[Bug] Use mmaction2 - main/configs/skeleton/posec3d/rgbpose_conv3d/rgbpose_conv3d py error for the demo
ya-92626 opened this issue · comments
Branch
main branch (1.x version, such as v1.0.0
, or dev-1.x
branch)
Prerequisite
- I have searched Issues and Discussions but cannot get the expected help.
- I have read the documentation but cannot get the expected help.
- The bug has not been fixed in the latest version.
Environment
Python: 3.9.13
GPU 0: NVIDIA GeForce GTX 1080 Ti
PyTorch: 1.12.1
Describe the bug
Traceback (most recent call last):
File "F:\shiyan\mmaction2-main\demo\demo_skeleton.py", line 169, in
main()
File "F:\shiyan\mmaction2-main\demo\demo_skeleton.py", line 157, in main
result = inference_skeleton(model, pose_results, (h, w))
File "F:\shiyan\mmaction2-main\mmaction\apis\inference.py", line 168, in inference_skeleton
return inference_recognizer(model, fake_anno, test_pipeline)
File "F:\shiyan\mmaction2-main\mmaction\apis\inference.py", line 105, in inference_recognizer
data = test_pipeline(data)
File "C:\Users\YA\anaconda3\envs\pytorch\lib\site-packages\mmengine\dataset\base_dataset.py", line 58, in call
data = t(data)
File "C:\Users\YA\anaconda3\envs\pytorch\lib\site-packages\mmcv\transforms\base.py", line 12, in call
return self.transform(results)
File "F:\shiyan\mmaction2-main\mmaction\datasets\transforms\pose_transforms.py", line 1342, in transform
results['filename'] = results['frame_dir'] + '.mp4'
KeyError: 'frame_dir'
Reproduces the problem - code sample
No response
Reproduces the problem - command or script
No response
Reproduces the problem - error message
No response
Additional information
No response