fer2013训练好的模型

WuJie1010 / Facial-Expression-Recognition.Pytorch

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

MIT License

1.79k stars 550 forks source link

fer2013训练好的模型 #26

Closed LeonardNiu closed 5 years ago

LeonardNiu commented 5 years ago

您好，由于自己的设备问题没办法实现对数据集fer2013的训练，请问您有最终达到70%左右准确率的参数文件吗？我想看一下最终效果，谢谢

NomiMalik0207 commented 5 years ago

i think the same setting of parameters meet 70+% accuracy on VGG using FER2013. I have tested it. I do not know why you did not get it. https://drive.google.com/open?id=1Oy_9YmpkSKX1Q8jkOhJbz3Mc7qjyISzU you can found here the pre trained model and run visulize.py to check the results