A CNN based pytorch implementation on facial expression recognition (FER2013 and CK+), achieving 73.112% (state-of-the-art) in FER2013 and 94.64% in CK+ dataset
Hi, I want to know why don't you split the training set to training and validation set. It is normal to do that, but I don't see that in your code. Also, did the FER2013 winner used the cross-validation technique? Thanks.
Hi, I want to know why don't you split the training set to training and validation set. It is normal to do that, but I don't see that in your code. Also, did the FER2013 winner used the cross-validation technique? Thanks.