How to get the intermediate layers output 'model.feature_list(input)' for any customized CNN like we do it in a pretrained ResNet34?

vision
2

You could pass through each individual block. Something like this

x1 = model.layer1(input)
x2 = model.layer2(x1)
x3 = model.layer3(x2)
x4 = model.layer4(x3)

etc. Then return the intermediate values.