权重

[maoshanwen]

为啥我用您这个模型权重的时候报错RuntimeError: Error(s) in loading state_dict for CustomResNet18: size mismatch for conv1.weight: copying a param with shape torch.Size([64, 3, 7, 7]) from checkpoint, the shape in current model is torch.Size([64, 3, 3, 3]). size mismatch for fc.weight: copying a param with shape torch.Size([1000, 512]) from checkpoint, the shape in current model is torch.Size([10, 512]). size mismatch for fc.bias: copying a param with shape torch.Size([1000]) from checkpoint, the shape in current model is torch.Size([10]). 这里显示您第一层还是7*7的卷积核呀

[li554]

修改之后的第一层不是7x7，是3x3。但是你加载的权重是原始7x7的

[maoshanwen]

我后面直接使用您的模型结构和best.pth,结果RuntimeError: Error(s) in loading state_dict for Resnet18: Missing key(s) in state_dict: "conv1.conv.weight", "conv1.bn.weight", "conv1.bn.bias", "conv1.bn.running_mean", "conv1.bn.running_var", "layer1.block1.conv1.conv1.weight", "layer1.block1.conv1.bn1.weight", "layer1.block1.conv1.bn1.bias", "layer1.block1.conv1.bn1.running_mean", "layer1.block1.conv1.bn1.running_var", "layer1.block1.conv2.conv2.weight", "layer1.block1.conv2.bn2.weight", "layer1.block1.conv2.bn2.bias", "layer1.block1.conv2.bn2.running_mean", "layer1.block1.conv2.bn2.running_var", "layer1.block2.conv1.conv1.weight", "layer1.block2.conv1.bn1.weight", "layer1.block2.conv1.bn1.bias", "layer1.block2.conv1.bn1.running_mean", "layer1.block2.conv1.bn1.running_var", "layer1.block2.conv2.conv2.weight", "layer1.block2.conv2.bn2.weight", "layer1.block2.conv2.bn2.bias", "layer1.block2.conv2.bn2.running_mean", "layer1.block2.conv2.bn2.running_var", "layer2.block1.conv1.conv1.weight", "layer2.block1.conv1.bn1.weight", "layer2.block1.conv1.bn1.bias", "layer2.block1.conv1.bn1.running_mean", "layer2.block1.conv1.bn1.running_var", "layer2.block1.shortcut.conv.weight", "layer2.block1.shortcut.bn.weight", "layer2.block1.shortcut.bn.bias", "layer2.block1.shortcut.bn.running_mean", "layer2.block1.shortcut.bn.running_var", "layer2.block1.conv2.conv2.weight", "layer2.block1.conv2.bn2.weight", "layer2.block1.conv2.bn2.bias", "layer2.block1.conv2.bn2.running_mean", "layer2.block1.conv2.bn2.running_var", "layer2.block2.conv1.conv1.weight", "layer2.block2.conv1.bn1.weight", "layer2.block... Unexpected key(s) in state_dict: "bn1.weight", "bn1.bias", "bn1.running_mean", "bn1.running_var", "bn1.num_batches_tracked", "conv1.weight", "layer1.0.conv1.weight", "layer1.0.bn1.weight", "layer1.0.bn1.bias", "layer1.0.bn1.running_mean", "layer1.0.bn1.running_var", "layer1.0.bn1.num_batches_tracked", "layer1.0.conv2.weight", "layer1.0.bn2.weight", "layer1.0.bn2.bias", "layer1.0.bn2.running_mean", "layer1.0.bn2.running_var", "layer1.0.bn2.num_batches_tracked", "layer1.1.conv1.weight", "layer1.1.bn1.weight", "layer1.1.bn1.bias", "layer1.1.bn1.running_mean", "layer1.1.bn1.running_var", "layer1.1.bn1.num_batches_tracked", "layer1.1.conv2.weight", "layer1.1.bn2.weight", "layer1.1.bn2.bias", "layer1.1.bn2.running_mean", "layer1.1.bn2.running_var", "layer1.1.bn2.num_batches_tracked", "layer2.0.conv1.weight", "layer2.0.bn1.weight", "layer2.0.bn1.bias", "layer2.0.bn1.running_mean", "layer2.0.bn1.running_var", "layer2.0.bn1.num_batches_tracked", "layer2.0.conv2.weight", "layer2.0.bn2.weight", "layer2.0.bn2.bias", "layer2.0.bn2.running_mean", "layer2.0.bn2.running_var", "layer2.0.bn2.num_batches_tracked", "layer2.0.downsample.0.weight", "layer2.0.downsample.1.weight", "layer2.0.downsample.1.bias", "layer2.0.downsample.1.running_mean", "layer2.0.downsample.1.running_var", "layer2.0.downsample.1.num_batches_tracked", "layer2.1.conv1.weight", "layer2.1.bn1.weight", "layer2.1.bn1.bias", "layer2.1.bn1.running_mean", "layer2.1.bn1.running_var", "layer2.1.bn1.num_batches_tracked", "layer2...