUG:PIL.Image:Importing PngImagePlugin +DEBUG:PIL.Image:Importing PpmImagePlugin +DEBUG:PIL.Image:Importing PsdImagePlugin +DEBUG:PIL.Image:Importing QoiImagePlugin +DEBUG:PIL.Image:Importing SgiImagePlugin +DEBUG:PIL.Image:Importing SpiderImagePlugin +DEBUG:PIL.Image:Importing SunImagePlugin +DEBUG:PIL.Image:Importing TgaImagePlugin +DEBUG:PIL.Image:Importing TiffImagePlugin +DEBUG:PIL.Image:Importing WebPImagePlugin +DEBUG:PIL.Image:Importing WmfImagePlugin +DEBUG:PIL.Image:Importing XbmImagePlugin +DEBUG:PIL.Image:Importing XpmImagePlugin +DEBUG:PIL.Image:Importing XVThumbImagePlugin + 14%|█▍ | 1/7 [01:17<07:42, 77.04s/it] 29%|██▊ | 2/7 [02:33<06:24, 76.95s/it] 43%|████▎ | 3/7 [03:50<05:07, 76.87s/it] 57%|█████▋ | 4/7 [05:06<03:49, 76.59s/it] 71%|███████▏ | 5/7 [06:24<02:33, 76.82s/it] 86%|████████▌ | 6/7 [07:39<01:16, 76.43s/it] 100%|██████████| 7/7 [08:55<00:00, 76.06s/it] 100%|██████████| 7/7 [08:55<00:00, 76.44s/it] +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 1: generating actions ... +>>> Step 1: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 2: generating actions ... +>>> Step 2: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 3: generating actions ... +>>> Step 3: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 4: generating actions ... +>>> Step 4: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 5: generating actions ... +>>> Step 5: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 6: generating actions ... +>>> Step 6: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> + +real 10m33.965s +user 42m57.756s +sys 0m41.772s +2026-02-11 22:18:17.396072: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. +2026-02-11 22:18:17.446095: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered +2026-02-11 22:18:17.446154: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered +2026-02-11 22:18:17.447480: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered +2026-02-11 22:18:17.455025: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. +To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. +2026-02-11 22:18:18.367007: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT +Global seed set to 123 +INFO:mainlogger:LatentVisualDiffusion: Running in v-prediction mode +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +AE working on z of shape (1, 4, 32, 32) = 4096 dimensions. +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +>>> model checkpoint loaded. +>>> Load pre-trained model ... +INFO:root:***** Configing Data ***** +>>> unitree_z1_stackbox: 1 data samples loaded. +>>> unitree_z1_stackbox: data stats loaded. +>>> unitree_z1_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox: data stats loaded. +>>> unitree_z1_dual_arm_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox_v2: data stats loaded. +>>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated. +>>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated. +>>> unitree_g1_pack_camera: 1 data samples loaded. +>>> unitree_g1_pack_camera: data stats loaded. +>>> unitree_g1_pack_camera: normalizer initiated. +>>> Dataset is successfully loaded ... +>>> Generate 16 frames under each generation ... +DEBUG:h5py._conv:Creating converter from 3 to 5 +DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13 +DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9 +DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096 + 0%| | 0/11 [00:00>> Step 0: generating actions ... +>>> Step 0: interacting with world model ... +DEBUG:PIL.Image:Importing BlpImagePlugin +DEBUG:PIL.Image:Importing BmpImagePlugin +DEBUG:PIL.Image:Importing BufrStubImagePlugin +DEBUG:PIL.Image:Importing CurImagePlugin +DEBUG:PIL.Image:Importing DcxImagePlugin +DEBUG:PIL.Image:Importing DdsImagePlugin +DEBUG:PIL.Image:Importing EpsImagePlugin +DEBUG:PIL.Image:Importing FitsImagePlugin +DEBUG:PIL.Image:Importing FitsStubImagePlugin +DEBUG:PIL.Image:Importing FliImagePlugin +DEBUG:PIL.Image:Importing FpxImagePlugin +DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing FtexImagePlugin +DEBUG:PIL.Image:Importing GbrImagePlugin +DEBUG:PIL.Image:Importing GifImagePlugin +DEBUG:PIL.Image:Importing GribStubImagePlugin +DEBUG:PIL.Image:Importing Hdf5StubImagePlugin +DEBUG:PIL.Image:Importing IcnsImagePlugin +DEBUG:PIL.Image:Importing IcoImagePlugin +DEBUG:PIL.Image:Importing ImImagePlugin +DEBUG:PIL.Image:Importing ImtImagePlugin +DEBUG:PIL.Image:Importing IptcImagePlugin +DEBUG:PIL.Image:Importing JpegImagePlugin +DEBUG:PIL.Image:Importing Jpeg2KImagePlugin +DEBUG:PIL.Image:Importing McIdasImagePlugin +DEBUG:PIL.Image:Importing MicImagePlugin +DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing MpegImagePlugin +DEBUG:PIL.Image:Importing MpoImagePlugin +DEBUG:PIL.Image:Importing MspImagePlugin +DEBUG:PIL.Image:Importing PalmImagePlugin +DEBUG:PIL.Image:Importing PcdImagePlugin +DEBUG:PIL.Image:Importing PcxImagePlugin +DEBUG:PIL.Image:Importing PdfImagePlugin +DEBUG:PIL.Image:Importing PixarImagePlugin +DEBUG:PIL.Image:Importing PngImagePlugin +DEBUG:PIL.Image:Importing PpmImagePlugin +DEBUG:PIL.Image:Importing PsdImagePlugin +DEBUG:PIL.Image:Importing QoiImagePlugin +DEBUG:PIL.Image:Importing SgiImagePlugin +DEBUG:PIL.Image:Importing SpiderImagePlugin +DEBUG:PIL.Image:Importing SunImagePlugin +DEBUG:PIL.Image:Importing TgaImagePlugin +DEBUG:PIL.Image:Importing TiffImagePlugin +DEBUG:PIL.Image:Importing WebPImagePlugin +DEBUG:PIL.Image:Importing WmfImagePlugin +DEBUG:PIL.Image:Importing XbmImagePlugin +DEBUG:PIL.Image:Importing XpmImagePlugin +DEBUG:PIL.Image:Importing XVThumbImagePlugin + 9%|▉ | 1/11 [01:15<12:35, 75.53s/it] 18%|█▊ | 2/11 [02:30<11:18, 75.39s/it] 27%|██▋ | 3/11 [03:46<10:03, 75.38s/it] 36%|███▋ | 4/11 [05:01<08:48, 75.47s/it] 45%|████▌ | 5/11 [06:16<07:31, 75.32s/it] 55%|█████▍ | 6/11 [07:31<06:15, 75.08s/it] 64%|██████▎ | 7/11 [08:46<05:00, 75.07s/it] 73%|███████▎ | 8/11 [10:00<03:44, 74.76s/it] 82%|████████▏ | 9/11 [11:15<02:29, 74.87s/it] 91%|█████████ | 10/11 [12:30<01:14, 74.79s/it] 100%|██████████| 11/11 [13:45<00:00, 74.80s/it] 100%|██████████| 11/11 [13:45<00:00, 75.02s/it] +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 1: generating actions ... +>>> Step 1: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 2: generating actions ... +>>> Step 2: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 3: generating actions ... +>>> Step 3: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 4: generating actions ... +>>> Step 4: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 5: generating actions ... +>>> Step 5: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 6: generating actions ... +>>> Step 6: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 7: generating actions ... +>>> Step 7: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 8: generating actions ... +>>> Step 8: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 9: generating actions ... +>>> Step 9: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 10: generating actions ... +>>> Step 10: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> + +real 15m24.880s +user 65m40.817s +sys 0m41.445s +2026-02-11 22:33:42.261398: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. +2026-02-11 22:33:42.310786: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered +2026-02-11 22:33:42.310845: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered +2026-02-11 22:33:42.312191: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered +2026-02-11 22:33:42.319738: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. +To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. +2026-02-11 22:33:43.232517: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT +Global seed set to 123 +INFO:mainlogger:LatentVisualDiffusion: Running in v-prediction mode +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +AE working on z of shape (1, 4, 32, 32) = 4096 dimensions. +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +>>> model checkpoint loaded. +>>> Load pre-trained model ... +INFO:root:***** Configing Data ***** +>>> unitree_z1_stackbox: 1 data samples loaded. +>>> unitree_z1_stackbox: data stats loaded. +>>> unitree_z1_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox: data stats loaded. +>>> unitree_z1_dual_arm_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox_v2: data stats loaded. +>>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated. +>>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated. +>>> unitree_g1_pack_camera: 1 data samples loaded. +>>> unitree_g1_pack_camera: data stats loaded. +>>> unitree_g1_pack_camera: normalizer initiated. +>>> Dataset is successfully loaded ... +>>> Generate 16 frames under each generation ... +DEBUG:h5py._conv:Creating converter from 3 to 5 +DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13 +DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9 +DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096 + 0%| | 0/11 [00:00>> Step 0: generating actions ... +>>> Step 0: interacting with world model ... +DEBUG:PIL.Image:Importing BlpImagePlugin +DEBUG:PIL.Image:Importing BmpImagePlugin +DEBUG:PIL.Image:Importing BufrStubImagePlugin +DEBUG:PIL.Image:Importing CurImagePlugin +DEBUG:PIL.Image:Importing DcxImagePlugin +DEBUG:PIL.Image:Importing DdsImagePlugin +DEBUG:PIL.Image:Importing EpsImagePlugin +DEBUG:PIL.Image:Importing FitsImagePlugin +DEBUG:PIL.Image:Importing FitsStubImagePlugin +DEBUG:PIL.Image:Importing FliImagePlugin +DEBUG:PIL.Image:Importing FpxImagePlugin +DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing FtexImagePlugin +DEBUG:PIL.Image:Importing GbrImagePlugin +DEBUG:PIL.Image:Importing GifImagePlugin +DEBUG:PIL.Image:Importing GribStubImagePlugin +DEBUG:PIL.Image:Importing Hdf5StubImagePlugin +DEBUG:PIL.Image:Importing IcnsImagePlugin +DEBUG:PIL.Image:Importing IcoImagePlugin +DEBUG:PIL.Image:Importing ImImagePlugin +DEBUG:PIL.Image:Importing ImtImagePlugin +DEBUG:PIL.Image:Importing IptcImagePlugin +DEBUG:PIL.Image:Importing JpegImagePlugin +DEBUG:PIL.Image:Importing Jpeg2KImagePlugin +DEBUG:PIL.Image:Importing McIdasImagePlugin +DEBUG:PIL.Image:Importing MicImagePlugin +DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing MpegImagePlugin +DEBUG:PIL.Image:Importing MpoImagePlugin +DEBUG:PIL.Image:Importing MspImagePlugin +DEBUG:PIL.Image:Importing PalmImagePlugin +DEBUG:PIL.Image:Importing PcdImagePlugin +DEBUG:PIL.Image:Importing PcxImagePlugin +DEBUG:PIL.Image:Importing PdfImagePlugin +DEBUG:PIL.Image:Importing PixarImagePlugin +DEBUG:PIL.Image:Importing PngImagePlugin +DEBUG:PIL.Image:Importing PpmImagePlugin +DEBUG:PIL.Image:Importing PsdImagePlugin +DEBUG:PIL.Image:Importing QoiImagePlugin +DEBUG:PIL.Image:Importing SgiImagePlugin +DEBUG:PIL.Image:Importing SpiderImagePlugin +DEBUG:PIL.Image:Importing SunImagePlugin +DEBUG:PIL.Image:Importing TgaImagePlugin +DEBUG:PIL.Image:Importing TiffImagePlugin +DEBUG:PIL.Image:Importing WebPImagePlugin +DEBUG:PIL.Image:Importing WmfImagePlugin +DEBUG:PIL.Image:Importing XbmImagePlugin +DEBUG:PIL.Image:Importing XpmImagePlugin +DEBUG:PIL.Image:Importing XVThumbImagePlugin + 9%|▉ | 1/11 [01:13<12:18, 73.90s/it] 18%|█▊ | 2/11 [02:27<11:05, 73.99s/it] 27%|██▋ | 3/11 [03:41<09:50, 73.86s/it] 36%|███▋ | 4/11 [04:55<08:35, 73.70s/it] 45%|████▌ | 5/11 [06:08<07:20, 73.48s/it] 55%|█████▍ | 6/11 [07:21<06:06, 73.39s/it] 64%|██████▎ | 7/11 [08:34<04:53, 73.28s/it] 73%|███████▎ | 8/11 [09:47<03:39, 73.11s/it] 82%|████████▏ | 9/11 [11:00<02:26, 73.21s/it] 91%|█████████ | 10/11 [12:14<01:13, 73.49s/it] 100%|██████████| 11/11 [13:28<00:00, 73.55s/it] 100%|██████████| 11/11 [13:28<00:00, 73.50s/it] +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 1: generating actions ... +>>> Step 1: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 2: generating actions ... +>>> Step 2: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 3: generating actions ... +>>> Step 3: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 4: generating actions ... +>>> Step 4: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 5: generating actions ... +>>> Step 5: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 6: generating actions ... +>>> Step 6: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 7: generating actions ... +>>> Step 7: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 8: generating actions ... +>>> Step 8: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 9: generating actions ... +>>> Step 9: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 10: generating actions ... +>>> Step 10: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> + +real 15m7.472s +user 65m58.841s +sys 0m41.599s +2026-02-11 22:48:49.761688: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. +2026-02-11 22:48:49.811395: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered +2026-02-11 22:48:49.811456: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered +2026-02-11 22:48:49.812798: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered +2026-02-11 22:48:49.820307: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. +To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. +2026-02-11 22:48:50.732941: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT +Global seed set to 123 +INFO:mainlogger:LatentVisualDiffusion: Running in v-prediction mode +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +AE working on z of shape (1, 4, 32, 32) = 4096 dimensions. +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +>>> model checkpoint loaded. +>>> Load pre-trained model ... +INFO:root:***** Configing Data ***** +>>> unitree_z1_stackbox: 1 data samples loaded. +>>> unitree_z1_stackbox: data stats loaded. +>>> unitree_z1_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox: data stats loaded. +>>> unitree_z1_dual_arm_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox_v2: data stats loaded. +>>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated. +>>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated. +>>> unitree_g1_pack_camera: 1 data samples loaded. +>>> unitree_g1_pack_camera: data stats loaded. +>>> unitree_g1_pack_camera: normalizer initiated. +>>> Dataset is successfully loaded ... +>>> Generate 16 frames under each generation ... +DEBUG:h5py._conv:Creating converter from 3 to 5 +DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13 +DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9 +DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096 + 0%| | 0/11 [00:00>> Step 0: generating actions ... +>>> Step 0: interacting with world model ... +DEBUG:PIL.Image:Importing BlpImagePlugin +DEBUG:PIL.Image:Importing BmpImagePlugin +DEBUG:PIL.Image:Importing BufrStubImagePlugin +DEBUG:PIL.Image:Importing CurImagePlugin +DEBUG:PIL.Image:Importing DcxImagePlugin +DEBUG:PIL.Image:Importing DdsImagePlugin +DEBUG:PIL.Image:Importing EpsImagePlugin +DEBUG:PIL.Image:Importing FitsImagePlugin +DEBUG:PIL.Image:Importing FitsStubImagePlugin +DEBUG:PIL.Image:Importing FliImagePlugin +DEBUG:PIL.Image:Importing FpxImagePlugin +DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing FtexImagePlugin +DEBUG:PIL.Image:Importing GbrImagePlugin +DEBUG:PIL.Image:Importing GifImagePlugin +DEBUG:PIL.Image:Importing GribStubImagePlugin +DEBUG:PIL.Image:Importing Hdf5StubImagePlugin +DEBUG:PIL.Image:Importing IcnsImagePlugin +DEBUG:PIL.Image:Importing IcoImagePlugin +DEBUG:PIL.Image:Importing ImImagePlugin +DEBUG:PIL.Image:Importing ImtImagePlugin +DEBUG:PIL.Image:Importing IptcImagePlugin +DEBUG:PIL.Image:Importing JpegImagePlugin +DEBUG:PIL.Image:Importing Jpeg2KImagePlugin +DEBUG:PIL.Image:Importing McIdasImagePlugin +DEBUG:PIL.Image:Importing MicImagePlugin +DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing MpegImagePlugin +DEBUG:PIL.Image:Importing MpoImagePlugin +DEBUG:PIL.Image:Importing MspImagePlugin +DEBUG:PIL.Image:Importing PalmImagePlugin +DEBUG:PIL.Image:Importing PcdImagePlugin +DEBUG:PIL.Image:Importing PcxImagePlugin +DEBUG:PIL.Image:Importing PdfImagePlugin +DEBUG:PIL.Image:Importing PixarImagePlugin +DEBUG:PIL.Image:Importing PngImagePlugin +DEBUG:PIL.Image:Importing PpmImagePlugin +DEBUG:PIL.Image:Importing PsdImagePlugin +DEBUG:PIL.Image:Importing QoiImagePlugin +DEBUG:PIL.Image:Importing SgiImagePlugin +DEBUG:PIL.Image:Importing SpiderImagePlugin +DEBUG:PIL.Image:Importing SunImagePlugin +DEBUG:PIL.Image:Importing TgaImagePlugin +DEBUG:PIL.Image:Importing TiffImagePlugin +DEBUG:PIL.Image:Importing WebPImagePlugin +DEBUG:PIL.Image:Importing WmfImagePlugin +DEBUG:PIL.Image:Importing XbmImagePlugin +DEBUG:PIL.Image:Importing XpmImagePlugin +DEBUG:PIL.Image:Importing XVThumbImagePlugin + 9%|▉ | 1/11 [01:14<12:29, 74.99s/it] 18%|█▊ | 2/11 [02:30<11:18, 75.44s/it] 27%|██▋ | 3/11 [03:46<10:03, 75.49s/it] 36%|███▋ | 4/11 [05:01<08:47, 75.30s/it] 45%|████▌ | 5/11 [06:15<07:30, 75.02s/it] 55%|█████▍ | 6/11 [07:30<06:14, 74.84s/it] 64%|██████▎ | 7/11 [08:44<04:59, 74.79s/it] 73%|███████▎ | 8/11 [10:00<03:44, 74.94s/it] 82%|████████▏ | 9/11 [11:15<02:29, 74.89s/it] 91%|█████████ | 10/11 [12:30<01:14, 74.95s/it] 100%|██████████| 11/11 [13:45<00:00, 74.95s/it] 100%|██████████| 11/11 [13:45<00:00, 75.01s/it] +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 1: generating actions ... +>>> Step 1: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 2: generating actions ... +>>> Step 2: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 3: generating actions ... +>>> Step 3: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 4: generating actions ... +>>> Step 4: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 5: generating actions ... +>>> Step 5: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 6: generating actions ... +>>> Step 6: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 7: generating actions ... +>>> Step 7: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 8: generating actions ... +>>> Step 8: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 9: generating actions ... +>>> Step 9: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 10: generating actions ... +>>> Step 10: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> + +real 15m26.006s +user 65m35.774s +sys 0m44.636s +2026-02-11 23:04:15.762959: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. +2026-02-11 23:04:15.814243: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered +2026-02-11 23:04:15.814301: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered +2026-02-11 23:04:15.815653: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered +2026-02-11 23:04:15.823287: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. +To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. +2026-02-11 23:04:16.742609: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT +Global seed set to 123 +INFO:mainlogger:LatentVisualDiffusion: Running in v-prediction mode +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +AE working on z of shape (1, 4, 32, 32) = 4096 dimensions. +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +>>> model checkpoint loaded. +>>> Load pre-trained model ... +INFO:root:***** Configing Data ***** +>>> unitree_z1_stackbox: 1 data samples loaded. +>>> unitree_z1_stackbox: data stats loaded. +>>> unitree_z1_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox: data stats loaded. +>>> unitree_z1_dual_arm_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox_v2: data stats loaded. +>>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated. +>>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated. +>>> unitree_g1_pack_camera: 1 data samples loaded. +>>> unitree_g1_pack_camera: data stats loaded. +>>> unitree_g1_pack_camera: normalizer initiated. +>>> Dataset is successfully loaded ... +>>> Generate 16 frames under each generation ... +DEBUG:h5py._conv:Creating converter from 3 to 5 +DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13 +DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9 +DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096 + 0%| | 0/11 [00:00>> Step 0: generating actions ... +>>> Step 0: interacting with world model ... +DEBUG:PIL.Image:Importing BlpImagePlugin +DEBUG:PIL.Image:Importing BmpImagePlugin +DEBUG:PIL.Image:Importing BufrStubImagePlugin +DEBUG:PIL.Image:Importing CurImagePlugin +DEBUG:PIL.Image:Importing DcxImagePlugin +DEBUG:PIL.Image:Importing DdsImagePlugin +DEBUG:PIL.Image:Importing EpsImagePlugin +DEBUG:PIL.Image:Importing FitsImagePlugin +DEBUG:PIL.Image:Importing FitsStubImagePlugin +DEBUG:PIL.Image:Importing FliImagePlugin +DEBUG:PIL.Image:Importing FpxImagePlugin +DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing FtexImagePlugin +DEBUG:PIL.Image:Importing GbrImagePlugin +DEBUG:PIL.Image:Importing GifImagePlugin +DEBUG:PIL.Image:Importing GribStubImagePlugin +DEBUG:PIL.Image:Importing Hdf5StubImagePlugin +DEBUG:PIL.Image:Importing IcnsImagePlugin +DEBUG:PIL.Image:Importing IcoImagePlugin +DEBUG:PIL.Image:Importing ImImagePlugin +DEBUG:PIL.Image:Importing ImtImagePlugin +DEBUG:PIL.Image:Importing IptcImagePlugin +DEBUG:PIL.Image:Importing JpegImagePlugin +DEBUG:PIL.Image:Importing Jpeg2KImagePlugin +DEBUG:PIL.Image:Importing McIdasImagePlugin +DEBUG:PIL.Image:Importing MicImagePlugin +DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing MpegImagePlugin +DEBUG:PIL.Image:Importing MpoImagePlugin +DEBUG:PIL.Image:Importing MspImagePlugin +DEBUG:PIL.Image:Importing PalmImagePlugin +DEBUG:PIL.Image:Importing PcdImagePlugin +DEBUG:PIL.Image:Importing PcxImagePlugin +DEBUG:PIL.Image:Importing PdfImagePlugin +DEBUG:PIL.Image:Importing PixarImagePlugin +DEBUG:PIL.Image:Importing PngImagePlugin +DEBUG:PIL.Image:Importing PpmImagePlugin +DEBUG:PIL.Image:Importing PsdImagePlugin +DEBUG:PIL.Image:Importing QoiImagePlugin +DEBUG:PIL.Image:Importing SgiImagePlugin +DEBUG:PIL.Image:Importing SpiderImagePlugin +DEBUG:PIL.Image:Importing SunImagePlugin +DEBUG:PIL.Image:Importing TgaImagePlugin +DEBUG:PIL.Image:Importing TiffImagePlugin +DEBUG:PIL.Image:Importing WebPImagePlugin +DEBUG:PIL.Image:Importing WmfImagePlugin +DEBUG:PIL.Image:Importing XbmImagePlugin +DEBUG:PIL.Image:Importing XpmImagePlugin +DEBUG:PIL.Image:Importing XVThumbImagePlugin + 9%|▉ | 1/11 [01:14<12:25, 74.55s/it] 18%|█▊ | 2/11 [02:29<11:13, 74.83s/it] 27%|██▋ | 3/11 [03:44<09:58, 74.77s/it] 36%|███▋ | 4/11 [04:59<08:43, 74.78s/it] 45%|████▌ | 5/11 [06:13<07:28, 74.83s/it] 55%|█████▍ | 6/11 [07:28<06:13, 74.62s/it] 64%|██████▎ | 7/11 [08:42<04:57, 74.37s/it] 73%|███████▎ | 8/11 [09:56<03:42, 74.28s/it] 82%|████████▏ | 9/11 [11:10<02:28, 74.26s/it] 91%|█████████ | 10/11 [12:24<01:14, 74.31s/it] 100%|██████████| 11/11 [13:39<00:00, 74.38s/it] 100%|██████████| 11/11 [13:39<00:00, 74.48s/it] +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 1: generating actions ... +>>> Step 1: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 2: generating actions ... +>>> Step 2: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 3: generating actions ... +>>> Step 3: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 4: generating actions ... +>>> Step 4: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 5: generating actions ... +>>> Step 5: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 6: generating actions ... +>>> Step 6: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 7: generating actions ... +>>> Step 7: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 8: generating actions ... +>>> Step 8: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 9: generating actions ... +>>> Step 9: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 10: generating actions ... +>>> Step 10: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> + +real 15m20.607s +user 66m10.462s +sys 0m45.655s +2026-02-11 23:19:36.475817: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. +2026-02-11 23:19:36.525118: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered +2026-02-11 23:19:36.525172: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered +2026-02-11 23:19:36.526479: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered +2026-02-11 23:19:36.533981: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. +To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. +2026-02-11 23:19:37.461985: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT +Global seed set to 123 +INFO:mainlogger:LatentVisualDiffusion: Running in v-prediction mode +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +AE working on z of shape (1, 4, 32, 32) = 4096 dimensions. +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +>>> model checkpoint loaded. +>>> Load pre-trained model ... +INFO:root:***** Configing Data ***** +>>> unitree_z1_stackbox: 1 data samples loaded. +>>> unitree_z1_stackbox: data stats loaded. +>>> unitree_z1_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox: data stats loaded. +>>> unitree_z1_dual_arm_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox_v2: data stats loaded. +>>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated. +>>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated. +>>> unitree_g1_pack_camera: 1 data samples loaded. +>>> unitree_g1_pack_camera: data stats loaded. +>>> unitree_g1_pack_camera: normalizer initiated. +>>> Dataset is successfully loaded ... +>>> Generate 16 frames under each generation ... +DEBUG:h5py._conv:Creating converter from 3 to 5 +DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13 +DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9 +DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096 + 0%| | 0/12 [00:00>> Step 0: generating actions ... +>>> Step 0: interacting with world model ... +DEBUG:PIL.Image:Importing BlpImagePlugin +DEBUG:PIL.Image:Importing BmpImagePlugin +DEBUG:PIL.Image:Importing BufrStubImagePlugin +DEBUG:PIL.Image:Importing CurImagePlugin +DEBUG:PIL.Image:Importing DcxImagePlugin +DEBUG:PIL.Image:Importing DdsImagePlugin +DEBUG:PIL.Image:Importing EpsImagePlugin +DEBUG:PIL.Image:Importing FitsImagePlugin +DEBUG:PIL.Image:Importing FitsStubImagePlugin +DEBUG:PIL.Image:Importing FliImagePlugin +DEBUG:PIL.Image:Importing FpxImagePlugin +DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing FtexImagePlugin +DEBUG:PIL.Image:Importing GbrImagePlugin +DEBUG:PIL.Image:Importing GifImagePlugin +DEBUG:PIL.Image:Importing GribStubImagePlugin +DEBUG:PIL.Image:Importing Hdf5StubImagePlugin +DEBUG:PIL.Image:Importing IcnsImagePlugin +DEBUG:PIL.Image:Importing IcoImagePlugin +DEBUG:PIL.Image:Importing ImImagePlugin +DEBUG:PIL.Image:Importing ImtImagePlugin +DEBUG:PIL.Image:Importing IptcImagePlugin +DEBUG:PIL.Image:Importing JpegImagePlugin +DEBUG:PIL.Image:Importing Jpeg2KImagePlugin +DEBUG:PIL.Image:Importing McIdasImagePlugin +DEBUG:PIL.Image:Importing MicImagePlugin +DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing MpegImagePlugin +DEBUG:PIL.Image:Importing MpoImagePlugin +DEBUG:PIL.Image:Importing MspImagePlugin +DEBUG:PIL.Image:Importing PalmImagePlugin +DEBUG:PIL.Image:Importing PcdImagePlugin +DEBUG:PIL.Image:Importing PcxImagePlugin +DEBUG:PIL.Image:Importing PdfImagePlugin +DEBUG:PIL.Image:Importing PixarImagePlugin +DEBUG:PIL.Image:Importing PngImagePlugin +DEBUG:PIL.Image:Importing PpmImagePlugin +DEBUG:PIL.Image:Importing PsdImagePlugin +DEBUG:PIL.Image:Importing QoiImagePlugin +DEBUG:PIL.Image:Importing SgiImagePlugin +DEBUG:PIL.Image:Importing SpiderImagePlugin +DEBUG:PIL.Image:Importing SunImagePlugin +DEBUG:PIL.Image:Importing TgaImagePlugin +DEBUG:PIL.Image:Importing TiffImagePlugin +DEBUG:PIL.Image:Importing WebPImagePlugin +DEBUG:PIL.Image:Importing WmfImagePlugin +DEBUG:PIL.Image:Importing XbmImagePlugin +DEBUG:PIL.Image:Importing XpmImagePlugin +DEBUG:PIL.Image:Importing XVThumbImagePlugin + 8%|▊ | 1/12 [01:14<13:38, 74.37s/it] 17%|█▋ | 2/12 [02:28<12:21, 74.13s/it] 25%|██▌ | 3/12 [03:42<11:05, 73.97s/it] 33%|███▎ | 4/12 [04:55<09:51, 73.92s/it] 42%|████▏ | 5/12 [06:09<08:35, 73.70s/it] 50%|█████ | 6/12 [07:22<07:21, 73.58s/it] 58%|█████▊ | 7/12 [08:35<06:07, 73.49s/it] 67%|██████▋ | 8/12 [09:49<04:53, 73.46s/it] 75%|███████▌ | 9/12 [11:02<03:40, 73.42s/it] 83%|████████▎ | 10/12 [12:16<02:26, 73.44s/it] 92%|█████████▏| 11/12 [13:29<01:13, 73.40s/it] 100%|██████████| 12/12 [14:42<00:00, 73.32s/it] 100%|██████████| 12/12 [14:42<00:00, 73.55s/it] +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 1: generating actions ... +>>> Step 1: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 2: generating actions ... +>>> Step 2: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 3: generating actions ... +>>> Step 3: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 4: generating actions ... +>>> Step 4: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 5: generating actions ... +>>> Step 5: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 6: generating actions ... +>>> Step 6: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 7: generating actions ... +>>> Step 7: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 8: generating actions ... +>>> Step 8: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 9: generating actions ... +>>> Step 9: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 10: generating actions ... +>>> Step 10: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 11: generating actions ... +>>> Step 11: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> + +real 16m18.361s +user 71m2.856s +sys 0m44.193s +2026-02-11 23:35:52.961572: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. +2026-02-11 23:35:53.011562: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered +2026-02-11 23:35:53.011622: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered +2026-02-11 23:35:53.012961: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered +2026-02-11 23:35:53.020520: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. +To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. +2026-02-11 23:35:53.953177: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT +Global seed set to 123 +INFO:mainlogger:LatentVisualDiffusion: Running in v-prediction mode +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +AE working on z of shape (1, 4, 32, 32) = 4096 dimensions. +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +>>> model checkpoint loaded. +>>> Load pre-trained model ... +INFO:root:***** Configing Data ***** +>>> unitree_z1_stackbox: 1 data samples loaded. +>>> unitree_z1_stackbox: data stats loaded. +>>> unitree_z1_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox: data stats loaded. +>>> unitree_z1_dual_arm_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox_v2: data stats loaded. +>>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated. +>>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated. +>>> unitree_g1_pack_camera: 1 data samples loaded. +>>> unitree_g1_pack_camera: data stats loaded. +>>> unitree_g1_pack_camera: normalizer initiated. +>>> Dataset is successfully loaded ... +>>> Generate 16 frames under each generation ... +DEBUG:h5py._conv:Creating converter from 3 to 5 +DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13 +DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9 +DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096 + 0%| | 0/12 [00:00>> Step 0: generating actions ... +>>> Step 0: interacting with world model ... +DEBUG:PIL.Image:Importing BlpImagePlugin +DEBUG:PIL.Image:Importing BmpImagePlugin +DEBUG:PIL.Image:Importing BufrStubImagePlugin +DEBUG:PIL.Image:Importing CurImagePlugin +DEBUG:PIL.Image:Importing DcxImagePlugin +DEBUG:PIL.Image:Importing DdsImagePlugin +DEBUG:PIL.Image:Importing EpsImagePlugin +DEBUG:PIL.Image:Importing FitsImagePlugin +DEBUG:PIL.Image:Importing FitsStubImagePlugin +DEBUG:PIL.Image:Importing FliImagePlugin +DEBUG:PIL.Image:Importing FpxImagePlugin +DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing FtexImagePlugin +DEBUG:PIL.Image:Importing GbrImagePlugin +DEBUG:PIL.Image:Importing GifImagePlugin +DEBUG:PIL.Image:Importing GribStubImagePlugin +DEBUG:PIL.Image:Importing Hdf5StubImagePlugin +DEBUG:PIL.Image:Importing IcnsImagePlugin +DEBUG:PIL.Image:Importing IcoImagePlugin +DEBUG:PIL.Image:Importing ImImagePlugin +DEBUG:PIL.Image:Importing ImtImagePlugin +DEBUG:PIL.Image:Importing IptcImagePlugin +DEBUG:PIL.Image:Importing JpegImagePlugin +DEBUG:PIL.Image:Importing Jpeg2KImagePlugin +DEBUG:PIL.Image:Importing McIdasImagePlugin +DEBUG:PIL.Image:Importing MicImagePlugin +DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing MpegImagePlugin +DEBUG:PIL.Image:Importing MpoImagePlugin +DEBUG:PIL.Image:Importing MspImagePlugin +DEBUG:PIL.Image:Importing PalmImagePlugin +DEBUG:PIL.Image:Importing PcdImagePlugin +DEBUG:PIL.Image:Importing PcxImagePlugin +DEBUG:PIL.Image:Importing PdfImagePlugin +DEBUG:PIL.Image:Importing PixarImagePlugin +DEBUG:PIL.Image:Importing PngImagePlugin +DEBUG:PIL.Image:Importing PpmImagePlugin +DEBUG:PIL.Image:Importing PsdImagePlugin +DEBUG:PIL.Image:Importing QoiImagePlugin +DEBUG:PIL.Image:Importing SgiImagePlugin +DEBUG:PIL.Image:Importing SpiderImagePlugin +DEBUG:PIL.Image:Importing SunImagePlugin +DEBUG:PIL.Image:Importing TgaImagePlugin +DEBUG:PIL.Image:Importing TiffImagePlugin +DEBUG:PIL.Image:Importing WebPImagePlugin +DEBUG:PIL.Image:Importing WmfImagePlugin +DEBUG:PIL.Image:Importing XbmImagePlugin +DEBUG:PIL.Image:Importing XpmImagePlugin +DEBUG:PIL.Image:Importing XVThumbImagePlugin + 8%|▊ | 1/12 [01:13<13:33, 73.92s/it] 17%|█▋ | 2/12 [02:28<12:22, 74.25s/it] 25%|██▌ | 3/12 [03:41<11:01, 73.53s/it] 33%|███▎ | 4/12 [04:53<09:45, 73.17s/it] 42%|████▏ | 5/12 [06:06<08:30, 72.96s/it] 50%|█████ | 6/12 [07:18<07:16, 72.80s/it] 58%|█████▊ | 7/12 [08:31<06:03, 72.71s/it] 67%|██████▋ | 8/12 [09:43<04:50, 72.64s/it] 75%|███████▌ | 9/12 [10:56<03:37, 72.61s/it] 83%|████████▎ | 10/12 [12:08<02:25, 72.56s/it] 92%|█████████▏| 11/12 [13:21<01:12, 72.53s/it] 100%|██████████| 12/12 [14:33<00:00, 72.48s/it] 100%|██████████| 12/12 [14:33<00:00, 72.80s/it] +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 1: generating actions ... +>>> Step 1: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 2: generating actions ... +>>> Step 2: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 3: generating actions ... +>>> Step 3: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 4: generating actions ... +>>> Step 4: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 5: generating actions ... +>>> Step 5: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 6: generating actions ... +>>> Step 6: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 7: generating actions ... +>>> Step 7: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 8: generating actions ... +>>> Step 8: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 9: generating actions ... +>>> Step 9: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 10: generating actions ... +>>> Step 10: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 11: generating actions ... +>>> Step 11: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> + +real 16m6.503s +user 71m18.296s +sys 0m44.031s +2026-02-11 23:51:59.440508: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. +2026-02-11 23:51:59.489849: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered +2026-02-11 23:51:59.489897: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered +2026-02-11 23:51:59.491194: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered +2026-02-11 23:51:59.498659: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. +To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. +2026-02-11 23:52:00.422248: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT +Global seed set to 123 +INFO:mainlogger:LatentVisualDiffusion: Running in v-prediction mode +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +AE working on z of shape (1, 4, 32, 32) = 4096 dimensions. +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +>>> model checkpoint loaded. +>>> Load pre-trained model ... +INFO:root:***** Configing Data ***** +>>> unitree_z1_stackbox: 1 data samples loaded. +>>> unitree_z1_stackbox: data stats loaded. +>>> unitree_z1_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox: data stats loaded. +>>> unitree_z1_dual_arm_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox_v2: data stats loaded. +>>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated. +>>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated. +>>> unitree_g1_pack_camera: 1 data samples loaded. +>>> unitree_g1_pack_camera: data stats loaded. +>>> unitree_g1_pack_camera: normalizer initiated. +>>> Dataset is successfully loaded ... +>>> Generate 16 frames under each generation ... +DEBUG:h5py._conv:Creating converter from 3 to 5 +DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13 +DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9 +DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096 + 0%| | 0/12 [00:00>> Step 0: generating actions ... +>>> Step 0: interacting with world model ... +DEBUG:PIL.Image:Importing BlpImagePlugin +DEBUG:PIL.Image:Importing BmpImagePlugin +DEBUG:PIL.Image:Importing BufrStubImagePlugin +DEBUG:PIL.Image:Importing CurImagePlugin +DEBUG:PIL.Image:Importing DcxImagePlugin +DEBUG:PIL.Image:Importing DdsImagePlugin +DEBUG:PIL.Image:Importing EpsImagePlugin +DEBUG:PIL.Image:Importing FitsImagePlugin +DEBUG:PIL.Image:Importing FitsStubImagePlugin +DEBUG:PIL.Image:Importing FliImagePlugin +DEBUG:PIL.Image:Importing FpxImagePlugin +DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing FtexImagePlugin +DEBUG:PIL.Image:Importing GbrImagePlugin +DEBUG:PIL.Image:Importing GifImagePlugin +DEBUG:PIL.Image:Importing GribStubImagePlugin +DEBUG:PIL.Image:Importing Hdf5StubImagePlugin +DEBUG:PIL.Image:Importing IcnsImagePlugin +DEBUG:PIL.Image:Importing IcoImagePlugin +DEBUG:PIL.Image:Importing ImImagePlugin +DEBUG:PIL.Image:Importing ImtImagePlugin +DEBUG:PIL.Image:Importing IptcImagePlugin +DEBUG:PIL.Image:Importing JpegImagePlugin +DEBUG:PIL.Image:Importing Jpeg2KImagePlugin +DEBUG:PIL.Image:Importing McIdasImagePlugin +DEBUG:PIL.Image:Importing MicImagePlugin +DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing MpegImagePlugin +DEBUG:PIL.Image:Importing MpoImagePlugin +DEBUG:PIL.Image:Importing MspImagePlugin +DEBUG:PIL.Image:Importing PalmImagePlugin +DEBUG:PIL.Image:Importing PcdImagePlugin +DEBUG:PIL.Image:Importing PcxImagePlugin +DEBUG:PIL.Image:Importing PdfImagePlugin +DEBUG:PIL.Image:Importing PixarImagePlugin +DEBUG:PIL.Image:Importing PngImagePlugin +DEBUG:PIL.Image:Importing PpmImagePlugin +DEBUG:PIL.Image:Importing PsdImagePlugin +DEBUG:PIL.Image:Importing QoiImagePlugin +DEBUG:PIL.Image:Importing SgiImagePlugin +DEBUG:PIL.Image:Importing SpiderImagePlugin +DEBUG:PIL.Image:Importing SunImagePlugin +DEBUG:PIL.Image:Importing TgaImagePlugin +DEBUG:PIL.Image:Importing TiffImagePlugin +DEBUG:PIL.Image:Importing WebPImagePlugin +DEBUG:PIL.Image:Importing WmfImagePlugin +DEBUG:PIL.Image:Importing XbmImagePlugin +DEBUG:PIL.Image:Importing XpmImagePlugin +DEBUG:PIL.Image:Importing XVThumbImagePlugin + 8%|▊ | 1/12 [01:14<13:34, 74.06s/it] 17%|█▋ | 2/12 [02:27<12:17, 73.74s/it] 25%|██▌ | 3/12 [03:40<10:59, 73.23s/it] 33%|███▎ | 4/12 [04:52<09:43, 72.94s/it] 42%|████▏ | 5/12 [06:05<08:29, 72.81s/it] 50%|█████ | 6/12 [07:17<07:16, 72.74s/it] 58%|█████▊ | 7/12 [08:30<06:03, 72.68s/it] 67%|██████▋ | 8/12 [09:42<04:50, 72.63s/it] 75%|███████▌ | 9/12 [10:55<03:38, 72.72s/it] 83%|████████▎ | 10/12 [12:09<02:25, 72.86s/it] 92%|█████████▏| 11/12 [13:21<01:12, 72.75s/it] 100%|██████████| 12/12 [14:33<00:00, 72.66s/it] 100%|██████████| 12/12 [14:33<00:00, 72.83s/it] +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 1: generating actions ... +>>> Step 1: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 2: generating actions ... +>>> Step 2: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 3: generating actions ... +>>> Step 3: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 4: generating actions ... +>>> Step 4: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 5: generating actions ... +>>> Step 5: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 6: generating actions ... +>>> Step 6: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 7: generating actions ... +>>> Step 7: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 8: generating actions ... +>>> Step 8: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 9: generating actions ... +>>> Step 9: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 10: generating actions ... +>>> Step 10: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 11: generating actions ... +>>> Step 11: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> + +real 16m6.056s +user 71m23.029s +sys 0m43.382s +2026-02-12 00:08:05.532356: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. +2026-02-12 00:08:05.582134: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered +2026-02-12 00:08:05.582180: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered +2026-02-12 00:08:05.583503: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered +2026-02-12 00:08:05.591049: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. +To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. +2026-02-12 00:08:06.523218: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT +Global seed set to 123 +INFO:mainlogger:LatentVisualDiffusion: Running in v-prediction mode +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +AE working on z of shape (1, 4, 32, 32) = 4096 dimensions. +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +>>> model checkpoint loaded. +>>> Load pre-trained model ... +INFO:root:***** Configing Data ***** +>>> unitree_z1_stackbox: 1 data samples loaded. +>>> unitree_z1_stackbox: data stats loaded. +>>> unitree_z1_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox: data stats loaded. +>>> unitree_z1_dual_arm_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox_v2: data stats loaded. +>>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated. +>>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated. +>>> unitree_g1_pack_camera: 1 data samples loaded. +>>> unitree_g1_pack_camera: data stats loaded. +>>> unitree_g1_pack_camera: normalizer initiated. +>>> Dataset is successfully loaded ... +>>> Generate 16 frames under each generation ... +DEBUG:h5py._conv:Creating converter from 3 to 5 +DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13 +DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9 +DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096 + 0%| | 0/12 [00:00>> Step 0: generating actions ... +>>> Step 0: interacting with world model ... +DEBUG:PIL.Image:Importing BlpImagePlugin +DEBUG:PIL.Image:Importing BmpImagePlugin +DEBUG:PIL.Image:Importing BufrStubImagePlugin +DEBUG:PIL.Image:Importing CurImagePlugin +DEBUG:PIL.Image:Importing DcxImagePlugin +DEBUG:PIL.Image:Importing DdsImagePlugin +DEBUG:PIL.Image:Importing EpsImagePlugin +DEBUG:PIL.Image:Importing FitsImagePlugin +DEBUG:PIL.Image:Importing FitsStubImagePlugin +DEBUG:PIL.Image:Importing FliImagePlugin +DEBUG:PIL.Image:Importing FpxImagePlugin +DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing FtexImagePlugin +DEBUG:PIL.Image:Importing GbrImagePlugin +DEBUG:PIL.Image:Importing GifImagePlugin +DEBUG:PIL.Image:Importing GribStubImagePlugin +DEBUG:PIL.Image:Importing Hdf5StubImagePlugin +DEBUG:PIL.Image:Importing IcnsImagePlugin +DEBUG:PIL.Image:Importing IcoImagePlugin +DEBUG:PIL.Image:Importing ImImagePlugin +DEBUG:PIL.Image:Importing ImtImagePlugin +DEBUG:PIL.Image:Importing IptcImagePlugin +DEBUG:PIL.Image:Importing JpegImagePlugin +DEBUG:PIL.Image:Importing Jpeg2KImagePlugin +DEBUG:PIL.Image:Importing McIdasImagePlugin +DEBUG:PIL.Image:Importing MicImagePlugin +DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing MpegImagePlugin +DEBUG:PIL.Image:Importing MpoImagePlugin +DEBUG:PIL.Image:Importing MspImagePlugin +DEBUG:PIL.Image:Importing PalmImagePlugin +DEBUG:PIL.Image:Importing PcdImagePlugin +DEBUG:PIL.Image:Importing PcxImagePlugin +DEBUG:PIL.Image:Importing PdfImagePlugin +DEBUG:PIL.Image:Importing PixarImagePlugin +DEBUG:PIL.Image:Importing PngImagePlugin +DEBUG:PIL.Image:Importing PpmImagePlugin +DEBUG:PIL.Image:Importing PsdImagePlugin +DEBUG:PIL.Image:Importing QoiImagePlugin +DEBUG:PIL.Image:Importing SgiImagePlugin +DEBUG:PIL.Image:Importing SpiderImagePlugin +DEBUG:PIL.Image:Importing SunImagePlugin +DEBUG:PIL.Image:Importing TgaImagePlugin +DEBUG:PIL.Image:Importing TiffImagePlugin +DEBUG:PIL.Image:Importing WebPImagePlugin +DEBUG:PIL.Image:Importing WmfImagePlugin +DEBUG:PIL.Image:Importing XbmImagePlugin +DEBUG:PIL.Image:Importing XpmImagePlugin +DEBUG:PIL.Image:Importing XVThumbImagePlugin + 8%|▊ | 1/12 [01:13<13:30, 73.69s/it] 17%|█▋ | 2/12 [02:26<12:12, 73.23s/it] 25%|██▌ | 3/12 [03:40<11:02, 73.59s/it] 33%|███▎ | 4/12 [04:54<09:50, 73.76s/it] 42%|████▏ | 5/12 [06:07<08:34, 73.51s/it] 50%|█████ | 6/12 [07:20<07:19, 73.19s/it] 58%|█████▊ | 7/12 [08:32<06:04, 72.98s/it] 67%|██████▋ | 8/12 [09:45<04:51, 72.85s/it] 75%|███████▌ | 9/12 [10:57<03:38, 72.76s/it] 83%|████████▎ | 10/12 [12:10<02:25, 72.69s/it] 92%|█████████▏| 11/12 [13:23<01:12, 72.66s/it] 100%|██████████| 12/12 [14:35<00:00, 72.63s/it] 100%|██████████| 12/12 [14:35<00:00, 72.97s/it] +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 1: generating actions ... +>>> Step 1: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 2: generating actions ... +>>> Step 2: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 3: generating actions ... +>>> Step 3: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 4: generating actions ... +>>> Step 4: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 5: generating actions ... +>>> Step 5: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 6: generating actions ... +>>> Step 6: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 7: generating actions ... +>>> Step 7: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 8: generating actions ... +>>> Step 8: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 9: generating actions ... +>>> Step 9: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 10: generating actions ... +>>> Step 10: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 11: generating actions ... +>>> Step 11: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> + +real 16m7.783s +user 71m30.579s +sys 0m41.570s diff --git a/unitree_g1_pack_camera/case1/output.log b/unitree_g1_pack_camera/case1/output.log new file mode 100644 index 0000000..4c25499 --- /dev/null +++ b/unitree_g1_pack_camera/case1/output.log @@ -0,0 +1,127 @@ +2026-02-11 19:49:03.885238: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. +2026-02-11 19:49:03.934263: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered +2026-02-11 19:49:03.934309: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered +2026-02-11 19:49:03.935622: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered +2026-02-11 19:49:03.943041: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. +To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. +2026-02-11 19:49:04.852993: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT +Global seed set to 123 +INFO:mainlogger:LatentVisualDiffusion: Running in v-prediction mode +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +AE working on z of shape (1, 4, 32, 32) = 4096 dimensions. +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +>>> model checkpoint loaded. +>>> Load pre-trained model ... +INFO:root:***** Configing Data ***** +>>> unitree_z1_stackbox: 1 data samples loaded. +>>> unitree_z1_stackbox: data stats loaded. +>>> unitree_z1_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox: data stats loaded. +>>> unitree_z1_dual_arm_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox_v2: data stats loaded. +>>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated. +>>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated. +>>> unitree_g1_pack_camera: 1 data samples loaded. +>>> unitree_g1_pack_camera: data stats loaded. +>>> unitree_g1_pack_camera: normalizer initiated. +>>> Dataset is successfully loaded ... +>>> Generate 16 frames under each generation ... +DEBUG:h5py._conv:Creating converter from 3 to 5 +DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13 +DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9 +DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096 + 0%| | 0/11 [00:00>> Step 0: generating actions ... +>>> Step 0: interacting with world model ... +DEBUG:PIL.Image:Importing BlpImagePlugin +DEBUG:PIL.Image:Importing BmpImagePlugin +DEBUG:PIL.Image:Importing BufrStubImagePlugin +DEBUG:PIL.Image:Importing CurImagePlugin +DEBUG:PIL.Image:Importing DcxImagePlugin +DEBUG:PIL.Image:Importing DdsImagePlugin +DEBUG:PIL.Image:Importing EpsImagePlugin +DEBUG:PIL.Image:Importing FitsImagePlugin +DEBUG:PIL.Image:Importing FitsStubImagePlugin +DEBUG:PIL.Image:Importing FliImagePlugin +DEBUG:PIL.Image:Importing FpxImagePlugin +DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing FtexImagePlugin +DEBUG:PIL.Image:Importing GbrImagePlugin +DEBUG:PIL.Image:Importing GifImagePlugin +DEBUG:PIL.Image:Importing GribStubImagePlugin +DEBUG:PIL.Image:Importing Hdf5StubImagePlugin +DEBUG:PIL.Image:Importing IcnsImagePlugin +DEBUG:PIL.Image:Importing IcoImagePlugin +DEBUG:PIL.Image:Importing ImImagePlugin +DEBUG:PIL.Image:Importing ImtImagePlugin +DEBUG:PIL.Image:Importing IptcImagePlugin +DEBUG:PIL.Image:Importing JpegImagePlugin +DEBUG:PIL.Image:Importing Jpeg2KImagePlugin +DEBUG:PIL.Image:Importing McIdasImagePlugin +DEBUG:PIL.Image:Importing MicImagePlugin +DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing MpegImagePlugin +DEBUG:PIL.Image:Importing MpoImagePlugin +DEBUG:PIL.Image:Importing MspImagePlugin +DEBUG:PIL.Image:Importing PalmImagePlugin +DEBUG:PIL.Image:Importing PcdImagePlugin +DEBUG:PIL.Image:Importing PcxImagePlugin +DEBUG:PIL.Image:Importing PdfImagePlugin +DEBUG:PIL.Image:Importing PixarImagePlugin +DEBUG:PIL.Image:Importing PngImagePlugin +DEBUG:PIL.Image:Importing PpmImagePlugin +DEBUG:PIL.Image:Importing PsdImagePlugin +DEBUG:PIL.Image:Importing QoiImagePlugin +DEBUG:PIL.Image:Importing SgiImagePlugin +DEBUG:PIL.Image:Importing SpiderImagePlugin +DEBUG:PIL.Image:Importing SunImagePlugin +DEBUG:PIL.Image:Importing TgaImagePlugin +DEBUG:PIL.Image:Importing TiffImagePlugin +DEBUG:PIL.Image:Importing WebPImagePlugin +DEBUG:PIL.Image:Importing WmfImagePlugin +DEBUG:PIL.Image:Importing XbmImagePlugin +DEBUG:PIL.Image:Importing XpmImagePlugin +DEBUG:PIL.Image:Importing XVThumbImagePlugin + 9%|▉ | 1/11 [01:12<12:09, 72.95s/it] 18%|█▊ | 2/11 [02:26<10:58, 73.19s/it] 27%|██▋ | 3/11 [03:39<09:45, 73.21s/it] 36%|███▋ | 4/11 [04:52<08:32, 73.21s/it] 45%|████▌ | 5/11 [06:05<07:19, 73.22s/it] 55%|█████▍ | 6/11 [07:19<06:06, 73.20s/it] 64%|██████▎ | 7/11 [08:32<04:52, 73.16s/it] 73%|███████▎ | 8/11 [09:45<03:39, 73.14s/it] 82%|████████▏ | 9/11 [10:58<02:26, 73.13s/it] 91%|█████████ | 10/11 [12:11<01:13, 73.15s/it] 100%|██████████| 11/11 [13:24<00:00, 73.18s/it] 100%|██████████| 11/11 [13:24<00:00, 73.17s/it] +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 1: generating actions ... +>>> Step 1: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 2: generating actions ... +>>> Step 2: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 3: generating actions ... +>>> Step 3: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 4: generating actions ... +>>> Step 4: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 5: generating actions ... +>>> Step 5: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 6: generating actions ... +>>> Step 6: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 7: generating actions ... +>>> Step 7: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 8: generating actions ... +>>> Step 8: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 9: generating actions ... +>>> Step 9: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 10: generating actions ... +>>> Step 10: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> + +real 15m0.258s +user 65m49.394s +sys 0m45.300s diff --git a/unitree_g1_pack_camera/case2/output.log b/unitree_g1_pack_camera/case2/output.log new file mode 100644 index 0000000..3f24b5d --- /dev/null +++ b/unitree_g1_pack_camera/case2/output.log @@ -0,0 +1,127 @@ +2026-02-11 20:04:06.049535: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. +2026-02-11 20:04:06.099186: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered +2026-02-11 20:04:06.099232: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered +2026-02-11 20:04:06.100544: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered +2026-02-11 20:04:06.108023: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. +To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. +2026-02-11 20:04:07.025500: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT +Global seed set to 123 +INFO:mainlogger:LatentVisualDiffusion: Running in v-prediction mode +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +AE working on z of shape (1, 4, 32, 32) = 4096 dimensions. +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +>>> model checkpoint loaded. +>>> Load pre-trained model ... +INFO:root:***** Configing Data ***** +>>> unitree_z1_stackbox: 1 data samples loaded. +>>> unitree_z1_stackbox: data stats loaded. +>>> unitree_z1_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox: data stats loaded. +>>> unitree_z1_dual_arm_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox_v2: data stats loaded. +>>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated. +>>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated. +>>> unitree_g1_pack_camera: 1 data samples loaded. +>>> unitree_g1_pack_camera: data stats loaded. +>>> unitree_g1_pack_camera: normalizer initiated. +>>> Dataset is successfully loaded ... +>>> Generate 16 frames under each generation ... +DEBUG:h5py._conv:Creating converter from 3 to 5 +DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13 +DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9 +DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096 + 0%| | 0/11 [00:00>> Step 0: generating actions ... +>>> Step 0: interacting with world model ... +DEBUG:PIL.Image:Importing BlpImagePlugin +DEBUG:PIL.Image:Importing BmpImagePlugin +DEBUG:PIL.Image:Importing BufrStubImagePlugin +DEBUG:PIL.Image:Importing CurImagePlugin +DEBUG:PIL.Image:Importing DcxImagePlugin +DEBUG:PIL.Image:Importing DdsImagePlugin +DEBUG:PIL.Image:Importing EpsImagePlugin +DEBUG:PIL.Image:Importing FitsImagePlugin +DEBUG:PIL.Image:Importing FitsStubImagePlugin +DEBUG:PIL.Image:Importing FliImagePlugin +DEBUG:PIL.Image:Importing FpxImagePlugin +DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing FtexImagePlugin +DEBUG:PIL.Image:Importing GbrImagePlugin +DEBUG:PIL.Image:Importing GifImagePlugin +DEBUG:PIL.Image:Importing GribStubImagePlugin +DEBUG:PIL.Image:Importing Hdf5StubImagePlugin +DEBUG:PIL.Image:Importing IcnsImagePlugin +DEBUG:PIL.Image:Importing IcoImagePlugin +DEBUG:PIL.Image:Importing ImImagePlugin +DEBUG:PIL.Image:Importing ImtImagePlugin +DEBUG:PIL.Image:Importing IptcImagePlugin +DEBUG:PIL.Image:Importing JpegImagePlugin +DEBUG:PIL.Image:Importing Jpeg2KImagePlugin +DEBUG:PIL.Image:Importing McIdasImagePlugin +DEBUG:PIL.Image:Importing MicImagePlugin +DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing MpegImagePlugin +DEBUG:PIL.Image:Importing MpoImagePlugin +DEBUG:PIL.Image:Importing MspImagePlugin +DEBUG:PIL.Image:Importing PalmImagePlugin +DEBUG:PIL.Image:Importing PcdImagePlugin +DEBUG:PIL.Image:Importing PcxImagePlugin +DEBUG:PIL.Image:Importing PdfImagePlugin +DEBUG:PIL.Image:Importing PixarImagePlugin +DEBUG:PIL.Image:Importing PngImagePlugin +DEBUG:PIL.Image:Importing PpmImagePlugin +DEBUG:PIL.Image:Importing PsdImagePlugin +DEBUG:PIL.Image:Importing QoiImagePlugin +DEBUG:PIL.Image:Importing SgiImagePlugin +DEBUG:PIL.Image:Importing SpiderImagePlugin +DEBUG:PIL.Image:Importing SunImagePlugin +DEBUG:PIL.Image:Importing TgaImagePlugin +DEBUG:PIL.Image:Importing TiffImagePlugin +DEBUG:PIL.Image:Importing WebPImagePlugin +DEBUG:PIL.Image:Importing WmfImagePlugin +DEBUG:PIL.Image:Importing XbmImagePlugin +DEBUG:PIL.Image:Importing XpmImagePlugin +DEBUG:PIL.Image:Importing XVThumbImagePlugin + 9%|▉ | 1/11 [01:14<12:22, 74.22s/it] 18%|█▊ | 2/11 [02:28<11:09, 74.33s/it] 27%|██▋ | 3/11 [03:42<09:54, 74.32s/it] 36%|███▋ | 4/11 [04:57<08:40, 74.32s/it] 45%|████▌ | 5/11 [06:11<07:25, 74.28s/it] 55%|█████▍ | 6/11 [07:25<06:10, 74.19s/it] 64%|██████▎ | 7/11 [08:39<04:56, 74.11s/it] 73%|███████▎ | 8/11 [09:53<03:42, 74.07s/it] 82%|████████▏ | 9/11 [11:07<02:28, 74.06s/it] 91%|█████████ | 10/11 [12:21<01:14, 74.01s/it] 100%|██████████| 11/11 [13:35<00:00, 73.98s/it] 100%|██████████| 11/11 [13:35<00:00, 74.12s/it] +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 1: generating actions ... +>>> Step 1: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 2: generating actions ... +>>> Step 2: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 3: generating actions ... +>>> Step 3: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 4: generating actions ... +>>> Step 4: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 5: generating actions ... +>>> Step 5: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 6: generating actions ... +>>> Step 6: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 7: generating actions ... +>>> Step 7: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 8: generating actions ... +>>> Step 8: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 9: generating actions ... +>>> Step 9: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 10: generating actions ... +>>> Step 10: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> + +real 15m13.215s +user 66m8.595s +sys 0m45.545s diff --git a/unitree_g1_pack_camera/case3/output.log b/unitree_g1_pack_camera/case3/output.log new file mode 100644 index 0000000..13e8213 --- /dev/null +++ b/unitree_g1_pack_camera/case3/output.log @@ -0,0 +1,127 @@ +2026-02-11 20:19:19.271045: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. +2026-02-11 20:19:19.320688: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered +2026-02-11 20:19:19.320734: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered +2026-02-11 20:19:19.322059: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered +2026-02-11 20:19:19.329606: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. +To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. +2026-02-11 20:19:20.248938: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT +Global seed set to 123 +INFO:mainlogger:LatentVisualDiffusion: Running in v-prediction mode +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +AE working on z of shape (1, 4, 32, 32) = 4096 dimensions. +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +>>> model checkpoint loaded. +>>> Load pre-trained model ... +INFO:root:***** Configing Data ***** +>>> unitree_z1_stackbox: 1 data samples loaded. +>>> unitree_z1_stackbox: data stats loaded. +>>> unitree_z1_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox: data stats loaded. +>>> unitree_z1_dual_arm_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox_v2: data stats loaded. +>>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated. +>>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated. +>>> unitree_g1_pack_camera: 1 data samples loaded. +>>> unitree_g1_pack_camera: