olivame/unifolm-world-model-action
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

主干部分fp16,最敏感psnr=25.21,可以考虑对主干部分太敏感的部分回退fp32

Browse Source
This commit is contained in:
qhy
2026-02-11 16:23:21 +08:00
parent 9a08e27a19
commit 352a79035f
64 changed files with 4769 additions and 60 deletions
Download Patch File Download Diff File Expand all files Collapse all files

42
unitree_z1_dual_arm_cleanup_pencils/case1/output.log
View File

@@ -1,24 +1,13 @@
2026-02-10 15:38:28.973314: 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`.
2026-02-10 15:38:29.023024: 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
2026-02-10 15:38:29.023070: 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
2026-02-10 15:38:29.024393: 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
2026-02-10 15:38:29.031901: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
2026-02-11 14:24:46.595601: 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 14:24:46.645554: 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 14:24:46.645598: 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 14:24:46.646935: 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 14:24:46.654595: 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.
2026-02-10 15:38:29.955454: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
2026-02-11 14:24:47.580547: 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.
DEBUG:urllib3.connectionpool:Starting new HTTPS connection (1): hf-mirror.com:443
DEBUG:urllib3.connectionpool:https://hf-mirror.com:443 "HEAD /laion/CLIP-ViT-H-14-laion2B-s32B-b79K/resolve/main/open_clip_pytorch_model.bin HTTP/1.1" 302 0
INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k).
INFO:root:Loaded ViT-H-14 model config.
DEBUG:urllib3.connectionpool:https://hf-mirror.com:443 "HEAD /laion/CLIP-ViT-H-14-laion2B-s32B-b79K/resolve/main/open_clip_pytorch_model.bin HTTP/1.1" 302 0
INFO:root:Loading pretrained ViT-H-14 weights (laion2b_s32b_b79k).
>>> model checkpoint loaded.
>>> Load pre-trained model ...
>>> Loading prepared model from ckpts/unifolm_wma_dual.ckpt.prepared.pt ...
>>> Prepared model loaded.
INFO:root:***** Configing Data *****
>>> unitree_z1_stackbox: 1 data samples loaded.
>>> unitree_z1_stackbox: data stats loaded.
@@ -36,13 +25,16 @@ INFO:root:***** Configing Data *****
>>> unitree_g1_pack_camera: data stats loaded.
>>> unitree_g1_pack_camera: normalizer initiated.
>>> Dataset is successfully loaded ...
✓ KV fused: 66 attention layers
>>> 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<?, ?it/s]
12%|█▎ | 1/8 [00:34<03:58, 34.12s/it]>>> Step 0: generating actions ...
>>> Step 0: interacting with world model ...
>>>>>>>>>>>>>>>>>>>>>>>>
>>> Step 1: generating actions ...
DEBUG:PIL.Image:Importing BlpImagePlugin
@@ -92,9 +84,7 @@ DEBUG:PIL.Image:Importing WmfImagePlugin
DEBUG:PIL.Image:Importing WebPImagePlugin
DEBUG:PIL.Image:Importing WmfImagePlugin
DEBUG:PIL.Image:Importing XbmImagePlugin
DEBUG:PIL.Image:Importing XVThumbImagePlugin
12%|█▎ | 1/8 [01:14<08:41, 74.51s/it]
DEBUG:PIL.Image:Importing XpmImagePlugin
DEBUG:PIL.Image:Importing XVThumbImagePlugin
25%|██▌ | 2/8 [01:08<03:24, 34.15s/it]
@@ -116,6 +106,6 @@ DEBUG:PIL.Image:Importing XVThumbImagePlugin
>>> Step 4: generating actions ...
>>> Step 4: interacting with world model ...
>>>>>>>>>>>>>>>>>>>>>>>>
>>> Step 5: generating actions ...
>>> Step 5: interacting with world model ...
>>>>>>>>>>>>>>>>>>>>>>>>
>>> Step 5: generating actions ...
>>> Step 5: interacting with world model ...
>>>>>>>>>>>>>>>>>>>>>>>>

