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.
