Custom a new convolution layer in cnn

2

If you would like to define a custom kernel, you could just set the weight attribute to it.
Here is a small example:

class MyModel(nn.Module):
    def __init__(self, kernel):
        super(MyModel, self).__init__()
        self.conv1 = nn.Conv2d(1, 1, 3, 1, 1, bias=False)
        # Add other layers here
        
        # Initialize conv1 with custom kernel
        self.conv1.weight = nn.Parameter(kernel)
        
    def forward(self, x):
        x = self.conv1(x)
        # pass x to other modules
        return x        

kernel = torch.randn(1, 1, 3, 3)  # Define your custom kernel
model = MyModel(kernel)
x = torch.randn(1, 1, 24, 24)
output = model(x)
2 Likes