SegGradCAM - GitLite

KO | EN

gitlite — search

#python #hacktoberfest #ai #typescript #llm #rust #docker #nodejs #java #windows #awesome #cli #kubernetes #open-source

SegGradCAM

(★ 107)

SEG-GRAD-CAM: Interpretable Semantic Segmentation via Gradient-Weighted Class Activation Mapping

파일 탐색기

최종 버전 다운로드 (.zip)

- - city_demo_backbone.ipynb
  - city_demo_vanilla.ipynb
  - train_cityscapes.py
- - LICENSE
  - mnist_generators_simple.py
  - README.md
  - TEXTURE_LICENSE
- - demo.ipynb
  - demo0.ipynb
  - train_texmnist_bias12.ipynb
- get_versions.ipynb
- __init__.py
- cityscape_labels.py
- dataloaders.py
- experiment_sgc.py
- metrics.py
- seggradcam.py
- training_plots.py
- training_write.py
- unet.py
- version.py
- visualize_sgc.py
.gitignore
LICENSE
poster_Vinogradova_AAAI_Feb2020.pdf
README.md
setup.py

# 설치 가이드

1. 코드 내려받기

git clone https://github.com/kiraving/SegGradCAM

깃허브에서 프로젝트 코드 전체를 내 컴퓨터로 내려받습니다.

cd SegGradCAM

방금 내려받은 프로젝트 폴더 안으로 이동합니다.

2. Python

쉬움 추천

사전 준비물

Git GitHub에서 프로젝트 코드를 내려받으려면 필요합니다.
Python 3 설치 시 'Add Python to PATH' 옵션을 꼭 체크하세요 (Windows).

pip install .

PyPI에 배포된 패키지를 바로 설치합니다. 소스 클론이 필요 없습니다.

jupyter notebook

브라우저에서 노트북(.ipynb) 파일들을 열람하고 실행할 수 있는 Jupyter 화면을 켭니다.

✅ 에러 메시지 없이 실행되고 터미널에 안내 문구가 출력되면 정상입니다.

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# SEG-GRAD-CAM
Publicly available implementation in Keras of our [paper](https://ojs.aaai.org/index.php/AAAI/article/view/7244) "Towards Interpretable Semantic Segmentation via Gradient-Weighted Class Activation Mapping" by Kira Vinogradova, Alexandr Dibrov, Gene Myers.

Check out our [poster](./poster_Vinogradova_AAAI_Feb2020.pdf) for a schematic overview of the method.

No updates or upgrades to newer versions are planned.

# Installation
``pip install git+https://github.com/kiraving/SegGradCAM.git``

# Requirements
Python 3.6, (recommended) Anaconda, versions of other packages can be found [here](./code/get_versions.ipynb)

Please download [Cityscapes](https://www.cityscapes-dataset.com/) (Fine annotations) if you intend to test Seg-Grad-CAM on a real-world dataset collected on German roads.

# Usage
* [Code for Seg-Grad-CAM method](./seggradcam/seggradcam.py#L118)
* [Notebook for training, loading pretrained model and usage of Seg-Grad-CAM on TextureMNIST](./code/textureMNIST-notebooks/demo.ipynb)
* [Training a U-Net with a backbone on Cityscapes & applying Seg-Grad-CAM](./code/cityscapes-notebooks/city_demo_backbone.ipynb) 
* [Vanilla U-Net on Cityscapes & Seg-Grad-CAM](./code/cityscapes-notebooks/city_demo_vanilla.ipynb)

# Credits:
[CSBDeep](https://github.com/csbdeep/csbdeep)

@article{weigert2018content,
      title={Content-aware image restoration: pushing the limits of fluorescence microscopy},
      author={Weigert, Martin and Schmidt, Uwe and Boothe, Tobias and M{\"u}ller, Andreas and Dibrov, Alexandr and Jain, Akanksha and Wilhelm, Benjamin and Schmidt, Deborah and Broaddus, Coleman and Culley, Si{\^a}n and others},
      journal={Nature methods},
      volume={15},
      number={12},
      pages={1090--1097},
      year={2018},
      publisher={Nature Publishing Group}
    }

[Cityscapes](https://www.cityscapes-dataset.com/) dataset:

@inproceedings{Cordts2016Cityscapes,
    title={The Cityscapes Dataset for Semantic Urban Scene Understanding},
    author={Cordts, Marius and Omran, Mohamed and Ramos, Sebastian and Rehfeld, Timo and Enzweiler, Markus and Benenson, Rodrigo and Franke, Uwe and Roth, Stefan and Schiele, Bernt},
    booktitle={Proc. of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
    year={2016}
    }

[segmentation_models](https://github.com/qubvel/segmentation_models) package:

@misc{Yakubovskiy:2019,
        Author = {Pavel Yakubovskiy},
        Title = {Segmentation Models},
        Year = {2019},
        Publisher = {GitHub},
        Journal = {GitHub repository},
        Howpublished = {\url{https://github.com/qubvel/segmentation_models}}
      }

[TextureMNIST dataset](https://github.com/boschresearch/GridSaliency-ToyDatasetGen)
Code for toy dataset generation of "Grid Saliency for Context Explanations of Semantic Segmentation" [paper](https://arxiv.org/abs/1907.13054)

# How to cite Seg-Grad-CAM:

@inproceedings{Vinogradova2020TowardsIS,
      title={Towards Interpretable Semantic Segmentation via Gradient-weighted Class Activation Mapping},
      author={Kira Vinogradova and Alexandr Dibrov and Eugene W. Myers},
      booktitle = {Proceedings of the AAAI Conference on Artificial Intelligence},
      year      = {2020},
      doi       = {10.1609/aaai.v34i10.7244}
    }