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

120
unitree_g1_pack_camera/case1/output.log Normal file
View File

@@ -0,0 +1,120 @@
2026-02-11 13:57:30.192579: 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 13:57:30.242090: 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 13:57:30.242134: 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 13:57:30.243443: 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 13:57:30.250963: 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 13:57:31.177911: 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%| | 0/11 [00:00<?, ?it/s]
9%|▉ | 1/11 [00:33<05:33, 33.38s/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
18%|█▊ | 2/11 [01:07<05:02, 33.64s/it]
27%|██▋ | 3/11 [01:41<04:31, 33.90s/it]
36%|███▋ | 4/11 [02:15<03:58, 34.05s/it]
45%|████▌ | 5/11 [02:49<03:24, 34.07s/it]
55%|█████▍ | 6/11 [03:23<02:50, 34.08s/it]
64%|██████▎ | 7/11 [03:58<02:16, 34.10s/it]
73%|███████▎ | 8/11 [04:32<01:42, 34.12s/it]
82%|████████▏ | 9/11 [05:06<01:08, 34.12s/it]
91%|█████████ | 10/11 [05:40<00:34, 34.11s/it]
100%|██████████| 11/11 [06:14<00:00, 34.10s/it]
100%|██████████| 11/11 [06:14<00:00, 34.04s/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 ...
>>>>>>>>>>>>>>>>>>>>>>>>
>>> Step 6: generating actions ...
>>> Step 6: interacting with world model ...
>>>>>>>>>>>>>>>>>>>>>>>>
>>> Step 7: generating actions ...
>>> Step 7: interacting with world model ...
>>>>>>>>>>>>>>>>>>>>>>>>

5
unitree_g1_pack_camera/case1/psnr_result.json Normal file
View File

@@ -0,0 +1,5 @@
{
"gt_video": "unitree_g1_pack_camera/case1/unitree_g1_pack_camera_case1.mp4",
"pred_video": "unitree_g1_pack_camera/case1/output/inference/0_full_fs6.mp4",
"psnr": 34.28787704598647
}

3
unitree_g1_pack_camera/case1/run_world_model_interaction.sh
View File

@@ -20,5 +20,6 @@ dataset="unitree_g1_pack_camera"
--n_iter 11 \
--timestep_spacing 'uniform_trailing' \
--guidance_rescale 0.7 \
--perframe_ae
--perframe_ae \
--fast_policy_no_decode
} 2>&1 | tee "${res_dir}/output.log"

120
unitree_g1_pack_camera/case2/output.log Normal file
View File

@@ -0,0 +1,120 @@
2026-02-11 14:04:18.542839: 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 14:04:18.593447: 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 14:04:18.593492: 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 14:04:18.594810: 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 14:04:18.602331: 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 14:04:19.529518: 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%| | 0/11 [00:00<?, ?it/s]
9%|▉ | 1/11 [00:34<05:41, 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
18%|█▊ | 2/11 [01:08<05:08, 34.26s/it]
27%|██▋ | 3/11 [01:42<04:33, 34.23s/it]
36%|███▋ | 4/11 [02:16<03:59, 34.23s/it]
45%|████▌ | 5/11 [02:50<03:25, 34.18s/it]
55%|█████▍ | 6/11 [03:25<02:50, 34.18s/it]
64%|██████▎ | 7/11 [03:59<02:16, 34.18s/it]
73%|███████▎ | 8/11 [04:33<01:42, 34.16s/it]
82%|████████▏ | 9/11 [05:07<01:08, 34.15s/it]
91%|█████████ | 10/11 [05:41<00:34, 34.16s/it]
100%|██████████| 11/11 [06:15<00:00, 34.13s/it]
100%|██████████| 11/11 [06:15<00:00, 34.17s/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 ...
>>>>>>>>>>>>>>>>>>>>>>>>
>>> Step 6: generating actions ...
>>> Step 6: interacting with world model ...
>>>>>>>>>>>>>>>>>>>>>>>>
>>> Step 7: generating actions ...
>>> Step 7: interacting with world model ...
>>>>>>>>>>>>>>>>>>>>>>>>

5
unitree_g1_pack_camera/case2/psnr_result.json Normal file
View File

@@ -0,0 +1,5 @@
{
"gt_video": "unitree_g1_pack_camera/case2/unitree_g1_pack_camera_case2.mp4",
"pred_video": "unitree_g1_pack_camera/case2/output/inference/50_full_fs6.mp4",
"psnr": 43.756296364111726
}

3
unitree_g1_pack_camera/case2/run_world_model_interaction.sh
View File

@@ -20,5 +20,6 @@ dataset="unitree_g1_pack_camera"
--n_iter 11 \
--timestep_spacing 'uniform_trailing' \
--guidance_rescale 0.7 \
--perframe_ae
--perframe_ae \
--fast_policy_no_decode
} 2>&1 | tee "${res_dir}/output.log"

