This is the pytorch implementation of "Axiomatic Attribution for Deep Networks". The original tensorflow version could be found here.

• ankurtaly's tensorflow version

• python-3.5.2
• pytorch-0.4.1
• opencv-python

• add more functions as the original code.
• finetune the results, make them close to the original paper.

Highly recommend to use GPU to accelerate the computation. If you use CPU, I will recommend to select some small networks, such as resnet18. You also need to put your images under examples/.

• inception
• resnet18
• resnet152
• vgg19

python main.py --cuda --model-type='inception' --img='01.jpg'

Results are slightly different from the original paper, it may have some bugs or need to do some adjustments. I will keep updating it, any contributions are welcome!