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
> > > 我也是这个问题，有什么办法不回退到python2.7来解决这个问题么 > > > > > > 我之前就是退回2.7搞得，要是你用python3解决了可以分享一下嘛 > > 回退2.7会import不了torch，不知道是不是官方抛弃了2.7的问题，python3的代码也不知道从哪改，唉 可以价格wechat交流一下啊 _Originally posted by @lander1003 in https://github.com/WuJie1010/Facial-Expression-Recognition.Pytorch/issues/58#issuecomment-586597317_
想请问下作者为什么无论运行哪个代码都是这个结果，没有别的任何显示，谢谢。 
os.popen
请问一下这句code的参数是不是有问题呀 _, term_width = os.popen('stty size', 'r').read().split() term_width = int(term_width) 当我run mainpro_CK+.py时会有这样的错误 _, term_width = os.popen('stty size', 'r').read().split() ValueError: not enough values to unpack (expected 2, got 0)
Dear, I see through the FER code "main_FER.py" carefully, but don't see any code about validation. However, there exist public test and private test. I wonder does the public test...
the FER2013 image size is 48*48 but in the code setting: cut_size = 44 why to random cut the image to 44*44
