Likert Scoring with Grade Decoupling for Long-term Action Assessment
This is the code for CVPR2022 paper "Likert Scoring with Grade Decoupling for Long-term Action Assessment".
Environments
- RTX2080Ti
- CUDA: 10.2
- Python: 3.9.7
- PyTorch: 1.10.1+cu102
Features
The features and label files of Rhythmic Gymnastics dataset can be download here.
Running
Please fill in or select the args enclosed by {} first.
- Training
CUDA_VISIBLE_DEVICES={device ID} python main.py --video-path {path of video features} --train-label-path {path of label file of training set} --test-label-path {path of label file of test set} --model-name {the name used to save model and log} --action-type {Ball/Clubs/Hoop/Ribbon} --lr 1e-2 --epoch {250/400/500/150} --n_decoder 2 --n_query 4 --alpha 1.0 --margin 1.0 --lr-decay cos --decay-rate 0.01 --dropout 0.3
- Testing
CUDA_VISIBLE_DEVICES={device ID} python main.py --video-path {path of video features} --train-label-path {path of label file of training set} --test-label-path {path of label file of test set} --action-type {Ball/Clubs/Hoop/Ribbon} --n_decoder 2 --n_query 4 --dropout 0.3 --test --ckpt {the name of the used checkpoint}
544 Dec 20, 2022
225 Dec 25, 2022
176 Nov 28, 2022
2 Dec 16, 2021
147 Dec 04, 2022
1 Jan 13, 2022
815 Dec 29, 2022
15 Nov 09, 2022
167 Nov 20, 2022
147 Dec 20, 2022
428 Nov 22, 2022
9 Jul 27, 2022
18 Jun 02, 2022
13 Aug 27, 2022
13 Dec 17, 2022
344 Dec 23, 2022
13 Dec 29, 2022
123 Dec 25, 2022
36 Dec 15, 2022
1 Jun 14, 2022