Can not render the `Inference Demo`

[ykk648]

Tried two pc with different cuda&python versions, build the env from zero, build pytorch3d(0.6.1) from src, when I run Inference Demo, the output video is same as the input video.

After added '--draw_bbox', the boxed detected can see.

I tried different render_choice , same results.

Trying to debug but may not spend a lot time on it.

[ykk648]

the frame rate is different, input video is 12 fps and output is 30 fps, may caused by ffmpeg, not connected with render I assume

[ykk648]

inference log:

Details

load checkpoint from http path: https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_fpn_1x_coco/faster_rcnn_r50_fpn_1x_coco_20200130-047c8118.pth WARNING: You are using a SMPL model, with only 10 shape coefficients. WARNING: You are using a SMPL model, with only 10 shape coefficients. load checkpoint from local path: data/checkpoints/resnet50_hmr_pw3d.pth [ ] 0/40, elapsed: 0s, ETA: [ ] 1/40, 1.8 task/s, elapsed: 1s, ETA: 21s [> ] 2/40, 3.2 task/s, elapsed: 1s, ETA: 12s [>> ] 3/40, 4.2 task/s, elapsed: 1s, ETA: 9s [>>> ] 4/40, 5.1 task/s, elapsed: 1s, ETA: 7s [>>>> ] 5/40, 5.8 task/s, elapsed: 1s, ETA: 6s [>>>>> ] 6/40, 6.5 task/s, elapsed: 1s, ETA: 5s [>>>>> ] 7/40, 7.0 task/s, elapsed: 1s, ETA: 5s [>>>>>> ] 8/40, 7.5 task/s, elapsed: 1s, ETA: 4s [>>>>>>> ] 9/40, 8.0 task/s, elapsed: 1s, ETA: 4s [>>>>>>>> ] 10/40, 8.3 task/s, elapsed: 1s, ETA: 4s [>>>>>>>>> ] 11/40, 8.7 task/s, elapsed: 1s, ETA: 3s [>>>>>>>>> ] 12/40, 9.0 task/s, elapsed: 1s, ETA: 3s [>>>>>>>>>> ] 13/40, 9.3 task/s, elapsed: 1s, ETA: 3s [>>>>>>>>>>> ] 14/40, 9.5 task/s, elapsed: 1s, ETA: 3s [>>>>>>>>>>>> ] 15/40, 9.8 task/s, elapsed: 2s, ETA: 3s [>>>>>>>>>>>> ] 16/40, 10.0 task/s, elapsed: 2s, ETA: 2s [>>>>>>>>>>>>> ] 17/40, 10.2 task/s, elapsed: 2s, ETA: 2s [>>>>>>>>>>>>>> ] 18/40, 10.3 task/s, elapsed: 2s, ETA: 2s [>>>>>>>>>>>>>>> ] 19/40, 10.5 task/s, elapsed: 2s, ETA: 2s [>>>>>>>>>>>>>>>> ] 20/40, 10.7 task/s, elapsed: 2s, ETA: 2s [>>>>>>>>>>>>>>>> ] 21/40, 10.8 task/s, elapsed: 2s, ETA: 2s [>>>>>>>>>>>>>>>>> ] 22/40, 10.9 task/s, elapsed: 2s, ETA: 2s [>>>>>>>>>>>>>>>>>> ] 23/40, 11.1 task/s, elapsed: 2s, ETA: 2s [>>>>>>>>>>>>>>>>>>> ] 24/40, 11.2 task/s, elapsed: 2s, ETA: 1s [>>>>>>>>>>>>>>>>>>>> ] 25/40, 11.3 task/s, elapsed: 2s, ETA: 1s [>>>>>>>>>>>>>>>>>>>> ] 26/40, 11.4 task/s, elapsed: 2s, ETA: 1s [>>>>>>>>>>>>>>>>>>>>> ] 27/40, 11.5 task/s, elapsed: 2s, ETA: 1s [>>>>>>>>>>>>>>>>>>>>>> ] 28/40, 11.6 task/s, elapsed: 2s, ETA: 1s [>>>>>>>>>>>>>>>>>>>>>>> ] 29/40, 11.7 task/s, elapsed: 2s, ETA: 1s [>>>>>>>>>>>>>>>>>>>>>>>> ] 30/40, 11.8 task/s, elapsed: 3s, ETA: 1s [>>>>>>>>>>>>>>>>>>>>>>>> ] 31/40, 11.8 task/s, elapsed: 3s, ETA: 1s [>>>>>>>>>>>>>>>>>>>>>>>>> ] 32/40, 11.9 task/s, elapsed: 3s, ETA: 1s [>>>>>>>>>>>>>>>>>>>>>>>>>> ] 33/40, 12.0 task/s, elapsed: 3s, ETA: 1s [>>>>>>>>>>>>>>>>>>>>>>>>>>> ] 34/40, 12.0 task/s, elapsed: 3s, ETA: 0s [>>>>>>>>>>>>>>>>>>>>>>>>>>>> ] 35/40, 12.1 task/s, elapsed: 3s, ETA: 0s [>>>>>>>>>>>>>>>>>>>>>>>>>>>> ] 36/40, 12.2 task/s, elapsed: 3s, ETA: 0s [>>>>>>>>>>>>>>>>>>>>>>>>>>>>> ] 37/40, 12.2 task/s, elapsed: 3s, ETA: 0s [>>>>>>>>>>>>>>>>>>>>>>>>>>>>>> ] 38/40, 12.3 task/s, elapsed: 3s, ETA: 0s [>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>> ] 39/40, 12.3 task/s, elapsed: 3s, ETA: 0s [>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>] 40/40, 12.4 task/s, elapsed: 3s, ETA: 0s WARNING: You are using a SMPL model, with only 10 shape coefficients. Overwriting vis_results/single_person_demo.mp4. make dir vis_results/single_person_demo.mp4_output_temp Make dir vis_results/single_person_demo.mp4_output_temp Overwriting vis_results/single_person_demo.mp4. Running "ffmpeg -y -threads 4 -start_number 0 -r 30 -i vis_results/single_person_demo.mp4_output_temp/%06d.png -frames:v 40 -profile:v baseline -level 3.0 -c:v libx264 -pix_fmt yuv420p -an -v error -loglevel error vis_results/single_person_demo.mp4"

