How to visualise filters in a CNN with PyTorch

Question

I'm new to deep learning and Pytorch. I want to visual my filter in my CNN model so that I can iterate layer in the CNN model that I define. But I meet error like below.

error: 'CNN' object is not iterable

The CNN object is my model.

My iteration code is like below：

for index, layer in enumerate(self.model):             
# Forward pass layer by layer
    x = layer(x)

my model code like below：

class CNN(nn.Module):
    def __init__(self):
        super(CNN,self).__init__()
        self.Conv1 = nn.Sequential( # input image size (1,28,20)
            nn.Conv2d(1, 16, 5, 1, 2), # outputize (16,28,20)
            nn.ReLU(),
            nn.MaxPool2d(2),           #outputize (16,14,10)
        )
        self.Conv2 = nn.Sequential( # input ize ? (16,,14,10)
            nn.Conv2d(16, 32, 5, 1, 2),   #output size(32,14,10)
            nn.ReLU(),
            nn.MaxPool2d(2),        #output size (32,7,5)
        )
        self.fc1 = nn.Linear(32 * 7 * 5, 800) 
        self.fc2 = nn.Linear(800,500)
        self.fc3 = nn.Linear(500,10)
        #self.fc4 = nn.Linear(200,10)
        
    def forward(self,x):
        x = self.Conv1(x)
        x = self.Conv2(x)
        x = x.view(x.size(0), -1)
        x = self.fc1(x)
        x = F.dropout(x)
        x = F.relu(x)
        x = self.fc2(x)
        x = F.dropout(x)
        x = F.relu(x)
        x = self.fc3(x)
        #x = F.relu(x)
        #x = self.fc4(x)
        return x

So anyone can tell me how can I solve this problem.

Answer 1

Essentially, you will need to access the features in your model and transpose those matrices into the right shape first, then you can visualise the filters

    import numpy as np
    import matplotlib.pyplot as plt
    from torchvision import utils

    def visTensor(tensor, ch=0, allkernels=False, nrow=8, padding=1): 
        n,c,w,h = tensor.shape

        if allkernels: tensor = tensor.view(n*c, -1, w, h)
        elif c != 3: tensor = tensor[:,ch,:,:].unsqueeze(dim=1)

        rows = np.min((tensor.shape[0] // nrow + 1, 64))    
        grid = utils.make_grid(tensor, nrow=nrow, normalize=True, padding=padding)
        plt.figure( figsize=(nrow,rows) )
        plt.imshow(grid.numpy().transpose((1, 2, 0)))


    if __name__ == "__main__":
        layer = 1
        filter = model.features[layer].weight.data.clone()
        visTensor(filter, ch=0, allkernels=False)

        plt.axis('off')
        plt.ioff()
        plt.show()

You should be able to get a grid visual.

There are a few more visualisation techniques, you can study them here