Visualisation toolkit for neural networks in PyTorch
Project description
FlashTorch :flashlight:
Visualisation toolkit implemented in PyTorch for inspecting what neural networks learn in image recognition tasks (feature visualisation).
The project is very much work in progress, and I would appreciate your feedback!
It currently supports visualisation of saliancy maps for all the models available under torchvision.models.
Installation
$ (sudo) pip install flashtorch
Usage (example notebooks)
Papers
-
Using backpropagation for gradient visualisation: Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
-
Guided backprobagation: Striving for Simplicity: The All Convolutional Net
Inspirations
-
pytorch-cnn-visualizations by utkuozbulak
-
keras-vis by raghakot
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.