A collection of visual attribution methods for model interpretability
Including:
- Vanilla Gradient Saliency
- Grad X Input
- Integrated Gradient
- SmoothGrad
- Deconv
- Guided Backpropagation
- Excitation Backpropagation, Contrastive Excitation Backpropagation
- GradCAM
- PatternNet, PatternLRP
- Real Time Saliency
- Occlusion
- Feedback
- DeepLIFT
- Meaningful Perturbation
- Linux
- NVIDIA GPU + CUDA (Current only support running on GPU)
- Python 3.x
- PyTorch version == 0.2.0 (Sorry I haven't tested on newer versions)
- torchvision, skimage, matplotlib
- Clone this repo:
git clone git@github.com:yulongwang12/visual-attribution.git
cd visual-attribution
- Download pretrained weights
cd weights
bash ./download_patterns.sh # for using PatternNet, PatternLRP
bash ./download_realtime_saliency.sh # for using Real Time Saliency
Note: I convert caffe bvlc_googlenet pretrained models in pytorch format (see googlenet.py
and weights/googlenet.pth
).
see notebook saliency_comparison.ipynb. If everything works, you will get the above image.
TBD
TBD