Skip to content

Files

Latest commit

394feb7 · Jan 7, 2022

History

History
75 lines (57 loc) · 3.64 KB

README.md

File metadata and controls

75 lines (57 loc) · 3.64 KB

Attribution methods - pytorch

This is a PyTorch implementation of attribution methods, Grad-Cam, Grad-Cam++, Guided Back Propagation, Guided Grad-Cam and Guided Grad-Cam++.

These codes have been used for the paper "Visual Explanation of a Deep Learning Solar Flare Forecast Model and Its Relationship to Physical Parameters" (https://doi.org/10.3847/1538-4357/abdebe).

These codes can be used for any custom models constructed by pytorch and pretrained models provided from torchvision.

Example (1)- Grad-CAM results

Image Container ship label Steel arch bridge label

Example (2)- Guided backpropagation results

Image Bull mastiff label Tigercat label

Example (3)- Guided Grad-CAM results

Image Sea lion label Penguin label

Example (4)- Grad-CAM results from the first CNN block to the last CNN block of the DenseNet161 model

Label First block Second block Third block Last block
Indigo bird
Birdhouse