The part of VGG16 Feature extractor

[hichoe95]

Thank you for your PyTorch open-source of IPR!

I have a question about the feature extractor code.
To the best of my knowledge, the feature extractor should use features after the 'ReLU' layer.

In vgg16 classifier block,

(classifier): Sequential( 
    (0): Linear(in_features=25088, out_features=4096, bias=True) 
    (1): ReLU(inplace=True) 
    (2): Dropout(p=0.5, inplace=False) 
    (3): Linear(in_features=4096, out_features=4096, bias=True) 
    (4): ReLU(inplace=True) 
    (5): Dropout(p=0.5, inplace=False) 
    (6): Linear(in_features=4096, out_features=1000, bias=True) 
  )

for using feature after ReLU layer, the code should be feature = self.vgg16.classifier[:5](before_fc)
, not feature = self.vgg16.classifier[:4](before_fc) .

I'd like to know whether my opinion is right or not.