120
unitree_g1_pack_camera/case3/output.log Normal file
View File

@@ -0,0 +1,120 @@
2026-02-11 14:11:08.388455: 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 14:11:08.437992: 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 14:11:08.438037: 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 14:11:08.439358: 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 14:11:08.446903: 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 14:11:09.369764: 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%| | 0/11 [00:00<?, ?it/s]
9%|▉ | 1/11 [00:34<05:40, 34.10s/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
18%|█▊ | 2/11 [01:08<05:08, 34.25s/it]
27%|██▋ | 3/11 [01:42<04:33, 34.25s/it]
36%|███▋ | 4/11 [02:16<03:59, 34.22s/it]
45%|████▌ | 5/11 [02:51<03:25, 34.20s/it]
55%|█████▍ | 6/11 [03:25<02:50, 34.16s/it]
64%|██████▎ | 7/11 [03:59<02:16, 34.14s/it]
73%|███████▎ | 8/11 [04:33<01:42, 34.13s/it]
82%|████████▏ | 9/11 [05:07<01:08, 34.11s/it]
91%|█████████ | 10/11 [05:41<00:34, 34.09s/it]
100%|██████████| 11/11 [06:15<00:00, 34.07s/it]
100%|██████████| 11/11 [06:15<00:00, 34.13s/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 ...
>>>>>>>>>>>>>>>>>>>>>>>>
>>> Step 6: generating actions ...
>>> Step 6: interacting with world model ...
>>>>>>>>>>>>>>>>>>>>>>>>
>>> Step 7: generating actions ...
>>> Step 7: interacting with world model ...
>>>>>>>>>>>>>>>>>>>>>>>>

5
unitree_g1_pack_camera/case3/psnr_result.json Normal file
View File

@@ -0,0 +1,5 @@
{
"gt_video": "unitree_g1_pack_camera/case3/unitree_g1_pack_camera_case3.mp4",
"pred_video": "unitree_g1_pack_camera/case3/output/inference/100_full_fs6.mp4",
"psnr": 37.65161306938167
}

3
unitree_g1_pack_camera/case3/run_world_model_interaction.sh
View File

@@ -20,5 +20,6 @@ dataset="unitree_g1_pack_camera"
--n_iter 11 \
--timestep_spacing 'uniform_trailing' \
--guidance_rescale 0.7 \
--perframe_ae
--perframe_ae \
--fast_policy_no_decode
} 2>&1 | tee "${res_dir}/output.log"

120
unitree_g1_pack_camera/case4/output.log Normal file
View File

@@ -0,0 +1,120 @@
2026-02-11 14:17:57.092085: 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 14:17:57.141607: 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 14:17:57.141661: 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 14:17:57.142984: 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 14:17:57.150517: 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 14:17:58.074812: 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%| | 0/11 [00:00<?, ?it/s]
9%|▉ | 1/11 [00:34<05:41, 34.20s/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
18%|█▊ | 2/11 [01:08<05:08, 34.29s/it]
27%|██▋ | 3/11 [01:42<04:34, 34.25s/it]
36%|███▋ | 4/11 [02:16<03:59, 34.23s/it]
45%|████▌ | 5/11 [02:51<03:25, 34.19s/it]
55%|█████▍ | 6/11 [03:25<02:50, 34.17s/it]
64%|██████▎ | 7/11 [03:59<02:16, 34.19s/it]
73%|███████▎ | 8/11 [04:33<01:42, 34.18s/it]
82%|████████▏ | 9/11 [05:07<01:08, 34.16s/it]
91%|█████████ | 10/11 [05:41<00:34, 34.13s/it]
100%|██████████| 11/11 [06:15<00:00, 34.11s/it]
100%|██████████| 11/11 [06:15<00:00, 34.17s/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 ...
>>>>>>>>>>>>>>>>>>>>>>>>
>>> Step 6: generating actions ...
>>> Step 6: interacting with world model ...
>>>>>>>>>>>>>>>>>>>>>>>>
>>> Step 7: generating actions ...
>>> Step 7: interacting with world model ...
>>>>>>>>>>>>>>>>>>>>>>>>

5
unitree_g1_pack_camera/case4/psnr_result.json Normal file
View File

@@ -0,0 +1,5 @@
{
"gt_video": "unitree_g1_pack_camera/case4/unitree_g1_pack_camera_case4.mp4",
"pred_video": "unitree_g1_pack_camera/case4/output/inference/200_full_fs6.mp4",
"psnr": 33.205596596179475
}

3
unitree_g1_pack_camera/case4/run_world_model_interaction.sh
View File

@@ -20,5 +20,6 @@ dataset="unitree_g1_pack_camera"
--n_iter 11 \
--timestep_spacing 'uniform_trailing' \
--guidance_rescale 0.7 \
--perframe_ae
--perframe_ae \
--fast_policy_no_decode
} 2>&1 | tee "${res_dir}/output.log"