Facial-Expression-Recognition.Pytorch
Facial-Expression-Recognition.Pytorch copied to clipboard
WuJie1010
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 is there resnet18 pretrained weights in the 'PrivateTest_model.t7' ? i change the "net = VGG('VGG19')" to the "net = ResNet18()" in the "visualize.py" but i encountered the following error...
@WuJie1010 @Hippasuss Hi authors, I have a question about CK+ preprocess py file. I got the output which is: (981, 48, 48) (981,) Save data finish!!! datafile.create_dataset("data_pixel", dtype = 'uint8',...
@WuJie1010 Hi Wujie, I'm kind of confused with clip_gradient which is this sentence: "clip_gradient(optimizer, 0.1)" I only know the gradient is for regularization, but don't know the details, that's also...
Hi, Do model CNN using Private Test dataset in your code do learning too? As far as I know, model CNN using Private Test dataset don't need learning. Sorry if...
Hi Wujie, I have some questions about the t7 file, it may sound stupid. So I know the t7 file stores the parameters or the model, but how can I...
Hi, I am wondering if you will release the pretrained model for CK+ dataset, or would you mind sending a CK+ pretrained model via email. Thanks!
