Deactivate a feature map

vision
1

There are lots of posts on feature visualization. But how do I deactivate a feature map (not filter)?

(layer4): Sequential(
(0): BasicBlock(
(conv1): Conv2d(256, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=1)
(relu): ReLU(inplace=True)
(conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=1)
(downsample): Sequential(
(0): Conv2d(256, 512, kernel_size=(1, 1), stride=(2, 2), bias=False)
(1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=1)
)
)
(1): BasicBlock(
(conv1): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=1)
(relu): ReLU(inplace=True)
(conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=1)
)
)

For the layer4.conv2 I want to set a feature map (not weights or filters) to zero at the output channel during inference. For example, ith output channel of conv2 in layer 4. Is it even possible?

2

Multiply the forward activation in the forward method with a mask, which will zero out the desired channel.

3

I tried to do the following:

def forward(self, x):
    x = self.conv1(x)
    x = self.bn1(x)
    x = self.relu(x)
    x = self.layer1(x)
    x = self.layer2(x)
    x = self.layer3(x)
    x = self.layer4(x)
    
   if self.usingfeaturedeactivation and self.feature_idx is not None:
        x[:,self.feature_idx,:,:] = 0
    
   x = self.avgpool(x)

    x = x.view(x.size(0), -1)
    x = self.fc(x)

    return x

Seems like it’s working. Thanks!