The output layer is equal to Linear layer, however it should not to be

[whisperLiang]

Here is the code:

import torch import torchvision import torchlens as tl

model = torchvision.models.alexnet(pretrained=True) x = torch.rand(1, 3, 224, 224) model_history = tl.log_forward_pass(model, x, vis_opt='unrolled', save_function_args=True) layer_list = model_history.layer_list print(layer_list[-1]) print(model_history)

[johnmarktaylor91]

In TorchLens the output layer is always just a copy of the final layer. So it should indeed be the same.

[whisperLiang]

Ok, thanks!