Load only a part of the network with pretrained weights

2

Hi,

For this, there are different approaches but personally, I would create a class on top of previously defined model which you have weights for. Then add any other layers as another sequential to the new defined model. Something like this:

pretrained = torchvision.models.alexnet(pretrained=True)
class MyAlexNet(nn.Module):
    def __init__(self, my_pretrained_model):
        super(MyAlexNet, self).__init__()
        self.pretrained = my_pretrained_model
        self.my_new_layers = nn.Sequential(nn.Linear(1000, 100),
                                           nn.ReLU(),
                                           nn.Linear(100, 2))
    
    def forward(self, x):
        x = self.pretrained(x)
        x = self.my_new_layers(x)
        return x

my_extended_model = MyAlexNet(my_pretrained_model=pretrained)
my_extended_model

# here is the structure

MyAlexNet(
  (pretrained): AlexNet(
    (features): Sequential(
      (0): Conv2d(3, 64, kernel_size=(11, 11), stride=(4, 4), padding=(2, 2))
      (1): ReLU(inplace=True)
      (2): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=False)
      (3): Conv2d(64, 192, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
      (4): ReLU(inplace=True)
      (5): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=False)
      (6): Conv2d(192, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
      (7): ReLU(inplace=True)
      (8): Conv2d(384, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
      (9): ReLU(inplace=True)
      (10): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
      (11): ReLU(inplace=True)
      (12): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=False)
    )
    (avgpool): AdaptiveAvgPool2d(output_size=(6, 6))
    (classifier): Sequential(
      (0): Dropout(p=0.5, inplace=False)
      (1): Linear(in_features=9216, out_features=4096, bias=True)
      (2): ReLU(inplace=True)
      (3): Dropout(p=0.5, inplace=False)
      (4): Linear(in_features=4096, out_features=4096, bias=True)
      (5): ReLU(inplace=True)
      (6): Linear(in_features=4096, out_features=1000, bias=True)
    )
  )  # till here corresponds to AlexNet's original implementation
  (my_new_layers): Sequential(
    (0): Linear(in_features=1000, out_features=100, bias=True)
    (1): ReLU()
    (2): Linear(in_features=100, out_features=2, bias=True)
  )
)

Bests

9 Likes