Largest multi-label image database; ResNet-101 model; 80.73% top-1 acc on ImageNet
Geek Repo:Geek Repo
Github PK Tool:Github PK Tool
Xelawk opened this issue 5 years ago · comments
我发现train.py,损失函数是Cross_entropy, 如果多Multi-labels的图像分类,不应该是使用Binary entropy吗?望解答!