keyframes-CNN-RNN(action recognition)
Environment:
python>=3.7
pytorch>=1.2
Datasets:
Following the format of UCF101 action recognition.
Run steps:
- Modify the "dict_data" of readpkl.py to your own category to generate your own label.pkl for training.
- Run train.py, remember to modify the data set address.
- During operation, all loss npy files will be saved for visualization, and all models will be saved under weights.
- Run train.py, remember to modify the test data set address and the name of your trained model.