This is the pytorch implementation of the paper - Axiomatic Attribution for Deep Networks.

Last update: Dec 23, 2022

Overview

Integrated Gradients

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

Acknowledgement

ankurtaly's tensorflow version

Requirements

python-3.5.2
pytorch-0.4.1
opencv-python

TODO List

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

Instructions

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/.

Lists of networks that support (of course, you can add any networks by yourself)

inception
resnet18
resnet152
vgg19

Run the code

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

Results

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!

This is the pytorch implementation of the paper - Axiomatic Attribution for Deep Networks.

Related tags

Overview

Integrated Gradients

Acknowledgement

Requirements

TODO List

Instructions

Lists of networks that support (of course, you can add any networks by yourself)

Run the code

Results

Inception-v3

ResNet-18

ResNet-152

VGG-19

Owner

Tianhong Dai

Malware Analysis Neural Network project.

for taichi voxel-challange event

Open source hardware and software platform to build a small scale self driving car.

JittorVis - Visual understanding of deep learning models

PyTorch code for the paper "Curriculum Graph Co-Teaching for Multi-target Domain Adaptation" (CVPR2021)

Part-aware Measurement for Robust Multi-View Multi-Human 3D Pose Estimation and Tracking

The official implementation of CVPR 2021 Paper: Improving Weakly Supervised Visual Grounding by Contrastive Knowledge Distillation.

PyTorch implementation of U-TAE and PaPs for satellite image time series panoptic segmentation.

Adaptive Denoising Training (ADT) for Recommendation.

DeLiGAN - This project is an implementation of the Generative Adversarial Network

Hybrid Neural Fusion for Full-frame Video Stabilization

Time series annotation library.

Code for our CVPR 2021 paper "MetaCam+DSCE"

Custom Implementation of Non-Deep Networks

MarcoPolo is a clustering-free approach to the exploration of bimodally expressed genes along with group information in single-cell RNA-seq data

A Python package for time series augmentation

A Re-implementation of the paper "A Deep Learning Framework for Character Motion Synthesis and Editing"

Classic Papers for Beginners and Impact Scope for Authors.

yolov5 deepsort 行人车辆跟踪检测计数

[ICCV-2021] An Empirical Study of the Collapsing Problem in Semi-Supervised 2D Human Pose Estimation

This is the pytorch implementation of the paper - Axiomatic Attribution for Deep Networks.

Related tags

Overview

Integrated Gradients

Acknowledgement

Requirements

TODO List

Instructions

Lists of networks that support (of course, you can add any networks by yourself)

Run the code

Results

Inception-v3

ResNet-18

ResNet-152

VGG-19

Owner

Tianhong Dai

Malware Analysis Neural Network project.

for taichi voxel-challange event

Open source hardware and software platform to build a small scale self driving car.

JittorVis - Visual understanding of deep learning models

PyTorch code for the paper "Curriculum Graph Co-Teaching for Multi-target Domain Adaptation" (CVPR2021)

Part-aware Measurement for Robust Multi-View Multi-Human 3D Pose Estimation and Tracking

The official implementation of CVPR 2021 Paper: Improving Weakly Supervised Visual Grounding by Contrastive Knowledge Distillation.

PyTorch implementation of U-TAE and PaPs for satellite image time series panoptic segmentation.

Adaptive Denoising Training (ADT) for Recommendation.

DeLiGAN - This project is an implementation of the Generative Adversarial Network

Hybrid Neural Fusion for Full-frame Video Stabilization

Time series annotation library.

Code for our CVPR 2021 paper "MetaCam+DSCE"

Custom Implementation of Non-Deep Networks

MarcoPolo is a clustering-free approach to the exploration of bimodally expressed genes along with group information in single-cell RNA-seq data

A Python package for time series augmentation

A Re-implementation of the paper "A Deep Learning Framework for Character Motion Synthesis and Editing"

Classic Papers for Beginners and Impact Scope for Authors.

yolov5 deepsort 行人 车辆 跟踪 检测 计数

[ICCV-2021] An Empirical Study of the Collapsing Problem in Semi-Supervised 2D Human Pose Estimation

yolov5 deepsort 行人车辆跟踪检测计数