2
unitree_z1_dual_arm_cleanup_pencils/case1/psnr_result.json
View File

@@ -1,5 +1,5 @@
{
"gt_video": "unitree_z1_dual_arm_cleanup_pencils/case1/unitree_z1_dual_arm_cleanup_pencils_case1.mp4",
"pred_video": "unitree_z1_dual_arm_cleanup_pencils/case1/output/inference/0_full_fs4.mp4",
"psnr": 47.911564449209735
"psnr": 48.52515070316814
}

3
unitree_z1_dual_arm_cleanup_pencils/case1/run_world_model_interaction.sh
View File

@@ -20,5 +20,6 @@ dataset="unitree_z1_dual_arm_cleanup_pencils"
--n_iter 8 \
--timestep_spacing 'uniform_trailing' \
--guidance_rescale 0.7 \
--perframe_ae
--perframe_ae \
--fast_policy_no_decode
} 2>&1 | tee "${res_dir}/output.log"

111
unitree_z1_dual_arm_cleanup_pencils/case2/output.log Normal file
View File

@@ -0,0 +1,111 @@
2026-02-11 14:29:51.911195: 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 14:29:51.961101: 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 14:29:51.961156: 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 14:29:51.962467: 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 14:29:51.969980: 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 14:29:52.899745: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
Global seed set to 123
>>> Loading prepared model from ckpts/unifolm_wma_dual.ckpt.prepared.pt ...
>>> Prepared model loaded.
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 ...
✓ KV fused: 66 attention layers
>>> 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<?, ?it/s]
12%|█▎ | 1/8 [00:34<03:59, 34.22s/it]>>> Step 0: generating actions ...
>>> Step 0: interacting with world model ...
>>>>>>>>>>>>>>>>>>>>>>>>
>>> Step 1: generating actions ...
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
25%|██▌ | 2/8 [01:08<03:25, 34.24s/it]
38%|███▊ | 3/8 [01:42<02:51, 34.21s/it]
50%|█████ | 4/8 [02:16<02:16, 34.18s/it]
62%|██████▎ | 5/8 [02:50<01:42, 34.15s/it]
75%|███████▌ | 6/8 [03:24<01:08, 34.11s/it]
88%|████████▊ | 7/8 [03:58<00:34, 34.10s/it]
100%|██████████| 8/8 [04:32<00:00, 34.07s/it]
100%|██████████| 8/8 [04:32<00:00, 34.12s/it]
>>> 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 ...
>>>>>>>>>>>>>>>>>>>>>>>>

5
unitree_z1_dual_arm_cleanup_pencils/case2/psnr_result.json Normal file
View File

@@ -0,0 +1,5 @@
{
"gt_video": "unitree_z1_dual_arm_cleanup_pencils/case2/unitree_z1_dual_arm_cleanup_pencils_case2.mp4",
"pred_video": "unitree_z1_dual_arm_cleanup_pencils/case2/output/inference/50_full_fs4.mp4",
"psnr": 47.91455867741451
}

3
unitree_z1_dual_arm_cleanup_pencils/case2/run_world_model_interaction.sh
View File

@@ -20,5 +20,6 @@ dataset="unitree_z1_dual_arm_cleanup_pencils"
--n_iter 8 \
--timestep_spacing 'uniform_trailing' \
--guidance_rescale 0.7 \
--perframe_ae
--perframe_ae \
--fast_policy_no_decode
} 2>&1 | tee "${res_dir}/output.log"

