search

genbing99 / SoftNet-SpotME

Shallow Optical Flow Three-Stream CNN For Macro and Micro-Expression Spotting From Long Videos
45 stars 20 forks source link

Training data set #7

Closed YUZHIWANG-bug closed 2 years ago

YUZHIWANG-bug commented 2 years ago

Can I only use cas (me) ^ 2 for training? If so, can you provide a pre-trained model？Thank you very much!

genbing99 commented 2 years ago

Hi, the pre-trained models have been provided in the folder SOFTNet_Weights. If you wish to continue the training, you can replace line 222 in training.py: model.set_weights(weight_reset) #Reset weights to ensure the model does not have info about current subject with: model.load_weights(path) Then, run the program by setting the parameters: python main.py --dataset_name CASME_sq --train True

YUZHIWANG-bug commented 2 years ago

Hi, the pre-trained models have been provided in the folder SOFTNet_Weights. If you wish to continue the training, you can replace line 222 in training.py: model.set_weights(weight_reset) #Reset weights to ensure the model does not have info about current subject with: model.load_weights(path) Then, run the program by setting the parameters: python main.py --dataset_name CASME_sq --train True

Thank you very much for your reply. I will try to use it. Thank you very much!