CODEWITHSUNDEEP
deep-learningpytorchtorchresnettorchvision
Anubhav Sinha
Anubhav Sinha

Reputation: 160

Errow Showing :'ResNet' object has no attribute 'classifier'

I download Resnet18 model to train a model.

When I type 

model

it shows

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()
  )
)

As you can see it clearly shows the classifier

but when I do

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

it shows an error

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

I don't know what mistake I am doing, if you can help that would be great. I can provide some extra details if you want.

Upvotes: 3

Views: 9490

Answers (2)

akshayk07
akshayk07

Reputation: 2200

Assuming you want to train only the classifier, you can freeze the parameters you don't want to change. For your case, you can do

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

This will freeze all the parameters except of the classifier.

And then you can do what the other answer suggests i.e. pass all parameters to the optimizer.

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

Upvotes: 1

Sparsh
Sparsh

Reputation: 1498

Remove classifier and keep it model.parameters() only.

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

To construct an Optimizer you have to give it an iterable containing the parameters to optimize.

Upvotes: 2

Related Questions