SmoothGrad implementation in PyTorch
Switch branches/tags
Nothing to show
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Failed to load latest commit information.
lib Fixed typo Jul 31, 2017
results Fixed typo Jul 31, 2017
.gitignore Fixed typo Jul 31, 2017
LICENSE initial commit Jul 28, 2017
README.md Fixed image path Jul 31, 2017
grad_cam.py Fixed some bugs when using GPU Jul 31, 2017
saliency.py Fixed some bugs when using GPU Jul 31, 2017

README.md

SmoothGrad implementation in PyTorch

PyTorch implementation of SmoothGrad: removing noise by adding noise.

Vanilla Gradients SmoothGrad Guided backpropagation Guided SmoothGrad

And other techniques such as the following are implemented.

Download

git clone https://github.com/pkdn/pytorch-smoothgrad

Usage

Save the saliency maps using VanillaGrad, GuidedBackpropGrad, SmoothGrad, GuidedBackpropSmoothGrad.

python saliency.py --img <image-path>

Save the Grad-CAM image.

python grad_cam.py --img <image-path>

If you do not specify an image path, read the raccoon's data (scipy.misc.face()).

Requirements

  • PyTorch
  • torch-vision
  • numpy
  • scipy
  • OpenCV

Environment under Python 3.5.2 is tested.

Acknowledgments

This code is insipired by pytorch-grad-cam.