search

cleverhans-lab / cleverhans

An adversarial example library for constructing attacks, building defenses, and benchmarking both
MIT License
6.15k stars 1.39k forks source link

Missing non-linearity in torch/mnist_tutorial.py #1237

Closed litvand closed 1 year ago

litvand commented 1 year ago

Describe the bug There are two fully-connected layers with no non-linearity in between:

        x = self.fc1(x)
        x = self.fc2(x)

These could be replaced by a single layer.

To Reproduce Steps to reproduce the behavior:

  1. Run 'torch/mnist_tutorial.py'
  2. It takes longer to run than it would with a single layer

System configuration

litvand commented 1 year ago

On second thought it seems like the tutorial isn't being maintained