MCG-NJU / TDN

[CVPR 2021] TDN: Temporal Difference Networks for Efficient Action Recognition
https://arxiv.org/abs/2012.10071
Apache License 2.0
368 stars 55 forks source link

about how to train #65

Closed sanwei111 closed 1 year ago

sanwei111 commented 1 year ago

hello,i want 2 train my own model through your pretrained model,how to put the video and the label?

yztongzhan commented 1 year ago
  1. Generate annotations needed for dataloader (" " in annotations) The annotation usually includes train.txt and val.txt. The format of *.txt file is like:
        dataset_root/video_1.mp4  label_1
        dataset_root/video_2.mp4  label_2
        dataset_root/video_3.mp4  label_3
        ...
        dataset_root/video_N.mp4  label_N
  2. Add the information to ops/dataset_configs.py.
  3. Modify this function and define the filename_categories = #num_of_class.