111
unitree_z1_dual_arm_cleanup_pencils/case3/output.log Normal file
View File

@@ -0,0 +1,111 @@
2026-02-11 14:34:58.016000: 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 14:34:58.066369: 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 14:34:58.066418: 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 14:34:58.067763: 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 14:34:58.075447: 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 14:34:59.008184: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
Global seed set to 123
>>> Loading prepared model from ckpts/unifolm_wma_dual.ckpt.prepared.pt ...
>>> Prepared model loaded.
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 ...
✓ KV fused: 66 attention layers
>>> 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<?, ?it/s]
12%|█▎ | 1/8 [00:34<03:58, 34.14s/it]>>> Step 0: generating actions ...
>>> Step 0: interacting with world model ...
>>>>>>>>>>>>>>>>>>>>>>>>
>>> Step 1: generating actions ...
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
25%|██▌ | 2/8 [01:08<03:25, 34.21s/it]
38%|███▊ | 3/8 [01:42<02:50, 34.18s/it]
50%|█████ | 4/8 [02:16<02:16, 34.16s/it]
62%|██████▎ | 5/8 [02:50<01:42, 34.11s/it]
75%|███████▌ | 6/8 [03:24<01:08, 34.08s/it]
88%|████████▊ | 7/8 [03:58<00:34, 34.09s/it]
100%|██████████| 8/8 [04:32<00:00, 34.08s/it]
100%|██████████| 8/8 [04:32<00:00, 34.11s/it]
>>> 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 ...
>>>>>>>>>>>>>>>>>>>>>>>>

5
unitree_z1_dual_arm_cleanup_pencils/case3/psnr_result.json Normal file
View File

@@ -0,0 +1,5 @@
{
"gt_video": "unitree_z1_dual_arm_cleanup_pencils/case3/unitree_z1_dual_arm_cleanup_pencils_case3.mp4",
"pred_video": "unitree_z1_dual_arm_cleanup_pencils/case3/output/inference/100_full_fs4.mp4",
"psnr": 41.260758562627046
}

3
unitree_z1_dual_arm_cleanup_pencils/case3/run_world_model_interaction.sh
View File

@@ -20,5 +20,6 @@ dataset="unitree_z1_dual_arm_cleanup_pencils"
--n_iter 8 \
--timestep_spacing 'uniform_trailing' \
--guidance_rescale 0.7 \
--perframe_ae
--perframe_ae \
--fast_policy_no_decode
} 2>&1 | tee "${res_dir}/output.log"

111
unitree_z1_dual_arm_cleanup_pencils/case4/output.log Normal file
View File

@@ -0,0 +1,111 @@
2026-02-11 14:40:06.781951: 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 14:40:06.832600: 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 14:40:06.832649: 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 14:40:06.833982: 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 14:40:06.841504: 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 14:40:07.772162: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
Global seed set to 123
>>> Loading prepared model from ckpts/unifolm_wma_dual.ckpt.prepared.pt ...
>>> Prepared model loaded.
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 ...
✓ KV fused: 66 attention layers
>>> 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<?, ?it/s]
12%|█▎ | 1/8 [00:34<03:59, 34.18s/it]>>> Step 0: generating actions ...
>>> Step 0: interacting with world model ...
>>>>>>>>>>>>>>>>>>>>>>>>
>>> Step 1: generating actions ...
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
25%|██▌ | 2/8 [01:08<03:25, 34.26s/it]
38%|███▊ | 3/8 [01:42<02:51, 34.23s/it]
50%|█████ | 4/8 [02:16<02:16, 34.20s/it]
62%|██████▎ | 5/8 [02:50<01:42, 34.16s/it]
75%|███████▌ | 6/8 [03:25<01:08, 34.14s/it]
88%|████████▊ | 7/8 [03:59<00:34, 34.12s/it]
100%|██████████| 8/8 [04:33<00:00, 34.12s/it]
100%|██████████| 8/8 [04:33<00:00, 34.15s/it]
>>> 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 ...
>>>>>>>>>>>>>>>>>>>>>>>>

5
unitree_z1_dual_arm_cleanup_pencils/case4/psnr_result.json Normal file
View File

@@ -0,0 +1,5 @@
{
"gt_video": "unitree_z1_dual_arm_cleanup_pencils/case4/unitree_z1_dual_arm_cleanup_pencils_case4.mp4",
"pred_video": "unitree_z1_dual_arm_cleanup_pencils/case4/output/inference/200_full_fs4.mp4",
"psnr": 47.046499351779815
}

3
unitree_z1_dual_arm_cleanup_pencils/case4/run_world_model_interaction.sh
View File

@@ -20,5 +20,6 @@ dataset="unitree_z1_dual_arm_cleanup_pencils"
--n_iter 8 \
--timestep_spacing 'uniform_trailing' \
--guidance_rescale 0.7 \
--perframe_ae
--perframe_ae \
--fast_policy_no_decode
} 2>&1 | tee "${res_dir}/output.log"