Get weights as list from a CNN

1

I am working on this CNN:

  class CustomConvNet(nn.Module):
    def __init__(self, num_classes):
        super(CustomConvNet, self).__init__()

        self.layer1 = self.conv_module(3, 64)
        self.layer2 = self.conv_module(64, 128)
        self.layer3 = self.conv_module(128, 256)
        self.layer4 = self.conv_module(256, 256)
        self.layer5 = self.conv_module(256, 512)
        self.gap = self.global_avg_pool(512, num_classes)
        #self.linear = nn.Linear(512, num_classes)
        #self.relu = nn.ReLU()
        #self.softmax = nn.Softmax()

    def forward(self, x):
        out = self.layer1(x)
        out = self.layer2(out)
        out = self.layer3(out)
        out = self.layer4(out)
        out = self.layer5(out)
        out = self.gap(out)
        out = out.view(-1, 4)
        #out = self.linear(out)

        return out

    def conv_module(self, in_num, out_num):
        return nn.Sequential(
            nn.Conv2d(in_num, out_num, kernel_size=3, stride=1, padding=1),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=(2, 2), stride=None))

    def global_avg_pool(self, in_num, out_num):
        return nn.Sequential(
            nn.Conv2d(in_num, out_num, kernel_size=3, stride=1, padding=1),
            #nn.BatchNorm2d(out_num),
            #nn.LeakyReLU(),

            nn.ReLU(),
            nn.Softmax(),
            nn.AdaptiveAvgPool2d((1, 1)))

Is there a way of getting the weights of the first layer as a list? I know one can save the model as a pth file, but I need a list with the weights. Thanks!

2

In your case your first layer has 1 Conv2d, 1 ReLU, and 1 MaxPool2d
You can get the weights of your Conv2d of layer1 by doing

# Just a sample CustomConvNet
net = CustomConvNet(num_classes=10)
# Print the weights of Conv2d of layer1
print(net.layer1[0].weight.data)
# Print the bias of Conv2d of layer1
print(net.layer1[0].bias.data)

[0] because nn.Conv2d is the first in your nn.Sequential
So if you print(net.layer1) you will see

Sequential(
  (0): Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (1): ReLU()
  (2): MaxPool2d(kernel_size=(2, 2), stride=(2, 2), padding=0, dilation=1, ceil_mode=False)
)