显示错误：“”ResNet“”对象没有“”classifier“”属性“”

Question

我下载Resnet18模型来训练模型。

当我键入

model

它显示了

ResNet(
  (conv1): Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False)
  (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  (relu): ReLU(inplace=True)
  (maxpool): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)
  (layer1): Sequential(
    (0): BasicBlock(
      (conv1): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU(inplace=True)
      (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
    (1): BasicBlock(
      (conv1): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU(inplace=True)
      (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
  )

  (layer3): Sequential(
    (0): BasicBlock(
      (conv1): Conv2d(128, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU(inplace=True)
      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (downsample): Sequential(
        (0): Conv2d(128, 256, kernel_size=(1, 1), stride=(2, 2), bias=False)
        (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
    )
    (1): BasicBlock(
      (conv1): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU(inplace=True)
      (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
  )
  (avgpool): AdaptiveAvgPool2d(output_size=(1, 1))
  (fc): Linear(in_features=512, out_features=1000, bias=True)
  (classifer): Sequential(
    (fc1): Linear(in_features=512, out_features=256, bias=True)
    (relu): ReLU()
    (fc5): Linear(in_features=128, out_features=2, bias=True)
    (output): LogSoftmax()
  )
)

正如您所看到的，它清楚地显示了分类器

但当我这么做的时候

optimizer = optim.Adam(model.classifier.parameters(), lr=0.001)

它显示一个错误

AttributeError: 'ResNet' object has no attribute 'classifier'

我不知道我做错了什么，如果你能帮助我，那就太好了。如果你愿意，我可以提供一些额外的细节。

Answer 1

删除classifier并仅保留model.parameters()。

optimizer = optim.Adam(model.parameters(), lr=0.001)

要构造Optimizer，您必须给它一个包含要优化的参数的迭代器。

Answer 2

假设你只想训练分类器，你可以冻结你不想改变的参数。对于您的情况，您可以这样做

for name, param in model.named_parameters() :
    param.requires_grad = False
    if name.startswith('classifier') : 
        param.requires_grad = True

这将冻结除分类器之外的所有参数。

然后，您可以按照the other answer的建议进行操作，即将所有参数传递给优化器。

optimizer = optim.Adam(model.parameters(), lr=0.001)