search

jfzhang95 / pytorch-video-recognition

PyTorch implemented C3D, R3D, R2Plus1D models for video activity recognition.
MIT License
1.16k stars 250 forks source link

about mypath.py #4

Closed JiaHongTai closed 5 years ago

JiaHongTai commented 5 years ago

I don't know the directory tree about the root_dir and output_dir,when i run train.py,just show not found files.please display the directory tree.thanks.

jfzhang95 commented 5 years ago

root_dir is the original dataset, it contains videos of different categories, output_dir is preprocessed dataset, it contains extracted frames of different videos from different categories. For more details, you can look at dataset,py.

I am very busy now. I will add directory tree at this weekend.

JiaHongTai commented 5 years ago

ok,thanks