Visualisation toolkit for neural networks in PyTorch
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.
$ (sudo) pip install flashtorch
Usage (example notebooks)
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