Filtering image in pytorch

vision
6

Dear @JuanFMontesinos
I want to apply this high-pass filter to my images:
image

My model is defined as below:

class CNN(nn.Module):
    
    def __init__(self):
        super(CNN, self).__init__()
        
        self.conv1 = nn.Sequential(
            nn.Conv2d(3, 96, kernel_size=7, stride=1 , padding=3),
            nn.BatchNorm2d(96),
            nn.ReLU(),
            nn.MaxPool2d(2)
.
.
.

Could you please help me with how to do that? (not learned filter)

Can I apply the filter out of the model? for example, in dataloader?
Thank you I found the answer:

======
[Apply Filter as a part of preprocessing]