data stats loaded. +>>> unitree_g1_pack_camera: normalizer initiated. +>>> Dataset is successfully loaded ... +>>> Generate 16 frames under each generation ... +DEBUG:h5py._conv:Creating converter from 3 to 5 +DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13 +DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9 +DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096 + 0%| | 0/11 [00:00>> Step 0: generating actions ... +>>> Step 0: interacting with world model ... +DEBUG:PIL.Image:Importing BlpImagePlugin +DEBUG:PIL.Image:Importing BmpImagePlugin +DEBUG:PIL.Image:Importing BufrStubImagePlugin +DEBUG:PIL.Image:Importing CurImagePlugin +DEBUG:PIL.Image:Importing DcxImagePlugin +DEBUG:PIL.Image:Importing DdsImagePlugin +DEBUG:PIL.Image:Importing EpsImagePlugin +DEBUG:PIL.Image:Importing FitsImagePlugin +DEBUG:PIL.Image:Importing FitsStubImagePlugin +DEBUG:PIL.Image:Importing FliImagePlugin +DEBUG:PIL.Image:Importing FpxImagePlugin +DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing FtexImagePlugin +DEBUG:PIL.Image:Importing GbrImagePlugin +DEBUG:PIL.Image:Importing GifImagePlugin +DEBUG:PIL.Image:Importing GribStubImagePlugin +DEBUG:PIL.Image:Importing Hdf5StubImagePlugin +DEBUG:PIL.Image:Importing IcnsImagePlugin +DEBUG:PIL.Image:Importing IcoImagePlugin +DEBUG:PIL.Image:Importing ImImagePlugin +DEBUG:PIL.Image:Importing ImtImagePlugin +DEBUG:PIL.Image:Importing IptcImagePlugin +DEBUG:PIL.Image:Importing JpegImagePlugin +DEBUG:PIL.Image:Importing Jpeg2KImagePlugin +DEBUG:PIL.Image:Importing McIdasImagePlugin +DEBUG:PIL.Image:Importing MicImagePlugin +DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing MpegImagePlugin +DEBUG:PIL.Image:Importing MpoImagePlugin +DEBUG:PIL.Image:Importing MspImagePlugin +DEBUG:PIL.Image:Importing PalmImagePlugin +DEBUG:PIL.Image:Importing PcdImagePlugin +DEBUG:PIL.Image:Importing PcxImagePlugin +DEBUG:PIL.Image:Importing PdfImagePlugin +DEBUG:PIL.Image:Importing PixarImagePlugin +DEBUG:PIL.Image:Importing PngImagePlugin +DEBUG:PIL.Image:Importing PpmImagePlugin +DEBUG:PIL.Image:Importing PsdImagePlugin +DEBUG:PIL.Image:Importing QoiImagePlugin +DEBUG:PIL.Image:Importing SgiImagePlugin +DEBUG:PIL.Image:Importing SpiderImagePlugin +DEBUG:PIL.Image:Importing SunImagePlugin +DEBUG:PIL.Image:Importing TgaImagePlugin +DEBUG:PIL.Image:Importing TiffImagePlugin +DEBUG:PIL.Image:Importing WebPImagePlugin +DEBUG:PIL.Image:Importing WmfImagePlugin +DEBUG:PIL.Image:Importing XbmImagePlugin +DEBUG:PIL.Image:Importing XpmImagePlugin +DEBUG:PIL.Image:Importing XVThumbImagePlugin + 9%|▉ | 1/11 [01:14<12:22, 74.28s/it] 18%|█▊ | 2/11 [02:28<11:09, 74.38s/it] 27%|██▋ | 3/11 [03:43<09:55, 74.45s/it] 36%|███▋ | 4/11 [04:57<08:41, 74.43s/it] 45%|████▌ | 5/11 [06:11<07:25, 74.25s/it] 55%|█████▍ | 6/11 [07:26<06:11, 74.31s/it] 64%|██████▎ | 7/11 [08:40<04:57, 74.26s/it] 73%|███████▎ | 8/11 [09:54<03:43, 74.34s/it] 82%|████████▏ | 9/11 [11:08<02:28, 74.29s/it] 91%|█████████ | 10/11 [12:23<01:14, 74.26s/it] 100%|██████████| 11/11 [13:37<00:00, 74.39s/it] 100%|██████████| 11/11 [13:37<00:00, 74.34s/it] +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 1: generating actions ... +>>> Step 1: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 2: generating actions ... +>>> Step 2: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 3: generating actions ... +>>> Step 3: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 4: generating actions ... +>>> Step 4: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 5: generating actions ... +>>> Step 5: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 6: generating actions ... +>>> Step 6: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 7: generating actions ... +>>> Step 7: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 8: generating actions ... +>>> Step 8: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 9: generating actions ... +>>> Step 9: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 10: generating actions ... +>>> Step 10: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> + +real 15m15.291s +user 65m30.562s +sys 0m45.706s diff --git a/unitree_g1_pack_camera/case4/output.log b/unitree_g1_pack_camera/case4/output.log new file mode 100644 index 0000000..3567eb6 --- /dev/null +++ b/unitree_g1_pack_camera/case4/output.log @@ -0,0 +1,127 @@ +2026-02-11 20:34:34.563818: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. +2026-02-11 20:34:34.613426: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered +2026-02-11 20:34:34.613485: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered +2026-02-11 20:34:34.614802: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered +2026-02-11 20:34:34.622286: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. +To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. +2026-02-11 20:34:35.540506: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT +Global seed set to 123 +INFO:mainlogger:LatentVisualDiffusion: Running in v-prediction mode +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +AE working on z of shape (1, 4, 32, 32) = 4096 dimensions. +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +>>> model checkpoint loaded. +>>> Load pre-trained model ... +INFO:root:***** Configing Data ***** +>>> unitree_z1_stackbox: 1 data samples loaded. +>>> unitree_z1_stackbox: data stats loaded. +>>> unitree_z1_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox: data stats loaded. +>>> unitree_z1_dual_arm_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox_v2: data stats loaded. +>>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated. +>>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated. +>>> unitree_g1_pack_camera: 1 data samples loaded. +>>> unitree_g1_pack_camera: data stats loaded. +>>> unitree_g1_pack_camera: normalizer initiated. +>>> Dataset is successfully loaded ... +>>> Generate 16 frames under each generation ... +DEBUG:h5py._conv:Creating converter from 3 to 5 +DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13 +DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9 +DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096 + 0%| | 0/11 [00:00>> Step 0: generating actions ... +>>> Step 0: interacting with world model ... +DEBUG:PIL.Image:Importing BlpImagePlugin +DEBUG:PIL.Image:Importing BmpImagePlugin +DEBUG:PIL.Image:Importing BufrStubImagePlugin +DEBUG:PIL.Image:Importing CurImagePlugin +DEBUG:PIL.Image:Importing DcxImagePlugin +DEBUG:PIL.Image:Importing DdsImagePlugin +DEBUG:PIL.Image:Importing EpsImagePlugin +DEBUG:PIL.Image:Importing FitsImagePlugin +DEBUG:PIL.Image:Importing FitsStubImagePlugin +DEBUG:PIL.Image:Importing FliImagePlugin +DEBUG:PIL.Image:Importing FpxImagePlugin +DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing FtexImagePlugin +DEBUG:PIL.Image:Importing GbrImagePlugin +DEBUG:PIL.Image:Importing GifImagePlugin +DEBUG:PIL.Image:Importing GribStubImagePlugin +DEBUG:PIL.Image:Importing Hdf5StubImagePlugin +DEBUG:PIL.Image:Importing IcnsImagePlugin +DEBUG:PIL.Image:Importing IcoImagePlugin +DEBUG:PIL.Image:Importing ImImagePlugin +DEBUG:PIL.Image:Importing ImtImagePlugin +DEBUG:PIL.Image:Importing IptcImagePlugin +DEBUG:PIL.Image:Importing JpegImagePlugin +DEBUG:PIL.Image:Importing Jpeg2KImagePlugin +DEBUG:PIL.Image:Importing McIdasImagePlugin +DEBUG:PIL.Image:Importing MicImagePlugin +DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing MpegImagePlugin +DEBUG:PIL.Image:Importing MpoImagePlugin +DEBUG:PIL.Image:Importing MspImagePlugin +DEBUG:PIL.Image:Importing PalmImagePlugin +DEBUG:PIL.Image:Importing PcdImagePlugin +DEBUG:PIL.Image:Importing PcxImagePlugin +DEBUG:PIL.Image:Importing PdfImagePlugin +DEBUG:PIL.Image:Importing PixarImagePlugin +DEBUG:PIL.Image:Importing PngImagePlugin +DEBUG:PIL.Image:Importing PpmImagePlugin +DEBUG:PIL.Image:Importing PsdImagePlugin +DEBUG:PIL.Image:Importing QoiImagePlugin +DEBUG:PIL.Image:Importing SgiImagePlugin +DEBUG:PIL.Image:Importing SpiderImagePlugin +DEBUG:PIL.Image:Importing SunImagePlugin +DEBUG:PIL.Image:Importing TgaImagePlugin +DEBUG:PIL.Image:Importing TiffImagePlugin +DEBUG:PIL.Image:Importing WebPImagePlugin +DEBUG:PIL.Image:Importing WmfImagePlugin +DEBUG:PIL.Image:Importing XbmImagePlugin +DEBUG:PIL.Image:Importing XpmImagePlugin +DEBUG:PIL.Image:Importing XVThumbImagePlugin + 9%|▉ | 1/11 [01:14<12:25, 74.52s/it] 18%|█▊ | 2/11 [02:29<11:15, 75.00s/it] 27%|██▋ | 3/11 [03:44<09:59, 74.99s/it] 36%|███▋ | 4/11 [04:59<08:43, 74.74s/it] 45%|████▌ | 5/11 [06:13<07:26, 74.48s/it] 55%|█████▍ | 6/11 [07:27<06:12, 74.56s/it] 64%|██████▎ | 7/11 [08:42<04:57, 74.46s/it] 73%|███████▎ | 8/11 [09:56<03:43, 74.48s/it] 82%|████████▏ | 9/11 [11:10<02:28, 74.32s/it] 91%|█████████ | 10/11 [12:23<01:13, 73.94s/it] 100%|██████████| 11/11 [13:36<00:00, 73.64s/it] 100%|██████████| 11/11 [13:36<00:00, 74.25s/it] +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 1: generating actions ... +>>> Step 1: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 2: generating actions ... +>>> Step 2: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 3: generating actions ... +>>> Step 3: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 4: generating actions ... +>>> Step 4: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 5: generating actions ... +>>> Step 5: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 6: generating actions ... +>>> Step 6: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 7: generating actions ... +>>> Step 7: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 8: generating actions ... +>>> Step 8: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 9: generating actions ... +>>> Step 9: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 10: generating actions ... +>>> Step 10: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> + +real 15m13.379s +user 65m31.865s +sys 0m45.108s diff --git a/unitree_z1_dual_arm_cleanup_pencils/case1/output.log b/unitree_z1_dual_arm_cleanup_pencils/case1/output.log new file mode 100644 index 0000000..c85d1d9 --- /dev/null +++ b/unitree_z1_dual_arm_cleanup_pencils/case1/output.log @@ -0,0 +1,118 @@ +2026-02-11 20:49:47.965949: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. +2026-02-11 20:49:48.015942: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered +2026-02-11 20:49:48.015997: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered +2026-02-11 20:49:48.017330: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered +2026-02-11 20:49:48.024854: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. +To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. +2026-02-11 20:49:48.943205: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT +Global seed set to 123 +INFO:mainlogger:LatentVisualDiffusion: Running in v-prediction mode +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +AE working on z of shape (1, 4, 32, 32) = 4096 dimensions. +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +>>> model checkpoint loaded. +>>> Load pre-trained model ... +INFO:root:***** Configing Data ***** +>>> unitree_z1_stackbox: 1 data samples loaded. +>>> unitree_z1_stackbox: data stats loaded. +>>> unitree_z1_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox: data stats loaded. +>>> unitree_z1_dual_arm_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox_v2: data stats loaded. +>>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated. +>>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated. +>>> unitree_g1_pack_camera: 1 data samples loaded. +>>> unitree_g1_pack_camera: data stats loaded. +>>> unitree_g1_pack_camera: normalizer initiated. +>>> Dataset is successfully loaded ... +>>> Generate 16 frames under each generation ... +DEBUG:h5py._conv:Creating converter from 3 to 5 +DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13 +DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9 +DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096 + 0%| | 0/8 [00:00>> Step 0: generating actions ... +>>> Step 0: interacting with world model ... +DEBUG:PIL.Image:Importing BlpImagePlugin +DEBUG:PIL.Image:Importing BmpImagePlugin +DEBUG:PIL.Image:Importing BufrStubImagePlugin +DEBUG:PIL.Image:Importing CurImagePlugin +DEBUG:PIL.Image:Importing DcxImagePlugin +DEBUG:PIL.Image:Importing DdsImagePlugin +DEBUG:PIL.Image:Importing EpsImagePlugin +DEBUG:PIL.Image:Importing FitsImagePlugin +DEBUG:PIL.Image:Importing FitsStubImagePlugin +DEBUG:PIL.Image:Importing FliImagePlugin +DEBUG:PIL.Image:Importing FpxImagePlugin +DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing FtexImagePlugin +DEBUG:PIL.Image:Importing GbrImagePlugin +DEBUG:PIL.Image:Importing GifImagePlugin +DEBUG:PIL.Image:Importing GribStubImagePlugin +DEBUG:PIL.Image:Importing Hdf5StubImagePlugin +DEBUG:PIL.Image:Importing IcnsImagePlugin +DEBUG:PIL.Image:Importing IcoImagePlugin +DEBUG:PIL.Image:Importing ImImagePlugin +DEBUG:PIL.Image:Importing ImtImagePlugin +DEBUG:PIL.Image:Importing IptcImagePlugin +DEBUG:PIL.Image:Importing JpegImagePlugin +DEBUG:PIL.Image:Importing Jpeg2KImagePlugin +DEBUG:PIL.Image:Importing McIdasImagePlugin +DEBUG:PIL.Image:Importing MicImagePlugin +DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing MpegImagePlugin +DEBUG:PIL.Image:Importing MpoImagePlugin +DEBUG:PIL.Image:Importing MspImagePlugin +DEBUG:PIL.Image:Importing PalmImagePlugin +DEBUG:PIL.Image:Importing PcdImagePlugin +DEBUG:PIL.Image:Importing PcxImagePlugin +DEBUG:PIL.Image:Importing PdfImagePlugin +DEBUG:PIL.Image:Importing PixarImagePlugin +DEBUG:PIL.Image:Importing PngImagePlugin +DEBUG:PIL.Image:Importing PpmImagePlugin +DEBUG:PIL.Image:Importing PsdImagePlugin +DEBUG:PIL.Image:Importing QoiImagePlugin +DEBUG:PIL.Image:Importing SgiImagePlugin +DEBUG:PIL.Image:Importing SpiderImagePlugin +DEBUG:PIL.Image:Importing SunImagePlugin +DEBUG:PIL.Image:Importing TgaImagePlugin +DEBUG:PIL.Image:Importing TiffImagePlugin +DEBUG:PIL.Image:Importing WebPImagePlugin +DEBUG:PIL.Image:Importing WmfImagePlugin +DEBUG:PIL.Image:Importing XbmImagePlugin +DEBUG:PIL.Image:Importing XpmImagePlugin +DEBUG:PIL.Image:Importing XVThumbImagePlugin + 12%|█▎ | 1/8 [01:15<08:48, 75.51s/it] 25%|██▌ | 2/8 [02:30<07:32, 75.39s/it] 38%|███▊ | 3/8 [03:46<06:16, 75.35s/it] 50%|█████ | 4/8 [05:00<05:00, 75.01s/it] 62%|██████▎ | 5/8 [06:14<03:44, 74.68s/it] 75%|███████▌ | 6/8 [07:28<02:28, 74.40s/it] 88%|████████▊ | 7/8 [08:42<01:14, 74.19s/it] 100%|██████████| 8/8 [09:55<00:00, 73.95s/it] 100%|██████████| 8/8 [09:55<00:00, 74.47s/it] +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 1: generating actions ... +>>> Step 1: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 2: generating actions ... +>>> Step 2: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 3: generating actions ... +>>> Step 3: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 4: generating actions ... +>>> Step 4: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 5: generating actions ... +>>> Step 5: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 6: generating actions ... +>>> Step 6: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 7: generating actions ... +>>> Step 7: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> + +real 11m31.593s +user 48m36.594s +sys 0m41.776s diff --git a/unitree_z1_dual_arm_cleanup_pencils/case2/output.log b/unitree_z1_dual_arm_cleanup_pencils/case2/output.log new file mode 100644 index 0000000..d0073b3 --- /dev/null +++ b/unitree_z1_dual_arm_cleanup_pencils/case2/output.log @@ -0,0 +1,118 @@ +2026-02-11 21:01:19.535243: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. +2026-02-11 21:01:19.585230: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered +2026-02-11 21:01:19.585275: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered +2026-02-11 21:01:19.586600: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered +2026-02-11 21:01:19.594107: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. +To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. +2026-02-11 21:01:20.510688: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT +Global seed set to 123 +INFO:mainlogger:LatentVisualDiffusion: Running in v-prediction mode +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +AE working on z of shape (1, 4, 32, 32) = 4096 dimensions. +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +>>> model checkpoint loaded. +>>> Load pre-trained model ... +INFO:root:***** Configing Data ***** +>>> unitree_z1_stackbox: 1 data samples loaded. +>>> unitree_z1_stackbox: data stats loaded. +>>> unitree_z1_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox: data stats loaded. +>>> unitree_z1_dual_arm_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox_v2: data stats loaded. +>>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated. +>>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated. +>>> unitree_g1_pack_camera: 1 data samples loaded. +>>> unitree_g1_pack_camera: data stats loaded. +>>> unitree_g1_pack_camera: normalizer initiated. +>>> Dataset is successfully loaded ... +>>> Generate 16 frames under each generation ... +DEBUG:h5py._conv:Creating converter from 3 to 5 +DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13 +DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9 +DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096 + 0%| | 0/8 [00:00>> Step 0: generating actions ... +>>> Step 0: interacting with world model ... +DEBUG:PIL.Image:Importing BlpImagePlugin +DEBUG:PIL.Image:Importing BmpImagePlugin +DEBUG:PIL.Image:Importing BufrStubImagePlugin +DEBUG:PIL.Image:Importing CurImagePlugin +DEBUG:PIL.Image:Importing DcxImagePlugin +DEBUG:PIL.Image:Importing DdsImagePlugin +DEBUG:PIL.Image:Importing EpsImagePlugin +DEBUG:PIL.Image:Importing FitsImagePlugin +DEBUG:PIL.Image:Importing FitsStubImagePlugin +DEBUG:PIL.Image:Importing FliImagePlugin +DEBUG:PIL.Image:Importing FpxImagePlugin +DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing FtexImagePlugin +DEBUG:PIL.Image:Importing GbrImagePlugin +DEBUG:PIL.Image:Importing GifImagePlugin +DEBUG:PIL.Image:Importing GribStubImagePlugin +DEBUG:PIL.Image:Importing Hdf5StubImagePlugin +DEBUG:PIL.Image:Importing IcnsImagePlugin +DEBUG:PIL.Image:Importing IcoImagePlugin +DEBUG:PIL.Image:Importing ImImagePlugin +DEBUG:PIL.Image:Importing ImtImagePlugin +DEBUG:PIL.Image:Importing IptcImagePlugin +DEBUG:PIL.Image:Importing JpegImagePlugin +DEBUG:PIL.Image:Importing Jpeg2KImagePlugin +DEBUG:PIL.Image:Importing McIdasImagePlugin +DEBUG:PIL.Image:Importing MicImagePlugin +DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing MpegImagePlugin +DEBUG:PIL.Image:Importing MpoImagePlugin +DEBUG:PIL.Image:Importing MspImagePlugin +DEBUG:PIL.Image:Importing PalmImagePlugin +DEBUG:PIL.Image:Importing PcdImagePlugin +DEBUG:PIL.Image:Importing PcxImagePlugin +DEBUG:PIL.Image:Importing PdfImagePlugin +DEBUG:PIL.Image:Importing PixarImagePlugin +DEBUG:PIL.Image:Importing PngImagePlugin +DEBUG:PIL.Image:Importing PpmImagePlugin +DEBUG:PIL.Image:Importing PsdImagePlugin +DEBUG:PIL.Image:Importing QoiImagePlugin +DEBUG:PIL.Image:Importing SgiImagePlugin +DEBUG:PIL.Image:Importing SpiderImagePlugin +DEBUG:PIL.Image:Importing SunImagePlugin +DEBUG:PIL.Image:Importing TgaImagePlugin +DEBUG:PIL.Image:Importing TiffImagePlugin +DEBUG:PIL.Image:Importing WebPImagePlugin +DEBUG:PIL.Image:Importing WmfImagePlugin +DEBUG:PIL.Image:Importing XbmImagePlugin +DEBUG:PIL.Image:Importing XpmImagePlugin +DEBUG:PIL.Image:Importing XVThumbImagePlugin + 12%|█▎ | 1/8 [01:16<08:54, 76.34s/it] 25%|██▌ | 2/8 [02:32<07:37, 76.28s/it] 38%|███▊ | 3/8 [03:48<06:21, 76.24s/it] 50%|█████ | 4/8 [05:04<05:04, 76.15s/it] 62%|██████▎ | 5/8 [06:21<03:48, 76.24s/it] 75%|███████▌ | 6/8 [07:36<02:32, 76.08s/it] 88%|████████▊ | 7/8 [08:52<01:15, 75.93s/it] 100%|██████████| 8/8 [10:09<00:00, 76.12s/it] 100%|██████████| 8/8 [10:09<00:00, 76.14s/it] +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 1: generating actions ... +>>> Step 1: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 2: generating actions ... +>>> Step 2: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 3: generating actions ... +>>> Step 3: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 4: generating actions ... +>>> Step 4: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 5: generating actions ... +>>> Step 5: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 6: generating actions ... +>>> Step 6: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 7: generating actions ... +>>> Step 7: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> + +real 11m45.279s +user 47m55.345s +sys 2m55.266s diff --git a/unitree_z1_dual_arm_cleanup_pencils/case3/output.log b/unitree_z1_dual_arm_cleanup_pencils/case3/output.log new file mode 100644 index 0000000..b8094b9 --- /dev/null +++ b/unitree_z1_dual_arm_cleanup_pencils/case3/output.log @@ -0,0 +1,118 @@ +2026-02-11 21:13:04.812376: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. +2026-02-11 21:13:04.862167: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered +2026-02-11 21:13:04.862223: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered +2026-02-11 21:13:04.863549: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered +2026-02-11 21:13:04.871078: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. +To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. +2026-02-11 21:13:05.785070: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT +Global seed set to 123 +INFO:mainlogger:LatentVisualDiffusion: Running in v-prediction mode +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +AE working on z of shape (1, 4, 32, 32) = 4096 dimensions. +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +>>> model checkpoint loaded. +>>> Load pre-trained model ... +INFO:root:***** Configing Data ***** +>>> unitree_z1_stackbox: 1 data samples loaded. +>>> unitree_z1_stackbox: data stats loaded. +>>> unitree_z1_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox: data stats loaded. +>>> unitree_z1_dual_arm_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox_v2: data stats loaded. +>>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated. +>>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated. +>>> unitree_g1_pack_camera: 1 data samples loaded. +>>> unitree_g1_pack_camera: data stats loaded. +>>> unitree_g1_pack_camera: normalizer initiated. +>>> Dataset is successfully loaded ... +>>> Generate 16 frames under each generation ... +DEBUG:h5py._conv:Creating converter from 3 to 5 +DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13 +DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9 +DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096 + 0%| | 0/8 [00:00>> Step 0: generating actions ... +>>> Step 0: interacting with world model ... +DEBUG:PIL.Image:Importing BlpImagePlugin +DEBUG:PIL.Image:Importing BmpImagePlugin +DEBUG:PIL.Image:Importing BufrStubImagePlugin +DEBUG:PIL.Image:Importing CurImagePlugin +DEBUG:PIL.Image:Importing DcxImagePlugin +DEBUG:PIL.Image:Importing DdsImagePlugin +DEBUG:PIL.Image:Importing EpsImagePlugin +DEBUG:PIL.Image:Importing FitsImagePlugin +DEBUG:PIL.Image:Importing FitsStubImagePlugin +DEBUG:PIL.Image:Importing FliImagePlugin +DEBUG:PIL.Image:Importing FpxImagePlugin +DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing FtexImagePlugin +DEBUG:PIL.Image:Importing GbrImagePlugin +DEBUG:PIL.Image:Importing GifImagePlugin +DEBUG:PIL.Image:Importing GribStubImagePlugin +DEBUG:PIL.Image:Importing Hdf5StubImagePlugin +DEBUG:PIL.Image:Importing IcnsImagePlugin +DEBUG:PIL.Image:Importing IcoImagePlugin +DEBUG:PIL.Image:Importing ImImagePlugin +DEBUG:PIL.Image:Importing ImtImagePlugin +DEBUG:PIL.Image:Importing IptcImagePlugin +DEBUG:PIL.Image:Importing JpegImagePlugin +DEBUG:PIL.Image:Importing Jpeg2KImagePlugin +DEBUG:PIL.Image:Importing McIdasImagePlugin +DEBUG:PIL.Image:Importing MicImagePlugin +DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing MpegImagePlugin +DEBUG:PIL.Image:Importing MpoImagePlugin +DEBUG:PIL.Image:Importing MspImagePlugin +DEBUG:PIL.Image:Importing PalmImagePlugin +DEBUG:PIL.Image:Importing PcdImagePlugin +DEBUG:PIL.Image:Importing PcxImagePlugin +DEBUG:PIL.Image:Importing PdfImagePlugin +DEBUG:PIL.Image:Importing PixarImagePlugin +DEBUG:PIL.Image:Importing PngImagePlugin +DEBUG:PIL.Image:Importing PpmImagePlugin +DEBUG:PIL.Image:Importing PsdImagePlugin +DEBUG:PIL.Image:Importing QoiImagePlugin +DEBUG:PIL.Image:Importing SgiImagePlugin +DEBUG:PIL.Image:Importing SpiderImagePlugin +DEBUG:PIL.Image:Importing SunImagePlugin +DEBUG:PIL.Image:Importing TgaImagePlugin +DEBUG:PIL.Image:Importing TiffImagePlugin +DEBUG:PIL.Image:Importing WebPImagePlugin +DEBUG:PIL.Image:Importing WmfImagePlugin +DEBUG:PIL.Image:Importing XbmImagePlugin +DEBUG:PIL.Image:Importing XpmImagePlugin +DEBUG:PIL.Image:Importing XVThumbImagePlugin + 12%|█▎ | 1/8 [01:15<08:45, 75.11s/it] 25%|██▌ | 2/8 [02:30<07:31, 75.30s/it] 38%|███▊ | 3/8 [03:45<06:16, 75.32s/it] 50%|█████ | 4/8 [05:01<05:01, 75.29s/it] 62%|██████▎ | 5/8 [06:16<03:46, 75.38s/it] 75%|███████▌ | 6/8 [07:32<02:30, 75.48s/it] 88%|████████▊ | 7/8 [08:47<01:15, 75.39s/it] 100%|██████████| 8/8 [10:02<00:00, 75.30s/it] 100%|██████████| 8/8 [10:02<00:00, 75.33s/it] +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 1: generating actions ... +>>> Step 1: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 2: generating actions ... +>>> Step 2: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 3: generating actions ... +>>> Step 3: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 4: generating actions ... +>>> Step 4: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 5: generating actions ... +>>> Step 5: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 6: generating actions ... +>>> Step 6: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 7: generating actions ... +>>> Step 7: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> + +real 11m37.624s +user 48m24.273s +sys 0m41.670s diff --git a/unitree_z1_dual_arm_cleanup_pencils/case4/output.log b/unitree_z1_dual_arm_cleanup_pencils/case4/output.log new file mode 100644 index 0000000..9ab82c5 --- /dev/null +++ b/unitree_z1_dual_arm_cleanup_pencils/case4/output.log @@ -0,0 +1,118 @@ +2026-02-11 21:24:42.443699: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. +2026-02-11 21:24:42.494143: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered +2026-02-11 21:24:42.494201: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered +2026-02-11 21:24:42.495506: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered +2026-02-11 21:24:42.503003: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. +To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. +2026-02-11 21:24:43.415898: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT +Global seed set to 123 +INFO:mainlogger:LatentVisualDiffusion: Running in v-prediction mode +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +AE working on z of shape (1, 4, 32, 32) = 4096 dimensions. +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +>>> model checkpoint loaded. +>>> Load pre-trained model ... +INFO:root:***** Configing Data ***** +>>> unitree_z1_stackbox: 1 data samples loaded. +>>> unitree_z1_stackbox: data stats loaded. +>>> unitree_z1_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox: data stats loaded. +>>> unitree_z1_dual_arm_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox_v2: data stats loaded. +>>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated. +>>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated. +>>> unitree_g1_pack_camera: 1 data samples loaded. +>>> unitree_g1_pack_camera: data stats loaded. +>>> unitree_g1_pack_camera: normalizer initiated. +>>> Dataset is successfully loaded ... +>>> Generate 16 frames under each generation ... +DEBUG:h5py._conv:Creating converter from 3 to 5 +DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13 +DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9 +DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096 + 0%| | 0/8 [00:00>> Step 0: generating actions ... +>>> Step 0: interacting with world model ... +DEBUG:PIL.Image:Importing BlpImagePlugin +DEBUG:PIL.Image:Importing BmpImagePlugin +DEBUG:PIL.Image:Importing BufrStubImagePlugin +DEBUG:PIL.Image:Importing CurImagePlugin +DEBUG:PIL.Image:Importing DcxImagePlugin +DEBUG:PIL.Image:Importing DdsImagePlugin +DEBUG:PIL.Image:Importing EpsImagePlugin +DEBUG:PIL.Image:Importing FitsImagePlugin +DEBUG:PIL.Image:Importing FitsStubImagePlugin +DEBUG:PIL.Image:Importing FliImagePlugin +DEBUG:PIL.Image:Importing FpxImagePlugin +DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing FtexImagePlugin +DEBUG:PIL.Image:Importing GbrImagePlugin +DEBUG:PIL.Image:Importing GifImagePlugin +DEBUG:PIL.Image:Importing GribStubImagePlugin +DEBUG:PIL.Image:Importing Hdf5StubImagePlugin +DEBUG:PIL.Image:Importing IcnsImagePlugin +DEBUG:PIL.Image:Importing IcoImagePlugin +DEBUG:PIL.Image:Importing ImImagePlugin +DEBUG:PIL.Image:Importing ImtImagePlugin +DEBUG:PIL.Image:Importing IptcImagePlugin +DEBUG:PIL.Image:Importing JpegImagePlugin +DEBUG:PIL.Image:Importing Jpeg2KImagePlugin +DEBUG:PIL.Image:Importing McIdasImagePlugin +DEBUG:PIL.Image:Importing MicImagePlugin +DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing MpegImagePlugin +DEBUG:PIL.Image:Importing MpoImagePlugin +DEBUG:PIL.Image:Importing MspImagePlugin +DEBUG:PIL.Image:Importing PalmImagePlugin +DEBUG:PIL.Image:Importing PcdImagePlugin +DEBUG:PIL.Image:Importing PcxImagePlugin +DEBUG:PIL.Image:Importing PdfImagePlugin +DEBUG:PIL.Image:Importing PixarImagePlugin +DEBUG:PIL.Image:Importing PngImagePlugin +DEBUG:PIL.Image:Importing PpmImagePlugin +DEBUG:PIL.Image:Importing PsdImagePlugin +DEBUG:PIL.Image:Importing QoiImagePlugin +DEBUG:PIL.Image:Importing SgiImagePlugin +DEBUG:PIL.Image:Importing SpiderImagePlugin +DEBUG:PIL.Image:Importing SunImagePlugin +DEBUG:PIL.Image:Importing TgaImagePlugin +DEBUG:PIL.Image:Importing TiffImagePlugin +DEBUG:PIL.Image:Importing WebPImagePlugin +DEBUG:PIL.Image:Importing WmfImagePlugin +DEBUG:PIL.Image:Importing XbmImagePlugin +DEBUG:PIL.Image:Importing XpmImagePlugin +DEBUG:PIL.Image:Importing XVThumbImagePlugin + 12%|█▎ | 1/8 [01:15<08:46, 75.28s/it] 25%|██▌ | 2/8 [02:30<07:32, 75.34s/it] 38%|███▊ | 3/8 [03:45<06:15, 75.08s/it] 50%|█████ | 4/8 [04:59<04:58, 74.69s/it] 62%|██████▎ | 5/8 [06:13<03:43, 74.43s/it] 75%|███████▌ | 6/8 [07:27<02:28, 74.27s/it] 88%|████████▊ | 7/8 [08:41<01:14, 74.21s/it] 100%|██████████| 8/8 [09:55<00:00, 74.13s/it] 100%|██████████| 8/8 [09:55<00:00, 74.43s/it] +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 1: generating actions ... +>>> Step 1: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 2: generating actions ... +>>> Step 2: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 3: generating actions ... +>>> Step 3: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 4: generating actions ... +>>> Step 4: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 5: generating actions ... +>>> Step 5: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 6: generating actions ... +>>> Step 6: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 7: generating actions ... +>>> Step 7: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> + +real 11m32.306s +user 48m37.680s +sys 0m41.716s diff --git a/unitree_z1_dual_arm_stackbox/case1/output.log b/unitree_z1_dual_arm_stackbox/case1/output.log new file mode 100644 index 0000000..0147cb7 --- /dev/null +++ b/unitree_z1_dual_arm_stackbox/case1/output.log @@ -0,0 +1,115 @@ +2026-02-11 21:36:14.761055: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. +2026-02-11 21:36:14.811056: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered +2026-02-11 21:36:14.811115: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered +2026-02-11 21:36:14.812480: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered +2026-02-11 21:36:14.820115: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. +To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. +2026-02-11 21:36:15.736583: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT +Global seed set to 123 +INFO:mainlogger:LatentVisualDiffusion: Running in v-prediction mode +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +AE working on z of shape (1, 4, 32, 32) = 4096 dimensions. +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +>>> model checkpoint loaded. +>>> Load pre-trained model ... +INFO:root:***** Configing Data ***** +>>> unitree_z1_stackbox: 1 data samples loaded. +>>> unitree_z1_stackbox: data stats loaded. +>>> unitree_z1_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox: data stats loaded. +>>> unitree_z1_dual_arm_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox_v2: data stats loaded. +>>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated. +>>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated. +>>> unitree_g1_pack_camera: 1 data samples loaded. +>>> unitree_g1_pack_camera: data stats loaded. +>>> unitree_g1_pack_camera: normalizer initiated. +>>> Dataset is successfully loaded ... +>>> Generate 16 frames under each generation ... +DEBUG:h5py._conv:Creating converter from 3 to 5 +DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13 +DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9 +DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096 + 0%| | 0/7 [00:00>> Step 0: generating actions ... +>>> Step 0: interacting with world model ... +DEBUG:PIL.Image:Importing BlpImagePlugin +DEBUG:PIL.Image:Importing BmpImagePlugin +DEBUG:PIL.Image:Importing BufrStubImagePlugin +DEBUG:PIL.Image:Importing CurImagePlugin +DEBUG:PIL.Image:Importing DcxImagePlugin +DEBUG:PIL.Image:Importing DdsImagePlugin +DEBUG:PIL.Image:Importing EpsImagePlugin +DEBUG:PIL.Image:Importing FitsImagePlugin +DEBUG:PIL.Image:Importing FitsStubImagePlugin +DEBUG:PIL.Image:Importing FliImagePlugin +DEBUG:PIL.Image:Importing FpxImagePlugin +DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing FtexImagePlugin +DEBUG:PIL.Image:Importing GbrImagePlugin +DEBUG:PIL.Image:Importing GifImagePlugin +DEBUG:PIL.Image:Importing GribStubImagePlugin +DEBUG:PIL.Image:Importing Hdf5StubImagePlugin +DEBUG:PIL.Image:Importing IcnsImagePlugin +DEBUG:PIL.Image:Importing IcoImagePlugin +DEBUG:PIL.Image:Importing ImImagePlugin +DEBUG:PIL.Image:Importing ImtImagePlugin +DEBUG:PIL.Image:Importing IptcImagePlugin +DEBUG:PIL.Image:Importing JpegImagePlugin +DEBUG:PIL.Image:Importing Jpeg2KImagePlugin +DEBUG:PIL.Image:Importing McIdasImagePlugin +DEBUG:PIL.Image:Importing MicImagePlugin +DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing MpegImagePlugin +DEBUG:PIL.Image:Importing MpoImagePlugin +DEBUG:PIL.Image:Importing MspImagePlugin +DEBUG:PIL.Image:Importing PalmImagePlugin +DEBUG:PIL.Image:Importing PcdImagePlugin +DEBUG:PIL.Image:Importing PcxImagePlugin +DEBUG:PIL.Image:Importing PdfImagePlugin +DEBUG:PIL.Image:Importing PixarImagePlugin +DEBUG:PIL.Image:Importing PngImagePlugin +DEBUG:PIL.Image:Importing PpmImagePlugin +DEBUG:PIL.Image:Importing PsdImagePlugin +DEBUG:PIL.Image:Importing QoiImagePlugin +DEBUG:PIL.Image:Importing SgiImagePlugin +DEBUG:PIL.Image:Importing SpiderImagePlugin +DEBUG:PIL.Image:Importing SunImagePlugin +DEBUG:PIL.Image:Importing TgaImagePlugin +DEBUG:PIL.Image:Importing TiffImagePlugin +DEBUG:PIL.Image:Importing WebPImagePlugin +DEBUG:PIL.Image:Importing WmfImagePlugin +DEBUG:PIL.Image:Importing XbmImagePlugin +DEBUG:PIL.Image:Importing XpmImagePlugin +DEBUG:PIL.Image:Importing XVThumbImagePlugin + 14%|█▍ | 1/7 [01:15<07:34, 75.70s/it] 29%|██▊ | 2/7 [02:31<06:18, 75.65s/it] 43%|████▎ | 3/7 [03:46<05:02, 75.52s/it] 57%|█████▋ | 4/7 [05:02<03:46, 75.47s/it] 71%|███████▏ | 5/7 [06:17<02:30, 75.40s/it] 86%|████████▌ | 6/7 [07:32<01:15, 75.37s/it] 100%|██████████| 7/7 [08:48<00:00, 75.38s/it] 100%|██████████| 7/7 [08:48<00:00, 75.44s/it] +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 1: generating actions ... +>>> Step 1: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 2: generating actions ... +>>> Step 2: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 3: generating actions ... +>>> Step 3: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 4: generating actions ... +>>> Step 4: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 5: generating actions ... +>>> Step 5: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 6: generating actions ... +>>> Step 6: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> + +real 10m26.533s +user 43m2.531s +sys 0m41.416s diff --git a/unitree_z1_dual_arm_stackbox/case2/output.log b/unitree_z1_dual_arm_stackbox/case2/output.log new file mode 100644 index 0000000..57ab513 --- /dev/null +++ b/unitree_z1_dual_arm_stackbox/case2/output.log @@ -0,0 +1,115 @@ +2026-02-11 21:46:41.375935: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. +2026-02-11 21:46:41.426557: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered +2026-02-11 21:46:41.426614: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered +2026-02-11 21:46:41.427937: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered +2026-02-11 21:46:41.435507: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. +To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. +2026-02-11 21:46:42.361310: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT +Global seed set to 123 +INFO:mainlogger:LatentVisualDiffusion: Running in v-prediction mode +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +AE working on z of shape (1, 4, 32, 32) = 4096 dimensions. +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +>>> model checkpoint loaded. +>>> Load pre-trained model ... +INFO:root:***** Configing Data ***** +>>> unitree_z1_stackbox: 1 data samples loaded. +>>> unitree_z1_stackbox: data stats loaded. +>>> unitree_z1_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox: data stats loaded. +>>> unitree_z1_dual_arm_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox_v2: data stats loaded. +>>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated. +>>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated. +>>> unitree_g1_pack_camera: 1 data samples loaded. +>>> unitree_g1_pack_camera: data stats loaded. +>>> unitree_g1_pack_camera: normalizer initiated. +>>> Dataset is successfully loaded ... +>>> Generate 16 frames under each generation ... +DEBUG:h5py._conv:Creating converter from 3 to 5 +DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13 +DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9 +DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096 + 0%| | 0/7 [00:00>> Step 0: generating actions ... +>>> Step 0: interacting with world model ... +DEBUG:PIL.Image:Importing BlpImagePlugin +DEBUG:PIL.Image:Importing BmpImagePlugin +DEBUG:PIL.Image:Importing BufrStubImagePlugin +DEBUG:PIL.Image:Importing CurImagePlugin +DEBUG:PIL.Image:Importing DcxImagePlugin +DEBUG:PIL.Image:Importing DdsImagePlugin +DEBUG:PIL.Image:Importing EpsImagePlugin +DEBUG:PIL.Image:Importing FitsImagePlugin +DEBUG:PIL.Image:Importing FitsStubImagePlugin +DEBUG:PIL.Image:Importing FliImagePlugin +DEBUG:PIL.Image:Importing FpxImagePlugin +DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing FtexImagePlugin +DEBUG:PIL.Image:Importing GbrImagePlugin +DEBUG:PIL.Image:Importing GifImagePlugin +DEBUG:PIL.Image:Importing GribStubImagePlugin +DEBUG:PIL.Image:Importing Hdf5StubImagePlugin +DEBUG:PIL.Image:Importing IcnsImagePlugin +DEBUG:PIL.Image:Importing IcoImagePlugin +DEBUG:PIL.Image:Importing ImImagePlugin +DEBUG:PIL.Image:Importing ImtImagePlugin +DEBUG:PIL.Image:Importing IptcImagePlugin +DEBUG:PIL.Image:Importing JpegImagePlugin +DEBUG:PIL.Image:Importing Jpeg2KImagePlugin +DEBUG:PIL.Image:Importing McIdasImagePlugin +DEBUG:PIL.Image:Importing MicImagePlugin +DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing MpegImagePlugin +DEBUG:PIL.Image:Importing MpoImagePlugin +DEBUG:PIL.Image:Importing MspImagePlugin +DEBUG:PIL.Image:Importing PalmImagePlugin +DEBUG:PIL.Image:Importing PcdImagePlugin +DEBUG:PIL.Image:Importing PcxImagePlugin +DEBUG:PIL.Image:Importing PdfImagePlugin +DEBUG:PIL.Image:Importing PixarImagePlugin +DEBUG:PIL.Image:Importing PngImagePlugin +DEBUG:PIL.Image:Importing PpmImagePlugin +DEBUG:PIL.Image:Importing PsdImagePlugin +DEBUG:PIL.Image:Importing QoiImagePlugin +DEBUG:PIL.Image:Importing SgiImagePlugin +DEBUG:PIL.Image:Importing SpiderImagePlugin +DEBUG:PIL.Image:Importing SunImagePlugin +DEBUG:PIL.Image:Importing TgaImagePlugin +DEBUG:PIL.Image:Importing TiffImagePlugin +DEBUG:PIL.Image:Importing WebPImagePlugin +DEBUG:PIL.Image:Importing WmfImagePlugin +DEBUG:PIL.Image:Importing XbmImagePlugin +DEBUG:PIL.Image:Importing XpmImagePlugin +DEBUG:PIL.Image:Importing XVThumbImagePlugin + 14%|█▍ | 1/7 [01:16<07:38, 76.39s/it] 29%|██▊ | 2/7 [02:33<06:23, 76.69s/it] 43%|████▎ | 3/7 [03:50<05:07, 76.87s/it] 57%|█████▋ | 4/7 [05:07<03:50, 76.91s/it] 71%|███████▏ | 5/7 [06:23<02:33, 76.80s/it] 86%|████████▌ | 6/7 [07:40<01:16, 76.77s/it] 100%|██████████| 7/7 [08:57<00:00, 76.85s/it] 100%|██████████| 7/7 [08:57<00:00, 76.81s/it] +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 1: generating actions ... +>>> Step 1: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 2: generating actions ... +>>> Step 2: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 3: generating actions ... +>>> Step 3: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 4: generating actions ... +>>> Step 4: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 5: generating actions ... +>>> Step 5: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 6: generating actions ... +>>> Step 6: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> + +real 10m36.315s +user 42m52.218s +sys 0m42.198s diff --git a/unitree_z1_dual_arm_stackbox/case3/output.log b/unitree_z1_dual_arm_stackbox/case3/output.log new file mode 100644 index 0000000..d9ff9cb --- /dev/null +++ b/unitree_z1_dual_arm_stackbox/case3/output.log @@ -0,0 +1,115 @@ +2026-02-11 21:57:17.623993: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. +2026-02-11 21:57:17.673835: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered +2026-02-11 21:57:17.673891: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered +2026-02-11 21:57:17.675211: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered +2026-02-11 21:57:17.682716: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. +To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. +2026-02-11 21:57:18.593525: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT +Global seed set to 123 +INFO:mainlogger:LatentVisualDiffusion: Running in v-prediction mode +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +AE working on z of shape (1, 4, 32, 32) = 4096 dimensions. +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +>>> model checkpoint loaded. +>>> Load pre-trained model ... +INFO:root:***** Configing Data ***** +>>> unitree_z1_stackbox: 1 data samples loaded. +>>> unitree_z1_stackbox: data stats loaded. +>>> unitree_z1_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox: data stats loaded. +>>> unitree_z1_dual_arm_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox_v2: data stats loaded. +>>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated. +>>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated. +>>> unitree_g1_pack_camera: 1 data samples loaded. +>>> unitree_g1_pack_camera: data stats loaded. +>>> unitree_g1_pack_camera: normalizer initiated. +>>> Dataset is successfully loaded ... +>>> Generate 16 frames under each generation ... +DEBUG:h5py._conv:Creating converter from 3 to 5 +DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13 +DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9 +DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096 + 0%| | 0/7 [00:00>> Step 0: generating actions ... +>>> Step 0: interacting with world model ... +DEBUG:PIL.Image:Importing BlpImagePlugin +DEBUG:PIL.Image:Importing BmpImagePlugin +DEBUG:PIL.Image:Importing BufrStubImagePlugin +DEBUG:PIL.Image:Importing CurImagePlugin +DEBUG:PIL.Image:Importing DcxImagePlugin +DEBUG:PIL.Image:Importing DdsImagePlugin +DEBUG:PIL.Image:Importing EpsImagePlugin +DEBUG:PIL.Image:Importing FitsImagePlugin +DEBUG:PIL.Image:Importing FitsStubImagePlugin +DEBUG:PIL.Image:Importing FliImagePlugin +DEBUG:PIL.Image:Importing FpxImagePlugin +DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing FtexImagePlugin +DEBUG:PIL.Image:Importing GbrImagePlugin +DEBUG:PIL.Image:Importing GifImagePlugin +DEBUG:PIL.Image:Importing GribStubImagePlugin +DEBUG:PIL.Image:Importing Hdf5StubImagePlugin +DEBUG:PIL.Image:Importing IcnsImagePlugin +DEBUG:PIL.Image:Importing IcoImagePlugin +DEBUG:PIL.Image:Importing ImImagePlugin +DEBUG:PIL.Image:Importing ImtImagePlugin +DEBUG:PIL.Image:Importing IptcImagePlugin +DEBUG:PIL.Image:Importing JpegImagePlugin +DEBUG:PIL.Image:Importing Jpeg2KImagePlugin +DEBUG:PIL.Image:Importing McIdasImagePlugin +DEBUG:PIL.Image:Importing MicImagePlugin +DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing MpegImagePlugin +DEBUG:PIL.Image:Importing MpoImagePlugin +DEBUG:PIL.Image:Importing MspImagePlugin +DEBUG:PIL.Image:Importing PalmImagePlugin +DEBUG:PIL.Image:Importing PcdImagePlugin +DEBUG:PIL.Image:Importing PcxImagePlugin +DEBUG:PIL.Image:Importing PdfImagePlugin +DEBUG:PIL.Image:Importing PixarImagePlugin +DEBUG:PIL.Image:Importing PngImagePlugin +DEBUG:PIL.Image:Importing PpmImagePlugin +DEBUG:PIL.Image:Importing PsdImagePlugin +DEBUG:PIL.Image:Importing QoiImagePlugin +DEBUG:PIL.Image:Importing SgiImagePlugin +DEBUG:PIL.Image:Importing SpiderImagePlugin +DEBUG:PIL.Image:Importing SunImagePlugin +DEBUG:PIL.Image:Importing TgaImagePlugin +DEBUG:PIL.Image:Importing TiffImagePlugin +DEBUG:PIL.Image:Importing WebPImagePlugin +DEBUG:PIL.Image:Importing WmfImagePlugin +DEBUG:PIL.Image:Importing XbmImagePlugin +DEBUG:PIL.Image:Importing XpmImagePlugin +DEBUG:PIL.Image:Importing XVThumbImagePlugin + 14%|█▍ | 1/7 [01:15<07:33, 75.59s/it] 29%|██▊ | 2/7 [02:31<06:17, 75.59s/it] 43%|████▎ | 3/7 [03:46<05:01, 75.44s/it] 57%|█████▋ | 4/7 [05:01<03:46, 75.39s/it] 71%|███████▏ | 5/7 [06:17<02:30, 75.35s/it] 86%|████████▌ | 6/7 [07:32<01:15, 75.32s/it] 100%|██████████| 7/7 [08:47<00:00, 75.24s/it] 100%|██████████| 7/7 [08:47<00:00, 75.34s/it] +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 1: generating actions ... +>>> Step 1: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 2: generating actions ... +>>> Step 2: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 3: generating actions ... +>>> Step 3: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 4: generating actions ... +>>> Step 4: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 5: generating actions ... +>>> Step 5: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 6: generating actions ... +>>> Step 6: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> + +real 10m25.792s +user 43m2.308s +sys 0m41.819s diff --git a/unitree_z1_dual_arm_stackbox/case4/output.log b/unitree_z1_dual_arm_stackbox/case4/output.log new file mode 100644 index 0000000..453317f --- /dev/null +++ b/unitree_z1_dual_arm_stackbox/case4/output.log @@ -0,0 +1,115 @@ +2026-02-11 22:07:43.398736: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. +2026-02-11 22:07:43.448264: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered +2026-02-11 22:07:43.448321: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered +2026-02-11 22:07:43.449636: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered +2026-02-11 22:07:43.457127: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. +To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. +2026-02-11 22:07:44.370935: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT +Global seed set to 123 +INFO:mainlogger:LatentVisualDiffusion: Running in v-prediction mode +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +AE working on z of shape (1, 4, 32, 32) = 4096 dimensions. +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +>>> model checkpoint loaded. +>>> Load pre-trained model ... +INFO:root:***** Configing Data ***** +>>> unitree_z1_stackbox: 1 data samples loaded. +>>> unitree_z1_stackbox: data stats loaded. +>>> unitree_z1_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox: data stats loaded. +>>> unitree_z1_dual_arm_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox_v2: data stats loaded. +>>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated. +>>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated. +>>> unitree_g1_pack_camera: 1 data samples loaded. +>>> unitree_g1_pack_camera: data stats loaded. +>>> unitree_g1_pack_camera: normalizer initiated. +>>> Dataset is successfully loaded ... +>>> Generate 16 frames under each generation ... +DEBUG:h5py._conv:Creating converter from 3 to 5 +DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13 +DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9 +DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096 + 0%| | 0/7 [00:00>> Step 0: generating actions ... +>>> Step 0: interacting with world model ... +DEBUG:PIL.Image:Importing BlpImagePlugin +DEBUG:PIL.Image:Importing BmpImagePlugin +DEBUG:PIL.Image:Importing BufrStubImagePlugin +DEBUG:PIL.Image:Importing CurImagePlugin +DEBUG:PIL.Image:Importing DcxImagePlugin +DEBUG:PIL.Image:Importing DdsImagePlugin +DEBUG:PIL.Image:Importing EpsImagePlugin +DEBUG:PIL.Image:Importing FitsImagePlugin +DEBUG:PIL.Image:Importing FitsStubImagePlugin +DEBUG:PIL.Image:Importing FliImagePlugin +DEBUG:PIL.Image:Importing FpxImagePlugin +DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing FtexImagePlugin +DEBUG:PIL.Image:Importing GbrImagePlugin +DEBUG:PIL.Image:Importing GifImagePlugin +DEBUG:PIL.Image:Importing GribStubImagePlugin +DEBUG:PIL.Image:Importing Hdf5StubImagePlugin +DEBUG:PIL.Image:Importing IcnsImagePlugin +DEBUG:PIL.Image:Importing IcoImagePlugin +DEBUG:PIL.Image:Importing ImImagePlugin +DEBUG:PIL.Image:Importing ImtImagePlugin +DEBUG:PIL.Image:Importing IptcImagePlugin +DEBUG:PIL.Image:Importing JpegImagePlugin +DEBUG:PIL.Image:Importing Jpeg2KImagePlugin +DEBUG:PIL.Image:Importing McIdasImagePlugin +DEBUG:PIL.Image:Importing MicImagePlugin +DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing MpegImagePlugin +DEBUG:PIL.Image:Importing MpoImagePlugin +DEBUG:PIL.Image:Importing MspImagePlugin +DEBUG:PIL.Image:Importing PalmImagePlugin +DEBUG:PIL.Image:Importing PcdImagePlugin +DEBUG:PIL.Image:Importing PcxImagePlugin +DEBUG:PIL.Image:Importing PdfImagePlugin +DEBUG:PIL.Image:Importing PixarImagePlugin +DEBUG:PIL.Image:Importing PngImagePlugin +DEBUG:PIL.Image:Importing PpmImagePlugin +DEBUG:PIL.Image:Importing PsdImagePlugin +DEBUG:PIL.Image:Importing QoiImagePlugin +DEBUG:PIL.Image:Importing SgiImagePlugin +DEBUG:PIL.Image:Importing SpiderImagePlugin +DEBUG:PIL.Image:Importing SunImagePlugin +DEBUG:PIL.Image:Importing TgaImagePlugin +DEBUG:PIL.Image:Importing TiffImagePlugin +DEBUG:PIL.Image:Importing WebPImagePlugin +DEBUG:PIL.Image:Importing WmfImagePlugin +DEBUG:PIL.Image:Importing XbmImagePlugin +DEBUG:PIL.Image:Importing XpmImagePlugin +DEBUG:PIL.Image:Importing XVThumbImagePlugin + 14%|█▍ | 1/7 [01:17<07:42, 77.04s/it] 29%|██▊ | 2/7 [02:33<06:24, 76.95s/it] 43%|████▎ | 3/7 [03:50<05:07, 76.87s/it] 57%|█████▋ | 4/7 [05:06<03:49, 76.59s/it] 71%|███████▏ | 5/7 [06:24<02:33, 76.82s/it] 86%|████████▌ | 6/7 [07:39<01:16, 76.43s/it] 100%|██████████| 7/7 [08:55<00:00, 76.06s/it] 100%|██████████| 7/7 [08:55<00:00, 76.44s/it] +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 1: generating actions ... +>>> Step 1: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 2: generating actions ... +>>> Step 2: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 3: generating actions ... +>>> Step 3: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 4: generating actions ... +>>> Step 4: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 5: generating actions ... +>>> Step 5: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 6: generating actions ... +>>> Step 6: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> + +real 10m33.965s +user 42m57.756s +sys 0m41.772s diff --git a/unitree_z1_dual_arm_stackbox_v2/case1/output.log b/unitree_z1_dual_arm_stackbox_v2/case1/output.log new file mode 100644 index 0000000..5948cf0 --- /dev/null +++ b/unitree_z1_dual_arm_stackbox_v2/case1/output.log @@ -0,0 +1,127 @@ +2026-02-11 22:18:17.396072: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. +2026-02-11 22:18:17.446095: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered +2026-02-11 22:18:17.446154: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered +2026-02-11 22:18:17.447480: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered +2026-02-11 22:18:17.455025: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. +To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. +2026-02-11 22:18:18.367007: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT +Global seed set to 123 +INFO:mainlogger:LatentVisualDiffusion: Running in v-prediction mode +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +AE working on z of shape (1, 4, 32, 32) = 4096 dimensions. +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +>>> model checkpoint loaded. +>>> Load pre-trained model ... +INFO:root:***** Configing Data ***** +>>> unitree_z1_stackbox: 1 data samples loaded. +>>> unitree_z1_stackbox: data stats loaded. +>>> unitree_z1_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox: data stats loaded. +>>> unitree_z1_dual_arm_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox_v2: data stats loaded. +>>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated. +>>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated. +>>> unitree_g1_pack_camera: 1 data samples loaded. +>>> unitree_g1_pack_camera: data stats loaded. +>>> unitree_g1_pack_camera: normalizer initiated. +>>> Dataset is successfully loaded ... +>>> Generate 16 frames under each generation ... +DEBUG:h5py._conv:Creating converter from 3 to 5 +DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13 +DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9 +DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096 + 0%| | 0/11 [00:00>> Step 0: generating actions ... +>>> Step 0: interacting with world model ... +DEBUG:PIL.Image:Importing BlpImagePlugin +DEBUG:PIL.Image:Importing BmpImagePlugin +DEBUG:PIL.Image:Importing BufrStubImagePlugin +DEBUG:PIL.Image:Importing CurImagePlugin +DEBUG:PIL.Image:Importing DcxImagePlugin +DEBUG:PIL.Image:Importing DdsImagePlugin +DEBUG:PIL.Image:Importing EpsImagePlugin +DEBUG:PIL.Image:Importing FitsImagePlugin +DEBUG:PIL.Image:Importing FitsStubImagePlugin +DEBUG:PIL.Image:Importing FliImagePlugin +DEBUG:PIL.Image:Importing FpxImagePlugin +DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing FtexImagePlugin +DEBUG:PIL.Image:Importing GbrImagePlugin +DEBUG:PIL.Image:Importing GifImagePlugin +DEBUG:PIL.Image:Importing GribStubImagePlugin +DEBUG:PIL.Image:Importing Hdf5StubImagePlugin +DEBUG:PIL.Image:Importing IcnsImagePlugin +DEBUG:PIL.Image:Importing IcoImagePlugin +DEBUG:PIL.Image:Importing ImImagePlugin +DEBUG:PIL.Image:Importing ImtImagePlugin +DEBUG:PIL.Image:Importing IptcImagePlugin +DEBUG:PIL.Image:Importing JpegImagePlugin +DEBUG:PIL.Image:Importing Jpeg2KImagePlugin +DEBUG:PIL.Image:Importing McIdasImagePlugin +DEBUG:PIL.Image:Importing MicImagePlugin +DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing MpegImagePlugin +DEBUG:PIL.Image:Importing MpoImagePlugin +DEBUG:PIL.Image:Importing MspImagePlugin +DEBUG:PIL.Image:Importing PalmImagePlugin +DEBUG:PIL.Image:Importing PcdImagePlugin +DEBUG:PIL.Image:Importing PcxImagePlugin +DEBUG:PIL.Image:Importing PdfImagePlugin +DEBUG:PIL.Image:Importing PixarImagePlugin +DEBUG:PIL.Image:Importing PngImagePlugin +DEBUG:PIL.Image:Importing PpmImagePlugin +DEBUG:PIL.Image:Importing PsdImagePlugin +DEBUG:PIL.Image:Importing QoiImagePlugin +DEBUG:PIL.Image:Importing SgiImagePlugin +DEBUG:PIL.Image:Importing SpiderImagePlugin +DEBUG:PIL.Image:Importing SunImagePlugin +DEBUG:PIL.Image:Importing TgaImagePlugin +DEBUG:PIL.Image:Importing TiffImagePlugin +DEBUG:PIL.Image:Importing WebPImagePlugin +DEBUG:PIL.Image:Importing WmfImagePlugin +DEBUG:PIL.Image:Importing XbmImagePlugin +DEBUG:PIL.Image:Importing XpmImagePlugin +DEBUG:PIL.Image:Importing XVThumbImagePlugin + 9%|▉ | 1/11 [01:15<12:35, 75.53s/it] 18%|█▊ | 2/11 [02:30<11:18, 75.39s/it] 27%|██▋ | 3/11 [03:46<10:03, 75.38s/it] 36%|███▋ | 4/11 [05:01<08:48, 75.47s/it] 45%|████▌ | 5/11 [06:16<07:31, 75.32s/it] 55%|█████▍ | 6/11 [07:31<06:15, 75.08s/it] 64%|██████▎ | 7/11 [08:46<05:00, 75.07s/it] 73%|███████▎ | 8/11 [10:00<03:44, 74.76s/it] 82%|████████▏ | 9/11 [11:15<02:29, 74.87s/it] 91%|█████████ | 10/11 [12:30<01:14, 74.79s/it] 100%|██████████| 11/11 [13:45<00:00, 74.80s/it] 100%|██████████| 11/11 [13:45<00:00, 75.02s/it] +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 1: generating actions ... +>>> Step 1: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 2: generating actions ... +>>> Step 2: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 3: generating actions ... +>>> Step 3: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 4: generating actions ... +>>> Step 4: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 5: generating actions ... +>>> Step 5: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 6: generating actions ... +>>> Step 6: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 7: generating actions ... +>>> Step 7: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 8: generating actions ... +>>> Step 8: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 9: generating actions ... +>>> Step 9: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 10: generating actions ... +>>> Step 10: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> + +real 15m24.880s +user 65m40.817s +sys 0m41.445s diff --git a/unitree_z1_dual_arm_stackbox_v2/case2/output.log b/unitree_z1_dual_arm_stackbox_v2/case2/output.log new file mode 100644 index 0000000..ceee7fc --- /dev/null +++ b/unitree_z1_dual_arm_stackbox_v2/case2/output.log @@ -0,0 +1,127 @@ +2026-02-11 22:33:42.261398: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. +2026-02-11 22:33:42.310786: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered +2026-02-11 22:33:42.310845: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered +2026-02-11 22:33:42.312191: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered +2026-02-11 22:33:42.319738: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. +To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. +2026-02-11 22:33:43.232517: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT +Global seed set to 123 +INFO:mainlogger:LatentVisualDiffusion: Running in v-prediction mode +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +AE working on z of shape (1, 4, 32, 32) = 4096 dimensions. +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +>>> model checkpoint loaded. +>>> Load pre-trained model ... +INFO:root:***** Configing Data ***** +>>> unitree_z1_stackbox: 1 data samples loaded. +>>> unitree_z1_stackbox: data stats loaded. +>>> unitree_z1_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox: data stats loaded. +>>> unitree_z1_dual_arm_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox_v2: data stats