This project is about action recognition. I begin this project from Feb. 2019, aiming to improve the performance of TSN. The experiment and paper are still in process. If you have any further questions, plz contact my. My emial address is 116010065@link.cuhk.edu.cn.
To train a new model, use the main.py
script.
The command to reproduce the original TSN experiments of RGB modality on UCF101 can be
python main.py ucf101 RGB <ucf101_rgb_train_list> <ucf101_rgb_val_list> \
--arch BNInception --num_segments 3 \
--gd 20 --lr 0.001 --lr_steps 30 60 --epochs 80 \
-b 128 -j 8 --dropout 0.8 \
--snapshot_pref ucf101_bninception_
For flow models:
python main.py ucf101 Flow <ucf101_flow_train_list> <ucf101_flow_val_list> \
--arch BNInception --num_segments 3 \
--gd 20 --lr 0.001 --lr_steps 190 300 --epochs 340 \
-b 128 -j 8 --dropout 0.7 \
--snapshot_pref ucf101_bninception_ --flow_pref flow_
For RGB-diff models:
python main.py ucf101 RGBDiff <ucf101_rgb_train_list> <ucf101_rgb_val_list> \
--arch BNInception --num_segments 7 \
--gd 40 --lr 0.001 --lr_steps 80 160 --epochs 180 \
-b 128 -j 8 --dropout 0.8 \
--snapshot_pref ucf101_bninception_
After training, there will checkpoints saved by pytorch, for example ucf101_bninception_rgb_checkpoint.pth
.
Use the following command to test its performance in the standard TSN testing protocol:
python test_models.py ucf101 RGB <ucf101_rgb_val_list> ucf101_bninception_rgb_checkpoint.pth \
--arch BNInception --save_scores <score_file_name>
Or for flow models:
python test_models.py ucf101 Flow <ucf101_rgb_val_list> ucf101_bninception_flow_checkpoint.pth \
--arch BNInception --save_scores <score_file_name> --flow_pref flow_