Implementation of FOMM with AWP and MRAA with AWP.
- Yi Zhang|@zylye123
- Xinhua Xu|@sysu19351158
- Youjun Zhao|@zhaoyjoy
- Yuhang Wen|@Necolizer
- Zixuan Tang|@sysu19351118
- [2022/02/18] Upload code.
- [2023/05/02] + Case Visualizations.
CASE | Driving | FOMM | FOMM w/ EWP | FOMM w/ AWP | MRAA | MRAA w/ AWP |
---|---|---|---|---|---|---|
1 | ![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
2 | ![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
3 | ![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
4 | ![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
5 | ![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
- To facilitate micro-expression observations and reduce the storage space of this repository, all Gifs have been slowed down and compressed.
- Case 1-3: Positive. Case 4: Negative. Case 5: Surprise.
-
Operations of FOMM_with_AWP and MRAA_with_AWP are the same.
-
Prepare your dataset. Recommend CASME2, SAMM, SMIC-HS
Divide into
your_dataset/train
andyour_dataset/test
Create or modify
yaml
format fileyour_dataset_train.yaml
in./config
-
Train
python run.py --config config/your_dataset_train.yaml
Log, parameters and checkpoints would be saved in
./log
-
Test
Create or modify
csv
format fileyour_dataset_test.csv
in./data
python run.py --config config/my_dataset_test.yaml --mode animate --checkpoint path/to/checkpoint
Generated videos would be saved in
path/to/checkpoint/animation