and some warning:

Details

/home/user/miniconda3/envs/open-mmlab/lib/python3.8/site-packages/smplx/body_models.py:137: DeprecationWarning: Please use `csc_matrix` from the `scipy.sparse` namespace, the `scipy.sparse.csc` namespace is deprecated. data_struct = Struct(**pickle.load(smpl_file, /home/user/miniconda3/envs/open-mmlab/lib/python3.8/site-packages/chumpy/ch.py:20: DeprecationWarning: Please use `LinearOperator` from the `scipy.sparse.linalg` namespace, the `scipy.sparse.linalg.interface` namespace is deprecated. from scipy.sparse.linalg.interface import LinearOperator /home/user/miniconda3/envs/open-mmlab/lib/python3.8/site-packages/chumpy/ch.py:1203: DeprecationWarning: inspect.getargspec() is deprecated since Python 3.0, use inspect.signature() or inspect.getfullargspec() want_out = 'out' in inspect.getargspec(func).args /home/user/miniconda3/envs/open-mmlab/lib/python3.8/site-packages/chumpy/__init__.py:11: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here. Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations from numpy import bool, int, float, complex, object, unicode, str, nan, inf /home/user/miniconda3/envs/open-mmlab/lib/python3.8/site-packages/chumpy/__init__.py:11: DeprecationWarning: `np.int` is a deprecated alias for the builtin `int`. To silence this warning, use `int` by itself. Doing this will not modify any behavior and is safe. When replacing `np.int`, you may wish to use e.g. `np.int64` or `np.int32` to specify the precision. If you wish to review your current use, check the release note link for additional information. Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations from numpy import bool, int, float, complex, object, unicode, str, nan, inf /home/user/miniconda3/envs/open-mmlab/lib/python3.8/site-packages/chumpy/__init__.py:11: DeprecationWarning: `np.float` is a deprecated alias for the builtin `float`. To silence this warning, use `float` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.float64` here. Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations from numpy import bool, int, float, complex, object, unicode, str, nan, inf /home/user/miniconda3/envs/open-mmlab/lib/python3.8/site-packages/chumpy/__init__.py:11: DeprecationWarning: `np.complex` is a deprecated alias for the builtin `complex`. To silence this warning, use `complex` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.complex128` here. Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations from numpy import bool, int, float, complex, object, unicode, str, nan, inf /home/user/miniconda3/envs/open-mmlab/lib/python3.8/site-packages/chumpy/__init__.py:11: DeprecationWarning: `np.object` is a deprecated alias for the builtin `object`. To silence this warning, use `object` by itself. Doing this will not modify any behavior and is safe. Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations from numpy import bool, int, float, complex, object, unicode, str, nan, inf /home/user/miniconda3/envs/open-mmlab/lib/python3.8/site-packages/chumpy/__init__.py:11: DeprecationWarning: `np.unicode` is a deprecated alias for `np.compat.unicode`. To silence this warning, use `np.compat.unicode` by itself. In the likely event your code does not need to work on Python 2 you can use the builtin `str` for which `np.compat.unicode` is itself an alias. Doing this will not modify any behaviour and is safe. If you specifically wanted the numpy scalar type, use `np.str_` here. Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations from numpy import bool, int, float, complex, object, unicode, str, nan, inf /home/user/miniconda3/envs/open-mmlab/lib/python3.8/site-packages/chumpy/__init__.py:11: DeprecationWarning: `np.str` is a deprecated alias for the builtin `str`. To silence this warning, use `str` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.str_` here. Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations from numpy import bool, int, float, complex, object, unicode, str, nan, inf 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 4/4 [00:10<00:00, 2.72s/it]

[ttxskk]

Hi @ykk648, please try PR #134.

[ykk648]

it works, thx