loaded. +>>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated. +>>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated. +>>> unitree_g1_pack_camera: 1 data samples loaded. +>>> unitree_g1_pack_camera: data stats loaded. +>>> unitree_g1_pack_camera: normalizer initiated. +>>> Dataset is successfully loaded ... +>>> Generate 16 frames under each generation ... +DEBUG:h5py._conv:Creating converter from 3 to 5 +DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13 +DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9 +DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096 + 0%| | 0/11 [00:00>> Step 0: generating actions ... +>>> Step 0: interacting with world model ... +DEBUG:PIL.Image:Importing BlpImagePlugin +DEBUG:PIL.Image:Importing BmpImagePlugin +DEBUG:PIL.Image:Importing BufrStubImagePlugin +DEBUG:PIL.Image:Importing CurImagePlugin +DEBUG:PIL.Image:Importing DcxImagePlugin +DEBUG:PIL.Image:Importing DdsImagePlugin +DEBUG:PIL.Image:Importing EpsImagePlugin +DEBUG:PIL.Image:Importing FitsImagePlugin +DEBUG:PIL.Image:Importing FitsStubImagePlugin +DEBUG:PIL.Image:Importing FliImagePlugin +DEBUG:PIL.Image:Importing FpxImagePlugin +DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing FtexImagePlugin +DEBUG:PIL.Image:Importing GbrImagePlugin +DEBUG:PIL.Image:Importing GifImagePlugin +DEBUG:PIL.Image:Importing GribStubImagePlugin +DEBUG:PIL.Image:Importing Hdf5StubImagePlugin +DEBUG:PIL.Image:Importing IcnsImagePlugin +DEBUG:PIL.Image:Importing IcoImagePlugin +DEBUG:PIL.Image:Importing ImImagePlugin +DEBUG:PIL.Image:Importing ImtImagePlugin +DEBUG:PIL.Image:Importing IptcImagePlugin +DEBUG:PIL.Image:Importing JpegImagePlugin +DEBUG:PIL.Image:Importing Jpeg2KImagePlugin +DEBUG:PIL.Image:Importing McIdasImagePlugin +DEBUG:PIL.Image:Importing MicImagePlugin +DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing MpegImagePlugin +DEBUG:PIL.Image:Importing MpoImagePlugin +DEBUG:PIL.Image:Importing MspImagePlugin +DEBUG:PIL.Image:Importing PalmImagePlugin +DEBUG:PIL.Image:Importing PcdImagePlugin +DEBUG:PIL.Image:Importing PcxImagePlugin +DEBUG:PIL.Image:Importing PdfImagePlugin +DEBUG:PIL.Image:Importing PixarImagePlugin +DEBUG:PIL.Image:Importing PngImagePlugin +DEBUG:PIL.Image:Importing PpmImagePlugin +DEBUG:PIL.Image:Importing PsdImagePlugin +DEBUG:PIL.Image:Importing QoiImagePlugin +DEBUG:PIL.Image:Importing SgiImagePlugin +DEBUG:PIL.Image:Importing SpiderImagePlugin +DEBUG:PIL.Image:Importing SunImagePlugin +DEBUG:PIL.Image:Importing TgaImagePlugin +DEBUG:PIL.Image:Importing TiffImagePlugin +DEBUG:PIL.Image:Importing WebPImagePlugin +DEBUG:PIL.Image:Importing WmfImagePlugin +DEBUG:PIL.Image:Importing XbmImagePlugin +DEBUG:PIL.Image:Importing XpmImagePlugin +DEBUG:PIL.Image:Importing XVThumbImagePlugin + 9%|▉ | 1/11 [01:13<12:18, 73.90s/it] 18%|█▊ | 2/11 [02:27<11:05, 73.99s/it] 27%|██▋ | 3/11 [03:41<09:50, 73.86s/it] 36%|███▋ | 4/11 [04:55<08:35, 73.70s/it] 45%|████▌ | 5/11 [06:08<07:20, 73.48s/it] 55%|█████▍ | 6/11 [07:21<06:06, 73.39s/it] 64%|██████▎ | 7/11 [08:34<04:53, 73.28s/it] 73%|███████▎ | 8/11 [09:47<03:39, 73.11s/it] 82%|████████▏ | 9/11 [11:00<02:26, 73.21s/it] 91%|█████████ | 10/11 [12:14<01:13, 73.49s/it] 100%|██████████| 11/11 [13:28<00:00, 73.55s/it] 100%|██████████| 11/11 [13:28<00:00, 73.50s/it] +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 1: generating actions ... +>>> Step 1: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 2: generating actions ... +>>> Step 2: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 3: generating actions ... +>>> Step 3: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 4: generating actions ... +>>> Step 4: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 5: generating actions ... +>>> Step 5: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 6: generating actions ... +>>> Step 6: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 7: generating actions ... +>>> Step 7: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 8: generating actions ... +>>> Step 8: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 9: generating actions ... +>>> Step 9: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 10: generating actions ... +>>> Step 10: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> + +real 15m7.472s +user 65m58.841s +sys 0m41.599s diff --git a/unitree_z1_dual_arm_stackbox_v2/case3/output.log b/unitree_z1_dual_arm_stackbox_v2/case3/output.log new file mode 100644 index 0000000..e1eaa3c --- /dev/null +++ b/unitree_z1_dual_arm_stackbox_v2/case3/output.log @@ -0,0 +1,127 @@ +2026-02-11 22:48:49.761688: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. +2026-02-11 22:48:49.811395: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered +2026-02-11 22:48:49.811456: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered +2026-02-11 22:48:49.812798: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered +2026-02-11 22:48:49.820307: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. +To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. +2026-02-11 22:48:50.732941: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT +Global seed set to 123 +INFO:mainlogger:LatentVisualDiffusion: Running in v-prediction mode +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +AE working on z of shape (1, 4, 32, 32) = 4096 dimensions. +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +>>> model checkpoint loaded. +>>> Load pre-trained model ... +INFO:root:***** Configing Data ***** +>>> unitree_z1_stackbox: 1 data samples loaded. +>>> unitree_z1_stackbox: data stats loaded. +>>> unitree_z1_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox: data stats loaded. +>>> unitree_z1_dual_arm_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox_v2: data stats loaded. +>>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated. +>>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated. +>>> unitree_g1_pack_camera: 1 data samples loaded. +>>> unitree_g1_pack_camera: data stats loaded. +>>> unitree_g1_pack_camera: normalizer initiated. +>>> Dataset is successfully loaded ... +>>> Generate 16 frames under each generation ... +DEBUG:h5py._conv:Creating converter from 3 to 5 +DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13 +DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9 +DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096 + 0%| | 0/11 [00:00>> Step 0: generating actions ... +>>> Step 0: interacting with world model ... +DEBUG:PIL.Image:Importing BlpImagePlugin +DEBUG:PIL.Image:Importing BmpImagePlugin +DEBUG:PIL.Image:Importing BufrStubImagePlugin +DEBUG:PIL.Image:Importing CurImagePlugin +DEBUG:PIL.Image:Importing DcxImagePlugin +DEBUG:PIL.Image:Importing DdsImagePlugin +DEBUG:PIL.Image:Importing EpsImagePlugin +DEBUG:PIL.Image:Importing FitsImagePlugin +DEBUG:PIL.Image:Importing FitsStubImagePlugin +DEBUG:PIL.Image:Importing FliImagePlugin +DEBUG:PIL.Image:Importing FpxImagePlugin +DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing FtexImagePlugin +DEBUG:PIL.Image:Importing GbrImagePlugin +DEBUG:PIL.Image:Importing GifImagePlugin +DEBUG:PIL.Image:Importing GribStubImagePlugin +DEBUG:PIL.Image:Importing Hdf5StubImagePlugin +DEBUG:PIL.Image:Importing IcnsImagePlugin +DEBUG:PIL.Image:Importing IcoImagePlugin +DEBUG:PIL.Image:Importing ImImagePlugin +DEBUG:PIL.Image:Importing ImtImagePlugin +DEBUG:PIL.Image:Importing IptcImagePlugin +DEBUG:PIL.Image:Importing JpegImagePlugin +DEBUG:PIL.Image:Importing Jpeg2KImagePlugin +DEBUG:PIL.Image:Importing McIdasImagePlugin +DEBUG:PIL.Image:Importing MicImagePlugin +DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing MpegImagePlugin +DEBUG:PIL.Image:Importing MpoImagePlugin +DEBUG:PIL.Image:Importing MspImagePlugin +DEBUG:PIL.Image:Importing PalmImagePlugin +DEBUG:PIL.Image:Importing PcdImagePlugin +DEBUG:PIL.Image:Importing PcxImagePlugin +DEBUG:PIL.Image:Importing PdfImagePlugin +DEBUG:PIL.Image:Importing PixarImagePlugin +DEBUG:PIL.Image:Importing PngImagePlugin +DEBUG:PIL.Image:Importing PpmImagePlugin +DEBUG:PIL.Image:Importing PsdImagePlugin +DEBUG:PIL.Image:Importing QoiImagePlugin +DEBUG:PIL.Image:Importing SgiImagePlugin +DEBUG:PIL.Image:Importing SpiderImagePlugin +DEBUG:PIL.Image:Importing SunImagePlugin +DEBUG:PIL.Image:Importing TgaImagePlugin +DEBUG:PIL.Image:Importing TiffImagePlugin +DEBUG:PIL.Image:Importing WebPImagePlugin +DEBUG:PIL.Image:Importing WmfImagePlugin +DEBUG:PIL.Image:Importing XbmImagePlugin +DEBUG:PIL.Image:Importing XpmImagePlugin +DEBUG:PIL.Image:Importing XVThumbImagePlugin + 9%|▉ | 1/11 [01:14<12:29, 74.99s/it] 18%|█▊ | 2/11 [02:30<11:18, 75.44s/it] 27%|██▋ | 3/11 [03:46<10:03, 75.49s/it] 36%|███▋ | 4/11 [05:01<08:47, 75.30s/it] 45%|████▌ | 5/11 [06:15<07:30, 75.02s/it] 55%|█████▍ | 6/11 [07:30<06:14, 74.84s/it] 64%|██████▎ | 7/11 [08:44<04:59, 74.79s/it] 73%|███████▎ | 8/11 [10:00<03:44, 74.94s/it] 82%|████████▏ | 9/11 [11:15<02:29, 74.89s/it] 91%|█████████ | 10/11 [12:30<01:14, 74.95s/it] 100%|██████████| 11/11 [13:45<00:00, 74.95s/it] 100%|██████████| 11/11 [13:45<00:00, 75.01s/it] +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 1: generating actions ... +>>> Step 1: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 2: generating actions ... +>>> Step 2: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 3: generating actions ... +>>> Step 3: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 4: generating actions ... +>>> Step 4: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 5: generating actions ... +>>> Step 5: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 6: generating actions ... +>>> Step 6: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 7: generating actions ... +>>> Step 7: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 8: generating actions ... +>>> Step 8: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 9: generating actions ... +>>> Step 9: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 10: generating actions ... +>>> Step 10: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> + +real 15m26.006s +user 65m35.774s +sys 0m44.636s diff --git a/unitree_z1_dual_arm_stackbox_v2/case4/output.log b/unitree_z1_dual_arm_stackbox_v2/case4/output.log new file mode 100644 index 0000000..60119bb --- /dev/null +++ b/unitree_z1_dual_arm_stackbox_v2/case4/output.log @@ -0,0 +1,127 @@ +2026-02-11 23:04:15.762959: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. +2026-02-11 23:04:15.814243: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered +2026-02-11 23:04:15.814301: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered +2026-02-11 23:04:15.815653: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered +2026-02-11 23:04:15.823287: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. +To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. +2026-02-11 23:04:16.742609: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT +Global seed set to 123 +INFO:mainlogger:LatentVisualDiffusion: Running in v-prediction mode +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +AE working on z of shape (1, 4, 32, 32) = 4096 dimensions. +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +>>> model checkpoint loaded. +>>> Load pre-trained model ... +INFO:root:***** Configing Data ***** +>>> unitree_z1_stackbox: 1 data samples loaded. +>>> unitree_z1_stackbox: data stats loaded. +>>> unitree_z1_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox: data stats loaded. +>>> unitree_z1_dual_arm_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox_v2: data stats loaded. +>>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated. +>>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated. +>>> unitree_g1_pack_camera: 1 data samples loaded. +>>> unitree_g1_pack_camera: data stats loaded. +>>> unitree_g1_pack_camera: normalizer initiated. +>>> Dataset is successfully loaded ... +>>> Generate 16 frames under each generation ... +DEBUG:h5py._conv:Creating converter from 3 to 5 +DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13 +DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9 +DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096 + 0%| | 0/11 [00:00>> Step 0: generating actions ... +>>> Step 0: interacting with world model ... +DEBUG:PIL.Image:Importing BlpImagePlugin +DEBUG:PIL.Image:Importing BmpImagePlugin +DEBUG:PIL.Image:Importing BufrStubImagePlugin +DEBUG:PIL.Image:Importing CurImagePlugin +DEBUG:PIL.Image:Importing DcxImagePlugin +DEBUG:PIL.Image:Importing DdsImagePlugin +DEBUG:PIL.Image:Importing EpsImagePlugin +DEBUG:PIL.Image:Importing FitsImagePlugin +DEBUG:PIL.Image:Importing FitsStubImagePlugin +DEBUG:PIL.Image:Importing FliImagePlugin +DEBUG:PIL.Image:Importing FpxImagePlugin +DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing FtexImagePlugin +DEBUG:PIL.Image:Importing GbrImagePlugin +DEBUG:PIL.Image:Importing GifImagePlugin +DEBUG:PIL.Image:Importing GribStubImagePlugin +DEBUG:PIL.Image:Importing Hdf5StubImagePlugin +DEBUG:PIL.Image:Importing IcnsImagePlugin +DEBUG:PIL.Image:Importing IcoImagePlugin +DEBUG:PIL.Image:Importing ImImagePlugin +DEBUG:PIL.Image:Importing ImtImagePlugin +DEBUG:PIL.Image:Importing IptcImagePlugin +DEBUG:PIL.Image:Importing JpegImagePlugin +DEBUG:PIL.Image:Importing Jpeg2KImagePlugin +DEBUG:PIL.Image:Importing McIdasImagePlugin +DEBUG:PIL.Image:Importing MicImagePlugin +DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing MpegImagePlugin +DEBUG:PIL.Image:Importing MpoImagePlugin +DEBUG:PIL.Image:Importing MspImagePlugin +DEBUG:PIL.Image:Importing PalmImagePlugin +DEBUG:PIL.Image:Importing PcdImagePlugin +DEBUG:PIL.Image:Importing PcxImagePlugin +DEBUG:PIL.Image:Importing PdfImagePlugin +DEBUG:PIL.Image:Importing PixarImagePlugin +DEBUG:PIL.Image:Importing PngImagePlugin +DEBUG:PIL.Image:Importing PpmImagePlugin +DEBUG:PIL.Image:Importing PsdImagePlugin +DEBUG:PIL.Image:Importing QoiImagePlugin +DEBUG:PIL.Image:Importing SgiImagePlugin +DEBUG:PIL.Image:Importing SpiderImagePlugin +DEBUG:PIL.Image:Importing SunImagePlugin +DEBUG:PIL.Image:Importing TgaImagePlugin +DEBUG:PIL.Image:Importing TiffImagePlugin +DEBUG:PIL.Image:Importing WebPImagePlugin +DEBUG:PIL.Image:Importing WmfImagePlugin +DEBUG:PIL.Image:Importing XbmImagePlugin +DEBUG:PIL.Image:Importing XpmImagePlugin +DEBUG:PIL.Image:Importing XVThumbImagePlugin + 9%|▉ | 1/11 [01:14<12:25, 74.55s/it] 18%|█▊ | 2/11 [02:29<11:13, 74.83s/it] 27%|██▋ | 3/11 [03:44<09:58, 74.77s/it] 36%|███▋ | 4/11 [04:59<08:43, 74.78s/it] 45%|████▌ | 5/11 [06:13<07:28, 74.83s/it] 55%|█████▍ | 6/11 [07:28<06:13, 74.62s/it] 64%|██████▎ | 7/11 [08:42<04:57, 74.37s/it] 73%|███████▎ | 8/11 [09:56<03:42, 74.28s/it] 82%|████████▏ | 9/11 [11:10<02:28, 74.26s/it] 91%|█████████ | 10/11 [12:24<01:14, 74.31s/it] 100%|██████████| 11/11 [13:39<00:00, 74.38s/it] 100%|██████████| 11/11 [13:39<00:00, 74.48s/it] +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 1: generating actions ... +>>> Step 1: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 2: generating actions ... +>>> Step 2: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 3: generating actions ... +>>> Step 3: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 4: generating actions ... +>>> Step 4: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 5: generating actions ... +>>> Step 5: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 6: generating actions ... +>>> Step 6: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 7: generating actions ... +>>> Step 7: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 8: generating actions ... +>>> Step 8: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 9: generating actions ... +>>> Step 9: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 10: generating actions ... +>>> Step 10: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> + +real 15m20.607s +user 66m10.462s +sys 0m45.655s diff --git a/unitree_z1_stackbox/case1/output.log b/unitree_z1_stackbox/case1/output.log new file mode 100644 index 0000000..ae49f13 --- /dev/null +++ b/unitree_z1_stackbox/case1/output.log @@ -0,0 +1,130 @@ +2026-02-11 23:19:36.475817: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. +2026-02-11 23:19:36.525118: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered +2026-02-11 23:19:36.525172: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered +2026-02-11 23:19:36.526479: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered +2026-02-11 23:19:36.533981: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. +To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. +2026-02-11 23:19:37.461985: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT +Global seed set to 123 +INFO:mainlogger:LatentVisualDiffusion: Running in v-prediction mode +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +AE working on z of shape (1, 4, 32, 32) = 4096 dimensions. +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +>>> model checkpoint loaded. +>>> Load pre-trained model ... +INFO:root:***** Configing Data ***** +>>> unitree_z1_stackbox: 1 data samples loaded. +>>> unitree_z1_stackbox: data stats loaded. +>>> unitree_z1_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox: data stats loaded. +>>> unitree_z1_dual_arm_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox_v2: data stats loaded. +>>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated. +>>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated. +>>> unitree_g1_pack_camera: 1 data samples loaded. +>>> unitree_g1_pack_camera: data stats loaded. +>>> unitree_g1_pack_camera: normalizer initiated. +>>> Dataset is successfully loaded ... +>>> Generate 16 frames under each generation ... +DEBUG:h5py._conv:Creating converter from 3 to 5 +DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13 +DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9 +DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096 + 0%| | 0/12 [00:00>> Step 0: generating actions ... +>>> Step 0: interacting with world model ... +DEBUG:PIL.Image:Importing BlpImagePlugin +DEBUG:PIL.Image:Importing BmpImagePlugin +DEBUG:PIL.Image:Importing BufrStubImagePlugin +DEBUG:PIL.Image:Importing CurImagePlugin +DEBUG:PIL.Image:Importing DcxImagePlugin +DEBUG:PIL.Image:Importing DdsImagePlugin +DEBUG:PIL.Image:Importing EpsImagePlugin +DEBUG:PIL.Image:Importing FitsImagePlugin +DEBUG:PIL.Image:Importing FitsStubImagePlugin +DEBUG:PIL.Image:Importing FliImagePlugin +DEBUG:PIL.Image:Importing FpxImagePlugin +DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing FtexImagePlugin +DEBUG:PIL.Image:Importing GbrImagePlugin +DEBUG:PIL.Image:Importing GifImagePlugin +DEBUG:PIL.Image:Importing GribStubImagePlugin +DEBUG:PIL.Image:Importing Hdf5StubImagePlugin +DEBUG:PIL.Image:Importing IcnsImagePlugin +DEBUG:PIL.Image:Importing IcoImagePlugin +DEBUG:PIL.Image:Importing ImImagePlugin +DEBUG:PIL.Image:Importing ImtImagePlugin +DEBUG:PIL.Image:Importing IptcImagePlugin +DEBUG:PIL.Image:Importing JpegImagePlugin +DEBUG:PIL.Image:Importing Jpeg2KImagePlugin +DEBUG:PIL.Image:Importing McIdasImagePlugin +DEBUG:PIL.Image:Importing MicImagePlugin +DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing MpegImagePlugin +DEBUG:PIL.Image:Importing MpoImagePlugin +DEBUG:PIL.Image:Importing MspImagePlugin +DEBUG:PIL.Image:Importing PalmImagePlugin +DEBUG:PIL.Image:Importing PcdImagePlugin +DEBUG:PIL.Image:Importing PcxImagePlugin +DEBUG:PIL.Image:Importing PdfImagePlugin +DEBUG:PIL.Image:Importing PixarImagePlugin +DEBUG:PIL.Image:Importing PngImagePlugin +DEBUG:PIL.Image:Importing PpmImagePlugin +DEBUG:PIL.Image:Importing PsdImagePlugin +DEBUG:PIL.Image:Importing QoiImagePlugin +DEBUG:PIL.Image:Importing SgiImagePlugin +DEBUG:PIL.Image:Importing SpiderImagePlugin +DEBUG:PIL.Image:Importing SunImagePlugin +DEBUG:PIL.Image:Importing TgaImagePlugin +DEBUG:PIL.Image:Importing TiffImagePlugin +DEBUG:PIL.Image:Importing WebPImagePlugin +DEBUG:PIL.Image:Importing