fine-tuning，resnet18结构

修改resnet最后的全连接层输出大小：

resnet = torchvision.models.resnet18(pretrained=True)

for param in resnet.parameters():
    param.requires_grad = False.  #冻结所有层

resnet.fc =nn.Linear(resnet.fc.in_features,100)。#修改fc层的输出size为100