阅读量:1
- original paper:《Axiomatic Attribution for Deep Networks》https://arxiv.org/pdf/1703.01365
2)usage : https://blog.paperspace.com/model-interpretability-and-understanding-for-pytorch-using-captum/
https://captum.ai/docs/extension/integrated_gradients
3)https://github.com/TianhongDai/integrated-gradient-pytorch
