错误：

RuntimeError: Error(s) in loading state_dict for DataParallel:
	size mismatch for module.conv1.weight: copying a param with shape torch.Size([16, 3, 3, 3]) from checkpoint, the shape in current model is torch.Size([128, 128, 3, 3]).
	size mismatch for module.bn1.weight: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([128]).
	size mismatch for module.bn1.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([128]).
	size mismatch for module.bn1.running_mean: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([128]).
	size mismatch for module.bn1.running_var: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([128]).
	size mismatch for module.bn2.weight: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]).
	size mismatch for module.bn2.bias: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]).
	size mismatch for module.bn2.running_mean: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]).
	size mismatch for module.bn2.running_var: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([256]).

解决方案：

在加载模型时加上上面这句话，因为是多GPU训练出来的模型。

model = nn.DataParallel(model).cuda()
model.load_state_dict(torch.load("C:\\Users\\83543\\Desktop\\model_best.pth.tar")['state_dict'],False)