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
UserWarning: volatile was removed and now has no effect. Use with torch.no_grad(): instead.
inputs, targets = Variable(inputs, volatile=True), Variable(targets)
Its located in mainpro_CK+.py line 141, can you give me suggestion? thanks.
You may use a higher version of pytorch~ please comment "inputs, targets = Variable(inputs, volatile=True), Variable(targets)", and add "with torch.no_grad():" before eval~
Running mainpro_CK+.py and got this warning:
UserWarning: volatile was removed and now has no effect. Use
with torch.no_grad():
instead. inputs, targets = Variable(inputs, volatile=True), Variable(targets)Its located in mainpro_CK+.py line 141, can you give me suggestion? thanks.