WmfImagePlugin +DEBUG:PIL.Image:Importing XbmImagePlugin +DEBUG:PIL.Image:Importing XpmImagePlugin +DEBUG:PIL.Image:Importing XVThumbImagePlugin + 8%|▊ | 1/12 [01:14<13:38, 74.37s/it] 17%|█▋ | 2/12 [02:28<12:21, 74.13s/it] 25%|██▌ | 3/12 [03:42<11:05, 73.97s/it] 33%|███▎ | 4/12 [04:55<09:51, 73.92s/it] 42%|████▏ | 5/12 [06:09<08:35, 73.70s/it] 50%|█████ | 6/12 [07:22<07:21, 73.58s/it] 58%|█████▊ | 7/12 [08:35<06:07, 73.49s/it] 67%|██████▋ | 8/12 [09:49<04:53, 73.46s/it] 75%|███████▌ | 9/12 [11:02<03:40, 73.42s/it] 83%|████████▎ | 10/12 [12:16<02:26, 73.44s/it] 92%|█████████▏| 11/12 [13:29<01:13, 73.40s/it] 100%|██████████| 12/12 [14:42<00:00, 73.32s/it] 100%|██████████| 12/12 [14:42<00:00, 73.55s/it] +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 1: generating actions ... +>>> Step 1: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 2: generating actions ... +>>> Step 2: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 3: generating actions ... +>>> Step 3: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 4: generating actions ... +>>> Step 4: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 5: generating actions ... +>>> Step 5: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 6: generating actions ... +>>> Step 6: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 7: generating actions ... +>>> Step 7: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 8: generating actions ... +>>> Step 8: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 9: generating actions ... +>>> Step 9: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 10: generating actions ... +>>> Step 10: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 11: generating actions ... +>>> Step 11: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> + +real 16m18.361s +user 71m2.856s +sys 0m44.193s diff --git a/unitree_z1_stackbox/case2/output.log b/unitree_z1_stackbox/case2/output.log new file mode 100644 index 0000000..7c74770 --- /dev/null +++ b/unitree_z1_stackbox/case2/output.log @@ -0,0 +1,130 @@ +2026-02-11 23:35:52.961572: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. +2026-02-11 23:35:53.011562: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered +2026-02-11 23:35:53.011622: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered +2026-02-11 23:35:53.012961: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered +2026-02-11 23:35:53.020520: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. +To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. +2026-02-11 23:35:53.953177: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT +Global seed set to 123 +INFO:mainlogger:LatentVisualDiffusion: Running in v-prediction mode +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +AE working on z of shape (1, 4, 32, 32) = 4096 dimensions. +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +>>> model checkpoint loaded. +>>> Load pre-trained model ... +INFO:root:***** Configing Data ***** +>>> unitree_z1_stackbox: 1 data samples loaded. +>>> unitree_z1_stackbox: data stats loaded. +>>> unitree_z1_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox: data stats loaded. +>>> unitree_z1_dual_arm_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox_v2: data stats loaded. +>>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated. +>>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated. +>>> unitree_g1_pack_camera: 1 data samples loaded. +>>> unitree_g1_pack_camera: data stats loaded. +>>> unitree_g1_pack_camera: normalizer initiated. +>>> Dataset is successfully loaded ... +>>> Generate 16 frames under each generation ... +DEBUG:h5py._conv:Creating converter from 3 to 5 +DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13 +DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9 +DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096 + 0%| | 0/12 [00:00>> Step 0: generating actions ... +>>> Step 0: interacting with world model ... +DEBUG:PIL.Image:Importing BlpImagePlugin +DEBUG:PIL.Image:Importing BmpImagePlugin +DEBUG:PIL.Image:Importing BufrStubImagePlugin +DEBUG:PIL.Image:Importing CurImagePlugin +DEBUG:PIL.Image:Importing DcxImagePlugin +DEBUG:PIL.Image:Importing DdsImagePlugin +DEBUG:PIL.Image:Importing EpsImagePlugin +DEBUG:PIL.Image:Importing FitsImagePlugin +DEBUG:PIL.Image:Importing FitsStubImagePlugin +DEBUG:PIL.Image:Importing FliImagePlugin +DEBUG:PIL.Image:Importing FpxImagePlugin +DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing FtexImagePlugin +DEBUG:PIL.Image:Importing GbrImagePlugin +DEBUG:PIL.Image:Importing GifImagePlugin +DEBUG:PIL.Image:Importing GribStubImagePlugin +DEBUG:PIL.Image:Importing Hdf5StubImagePlugin +DEBUG:PIL.Image:Importing IcnsImagePlugin +DEBUG:PIL.Image:Importing IcoImagePlugin +DEBUG:PIL.Image:Importing ImImagePlugin +DEBUG:PIL.Image:Importing ImtImagePlugin +DEBUG:PIL.Image:Importing IptcImagePlugin +DEBUG:PIL.Image:Importing JpegImagePlugin +DEBUG:PIL.Image:Importing Jpeg2KImagePlugin +DEBUG:PIL.Image:Importing McIdasImagePlugin +DEBUG:PIL.Image:Importing MicImagePlugin +DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing MpegImagePlugin +DEBUG:PIL.Image:Importing MpoImagePlugin +DEBUG:PIL.Image:Importing MspImagePlugin +DEBUG:PIL.Image:Importing PalmImagePlugin +DEBUG:PIL.Image:Importing PcdImagePlugin +DEBUG:PIL.Image:Importing PcxImagePlugin +DEBUG:PIL.Image:Importing PdfImagePlugin +DEBUG:PIL.Image:Importing PixarImagePlugin +DEBUG:PIL.Image:Importing PngImagePlugin +DEBUG:PIL.Image:Importing PpmImagePlugin +DEBUG:PIL.Image:Importing PsdImagePlugin +DEBUG:PIL.Image:Importing QoiImagePlugin +DEBUG:PIL.Image:Importing SgiImagePlugin +DEBUG:PIL.Image:Importing SpiderImagePlugin +DEBUG:PIL.Image:Importing SunImagePlugin +DEBUG:PIL.Image:Importing TgaImagePlugin +DEBUG:PIL.Image:Importing TiffImagePlugin +DEBUG:PIL.Image:Importing WebPImagePlugin +DEBUG:PIL.Image:Importing WmfImagePlugin +DEBUG:PIL.Image:Importing XbmImagePlugin +DEBUG:PIL.Image:Importing XpmImagePlugin +DEBUG:PIL.Image:Importing XVThumbImagePlugin + 8%|▊ | 1/12 [01:13<13:33, 73.92s/it] 17%|█▋ | 2/12 [02:28<12:22, 74.25s/it] 25%|██▌ | 3/12 [03:41<11:01, 73.53s/it] 33%|███▎ | 4/12 [04:53<09:45, 73.17s/it] 42%|████▏ | 5/12 [06:06<08:30, 72.96s/it] 50%|█████ | 6/12 [07:18<07:16, 72.80s/it] 58%|█████▊ | 7/12 [08:31<06:03, 72.71s/it] 67%|██████▋ | 8/12 [09:43<04:50, 72.64s/it] 75%|███████▌ | 9/12 [10:56<03:37, 72.61s/it] 83%|████████▎ | 10/12 [12:08<02:25, 72.56s/it] 92%|█████████▏| 11/12 [13:21<01:12, 72.53s/it] 100%|██████████| 12/12 [14:33<00:00, 72.48s/it] 100%|██████████| 12/12 [14:33<00:00, 72.80s/it] +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 1: generating actions ... +>>> Step 1: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 2: generating actions ... +>>> Step 2: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 3: generating actions ... +>>> Step 3: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 4: generating actions ... +>>> Step 4: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 5: generating actions ... +>>> Step 5: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 6: generating actions ... +>>> Step 6: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 7: generating actions ... +>>> Step 7: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 8: generating actions ... +>>> Step 8: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 9: generating actions ... +>>> Step 9: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 10: generating actions ... +>>> Step 10: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 11: generating actions ... +>>> Step 11: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> + +real 16m6.503s +user 71m18.296s +sys 0m44.031s diff --git a/unitree_z1_stackbox/case3/output.log b/unitree_z1_stackbox/case3/output.log new file mode 100644 index 0000000..3da03dc --- /dev/null +++ b/unitree_z1_stackbox/case3/output.log @@ -0,0 +1,130 @@ +2026-02-11 23:51:59.440508: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. +2026-02-11 23:51:59.489849: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered +2026-02-11 23:51:59.489897: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered +2026-02-11 23:51:59.491194: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered +2026-02-11 23:51:59.498659: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. +To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. +2026-02-11 23:52:00.422248: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT +Global seed set to 123 +INFO:mainlogger:LatentVisualDiffusion: Running in v-prediction mode +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +AE working on z of shape (1, 4, 32, 32) = 4096 dimensions. +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +>>> model checkpoint loaded. +>>> Load pre-trained model ... +INFO:root:***** Configing Data ***** +>>> unitree_z1_stackbox: 1 data samples loaded. +>>> unitree_z1_stackbox: data stats loaded. +>>> unitree_z1_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox: data stats loaded. +>>> unitree_z1_dual_arm_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox_v2: data stats loaded. +>>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated. +>>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated. +>>> unitree_g1_pack_camera: 1 data samples loaded. +>>> unitree_g1_pack_camera: data stats loaded. +>>> unitree_g1_pack_camera: normalizer initiated. +>>> Dataset is successfully loaded ... +>>> Generate 16 frames under each generation ... +DEBUG:h5py._conv:Creating converter from 3 to 5 +DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13 +DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9 +DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096 + 0%| | 0/12 [00:00>> Step 0: generating actions ... +>>> Step 0: interacting with world model ... +DEBUG:PIL.Image:Importing BlpImagePlugin +DEBUG:PIL.Image:Importing BmpImagePlugin +DEBUG:PIL.Image:Importing BufrStubImagePlugin +DEBUG:PIL.Image:Importing CurImagePlugin +DEBUG:PIL.Image:Importing DcxImagePlugin +DEBUG:PIL.Image:Importing DdsImagePlugin +DEBUG:PIL.Image:Importing EpsImagePlugin +DEBUG:PIL.Image:Importing FitsImagePlugin +DEBUG:PIL.Image:Importing FitsStubImagePlugin +DEBUG:PIL.Image:Importing FliImagePlugin +DEBUG:PIL.Image:Importing FpxImagePlugin +DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing FtexImagePlugin +DEBUG:PIL.Image:Importing GbrImagePlugin +DEBUG:PIL.Image:Importing GifImagePlugin +DEBUG:PIL.Image:Importing GribStubImagePlugin +DEBUG:PIL.Image:Importing Hdf5StubImagePlugin +DEBUG:PIL.Image:Importing IcnsImagePlugin +DEBUG:PIL.Image:Importing IcoImagePlugin +DEBUG:PIL.Image:Importing ImImagePlugin +DEBUG:PIL.Image:Importing ImtImagePlugin +DEBUG:PIL.Image:Importing IptcImagePlugin +DEBUG:PIL.Image:Importing JpegImagePlugin +DEBUG:PIL.Image:Importing Jpeg2KImagePlugin +DEBUG:PIL.Image:Importing McIdasImagePlugin +DEBUG:PIL.Image:Importing MicImagePlugin +DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing MpegImagePlugin +DEBUG:PIL.Image:Importing MpoImagePlugin +DEBUG:PIL.Image:Importing MspImagePlugin +DEBUG:PIL.Image:Importing PalmImagePlugin +DEBUG:PIL.Image:Importing PcdImagePlugin +DEBUG:PIL.Image:Importing PcxImagePlugin +DEBUG:PIL.Image:Importing PdfImagePlugin +DEBUG:PIL.Image:Importing PixarImagePlugin +DEBUG:PIL.Image:Importing PngImagePlugin +DEBUG:PIL.Image:Importing PpmImagePlugin +DEBUG:PIL.Image:Importing PsdImagePlugin +DEBUG:PIL.Image:Importing QoiImagePlugin +DEBUG:PIL.Image:Importing SgiImagePlugin +DEBUG:PIL.Image:Importing SpiderImagePlugin +DEBUG:PIL.Image:Importing SunImagePlugin +DEBUG:PIL.Image:Importing TgaImagePlugin +DEBUG:PIL.Image:Importing TiffImagePlugin +DEBUG:PIL.Image:Importing WebPImagePlugin +DEBUG:PIL.Image:Importing WmfImagePlugin +DEBUG:PIL.Image:Importing XbmImagePlugin +DEBUG:PIL.Image:Importing XpmImagePlugin +DEBUG:PIL.Image:Importing XVThumbImagePlugin + 8%|▊ | 1/12 [01:14<13:34, 74.06s/it] 17%|█▋ | 2/12 [02:27<12:17, 73.74s/it] 25%|██▌ | 3/12 [03:40<10:59, 73.23s/it] 33%|███▎ | 4/12 [04:52<09:43, 72.94s/it] 42%|████▏ | 5/12 [06:05<08:29, 72.81s/it] 50%|█████ | 6/12 [07:17<07:16, 72.74s/it] 58%|█████▊ | 7/12 [08:30<06:03, 72.68s/it] 67%|██████▋ | 8/12 [09:42<04:50, 72.63s/it] 75%|███████▌ | 9/12 [10:55<03:38, 72.72s/it] 83%|████████▎ | 10/12 [12:09<02:25, 72.86s/it] 92%|█████████▏| 11/12 [13:21<01:12, 72.75s/it] 100%|██████████| 12/12 [14:33<00:00, 72.66s/it] 100%|██████████| 12/12 [14:33<00:00, 72.83s/it] +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 1: generating actions ... +>>> Step 1: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 2: generating actions ... +>>> Step 2: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 3: generating actions ... +>>> Step 3: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 4: generating actions ... +>>> Step 4: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 5: generating actions ... +>>> Step 5: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 6: generating actions ... +>>> Step 6: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 7: generating actions ... +>>> Step 7: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 8: generating actions ... +>>> Step 8: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 9: generating actions ... +>>> Step 9: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 10: generating actions ... +>>> Step 10: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 11: generating actions ... +>>> Step 11: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> + +real 16m6.056s +user 71m23.029s +sys 0m43.382s diff --git a/unitree_z1_stackbox/case4/output.log b/unitree_z1_stackbox/case4/output.log new file mode 100644 index 0000000..3210376 --- /dev/null +++ b/unitree_z1_stackbox/case4/output.log @@ -0,0 +1,130 @@ +2026-02-12 00:08:05.532356: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. +2026-02-12 00:08:05.582134: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered +2026-02-12 00:08:05.582180: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered +2026-02-12 00:08:05.583503: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered +2026-02-12 00:08:05.591049: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. +To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. +2026-02-12 00:08:06.523218: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT +Global seed set to 123 +INFO:mainlogger:LatentVisualDiffusion: Running in v-prediction mode +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +INFO:unifolm_wma.models.diffusion_head.conditional_unet1d:number of parameters: 5.010531e+08 +AE working on z of shape (1, 4, 32, 32) = 4096 dimensions. +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +INFO:root:Loaded ViT-H-14 model config. +INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k). +>>> model checkpoint loaded. +>>> Load pre-trained model ... +INFO:root:***** Configing Data ***** +>>> unitree_z1_stackbox: 1 data samples loaded. +>>> unitree_z1_stackbox: data stats loaded. +>>> unitree_z1_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox: data stats loaded. +>>> unitree_z1_dual_arm_stackbox: normalizer initiated. +>>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded. +>>> unitree_z1_dual_arm_stackbox_v2: data stats loaded. +>>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated. +>>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded. +>>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated. +>>> unitree_g1_pack_camera: 1 data samples loaded. +>>> unitree_g1_pack_camera: data stats loaded. +>>> unitree_g1_pack_camera: normalizer initiated. +>>> Dataset is successfully loaded ... +>>> Generate 16 frames under each generation ... +DEBUG:h5py._conv:Creating converter from 3 to 5 +DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13 +DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9 +DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096 + 0%| | 0/12 [00:00>> Step 0: generating actions ... +>>> Step 0: interacting with world model ... +DEBUG:PIL.Image:Importing BlpImagePlugin +DEBUG:PIL.Image:Importing BmpImagePlugin +DEBUG:PIL.Image:Importing BufrStubImagePlugin +DEBUG:PIL.Image:Importing CurImagePlugin +DEBUG:PIL.Image:Importing DcxImagePlugin +DEBUG:PIL.Image:Importing DdsImagePlugin +DEBUG:PIL.Image:Importing EpsImagePlugin +DEBUG:PIL.Image:Importing FitsImagePlugin +DEBUG:PIL.Image:Importing FitsStubImagePlugin +DEBUG:PIL.Image:Importing FliImagePlugin +DEBUG:PIL.Image:Importing FpxImagePlugin +DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing FtexImagePlugin +DEBUG:PIL.Image:Importing GbrImagePlugin +DEBUG:PIL.Image:Importing GifImagePlugin +DEBUG:PIL.Image:Importing GribStubImagePlugin +DEBUG:PIL.Image:Importing Hdf5StubImagePlugin +DEBUG:PIL.Image:Importing IcnsImagePlugin +DEBUG:PIL.Image:Importing IcoImagePlugin +DEBUG:PIL.Image:Importing ImImagePlugin +DEBUG:PIL.Image:Importing ImtImagePlugin +DEBUG:PIL.Image:Importing IptcImagePlugin +DEBUG:PIL.Image:Importing JpegImagePlugin +DEBUG:PIL.Image:Importing Jpeg2KImagePlugin +DEBUG:PIL.Image:Importing McIdasImagePlugin +DEBUG:PIL.Image:Importing MicImagePlugin +DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile' +DEBUG:PIL.Image:Importing MpegImagePlugin +DEBUG:PIL.Image:Importing MpoImagePlugin +DEBUG:PIL.Image:Importing MspImagePlugin +DEBUG:PIL.Image:Importing PalmImagePlugin +DEBUG:PIL.Image:Importing PcdImagePlugin +DEBUG:PIL.Image:Importing PcxImagePlugin +DEBUG:PIL.Image:Importing PdfImagePlugin +DEBUG:PIL.Image:Importing PixarImagePlugin +DEBUG:PIL.Image:Importing PngImagePlugin +DEBUG:PIL.Image:Importing PpmImagePlugin +DEBUG:PIL.Image:Importing PsdImagePlugin +DEBUG:PIL.Image:Importing QoiImagePlugin +DEBUG:PIL.Image:Importing SgiImagePlugin +DEBUG:PIL.Image:Importing SpiderImagePlugin +DEBUG:PIL.Image:Importing SunImagePlugin +DEBUG:PIL.Image:Importing TgaImagePlugin +DEBUG:PIL.Image:Importing TiffImagePlugin +DEBUG:PIL.Image:Importing WebPImagePlugin +DEBUG:PIL.Image:Importing WmfImagePlugin +DEBUG:PIL.Image:Importing XbmImagePlugin +DEBUG:PIL.Image:Importing XpmImagePlugin +DEBUG:PIL.Image:Importing XVThumbImagePlugin + 8%|▊ | 1/12 [01:13<13:30, 73.69s/it] 17%|█▋ | 2/12 [02:26<12:12, 73.23s/it] 25%|██▌ | 3/12 [03:40<11:02, 73.59s/it] 33%|███▎ | 4/12 [04:54<09:50, 73.76s/it] 42%|████▏ | 5/12 [06:07<08:34, 73.51s/it] 50%|█████ | 6/12 [07:20<07:19, 73.19s/it] 58%|█████▊ | 7/12 [08:32<06:04, 72.98s/it] 67%|██████▋ | 8/12 [09:45<04:51, 72.85s/it] 75%|███████▌ | 9/12 [10:57<03:38, 72.76s/it] 83%|████████▎ | 10/12 [12:10<02:25, 72.69s/it] 92%|█████████▏| 11/12 [13:23<01:12, 72.66s/it] 100%|██████████| 12/12 [14:35<00:00, 72.63s/it] 100%|██████████| 12/12 [14:35<00:00, 72.97s/it] +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 1: generating actions ... +>>> Step 1: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 2: generating actions ... +>>> Step 2: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 3: generating actions ... +>>> Step 3: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 4: generating actions ... +>>> Step 4: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 5: generating actions ... +>>> Step 5: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 6: generating actions ... +>>> Step 6: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 7: generating actions ... +>>> Step 7: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 8: generating actions ... +>>> Step 8: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 9: generating actions ... +>>> Step 9: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 10: generating actions ... +>>> Step 10: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> +>>> Step 11: generating actions ... +>>> Step 11: interacting with world model ... +>>>>>>>>>>>>>>>>>>>>>>>> + +real 16m7.783s +user 71m30.579s +sys 0m41.570s