https://discuss.pytorch.org/t/how-to-modify-the-final-fc-layer-based-on-the-torch-model/766/12

That’s because vgg19 doesn’t have a fc member variable. Instead, it has a

  (classifier): Sequential (
    (0): Dropout (p = 0.5)
    (1): Linear (25088 -> 4096)
    (2): ReLU (inplace)
    (3): Dropout (p = 0.5)
    (4): Linear (4096 -> 4096)
    (5): ReLU (inplace)
    (6): Linear (4096 -> 100)
  )
 

To replace the last linear layer, a temporary solution would be

vgg19.classifier._modules['6'] = nn.Linear(4096, 8)