timm-vis is a PyTorch image models visualizer.

Implementation of various visualization techniques for pytorch image
classifiers. This library can be used to visualize and understand any PyTorch
image classifier. This is NOT an official PyTorch library, nor is it affiliated
with Ross Wightman's pytorch-image-models library. details.ipynb has visual
examples of all methods implemented.

Currently, the following methods are implemented:
* Filter visualization
* Activations visualization
* Maximally activated patches
* Saliency maps
* Synthetic image generation
* Adversarial attacks to fool models
* Feature inversion
* Grad-CAM
* Deep Dream