coral-pytorch - GitLite

KO | EN

gitlite — search

#javascript #python #react #typescript #llm #go #android #rust #deep-learning #nodejs #java #cli #kubernetes #awesome-list

coral-pytorch

(★ 278)

CORAL and CORN implementations for ordinal regression with deep neural networks.

파일 탐색기

최종 버전 다운로드 (.zip)

- - python-package-conda.yml
- - test_dataset__corn_label_from_logits.py
  - test_dataset__label_to_levels.py
  - test_dataset__levels_from_labelbatch.py
  - test_dataset__proba_to_label.py
  - test_layers__corallayer.py
  - test_losses.py
- __init__.py
- dataset.py
- layers.py
- losses.py
- - coral-logo-alpha.png
  - coral-logo-alpha.pxm
  - corn-coral-logo copy.png
  - corn-coral-logo-alpha.png
  - corn-coral-logo.png
  - figure1.jpg
- CHANGELOG.md
- citing.md
- extra.css
- favicon.ico
- index.md
- installation.md
- ipynb2markdown.py
- license.md
- make_api.py
- mathjaxhelper.js
.gitignore
environment.yml
LICENSE.txt
mkdocs.yml
pytest.ini
README.md
requirements-docs.txt
requirements.txt
setup.cfg
setup.py

# 설치 가이드

1. 코드 내려받기

git clone https://github.com/Raschka-research-group/coral-pytorch

깃허브에서 프로젝트 코드 전체를 내 컴퓨터로 내려받습니다.

cd coral-pytorch

방금 내려받은 프로젝트 폴더 안으로 이동합니다.

2. 공식 설치 스크립트

쉬움 추천

사전 준비물

Python 3 pip 명령어를 쓰려면 Python이 필요합니다.

pip install coral-pytorch

PyPI에 배포된 패키지를 바로 설치합니다. 소스 클론이 필요 없습니다.

✅ 설치 후 새 터미널을 열고, 프로그램의 버전 확인 명령(예: --version)으로 정상 설치됐는지 확인하세요.

이 레포의 README에 적힌 실제 명령어를 그대로 가져왔습니다.

3. Python

쉬움

사전 준비물

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

pip install coral-pytorch

PyPI에 배포된 패키지를 바로 설치합니다. 소스 클론이 필요 없습니다.

✅ 에러 메시지 없이 실행되고 터미널에 안내 문구가 출력되면 정상입니다.

이 레포의 README에 적힌 실제 명령어를 그대로 가져왔습니다.

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

<img src="docs/img/corn-coral-logo-alpha.png" width=300>

**CORAL & CORN implementations for ordinal regression with deep neural networks.**

[![PyPI version](https://badge.fury.io/py/coral-pytorch.svg)](https://badge.fury.io/py/coral-pytorch)
[![License](https://img.shields.io/badge/license-MIT-blue.svg)](https://github.com/Raschka-research-group/coral-pytorch/blob/main/LICENSE.txt)
![Python 3](https://img.shields.io/badge/python-3-blue.svg)

<br>

**Documentation: [https://Raschka-research-group.github.io/coral-pytorch](https://Raschka-research-group.github.io/coral-pytorch)**

---

## Installation

```bash
pip install coral-pytorch
```

## About

CORAL (COnsistent RAnk Logits) and CORN (Conditional Ordinal Regression for Neural networks) are methods for ordinal regression with deep neural networks, which address the rank inconsistency issue of other ordinal regression frameworks.

<img src="docs/img/figure1.jpg" width=400>

Originally, developed this method in the context of age prediction from face images. Our approach was evaluated on several face image datasets for age prediction using ResNet-34, but it is compatible with other state-of-the-art deep neural networks.

This repository implements the CORAL and CORN functionality (neural network layer, loss function, and dataset utilities) for convenient use. Examples are provided via the "Tutorials" that can be found on the documentation website at [https://Raschka-research-group.github.io/coral-pytorch](https://Raschka-research-group.github.io/coral-pytorch).

If you are looking for the orginal implementation, training datasets, and training log files corresponding to the paper, you can find these here:

- CORAL: [https://github.com/Raschka-research-group/coral-cnn](https://github.com/Raschka-research-group/coral-cnn).
- CORN: [https://github.com/Raschka-research-group/corn-ordinal-neuralnet](https://github.com/Raschka-research-group/corn-ordinal-neuralnet)

---

## Cite as

If you use CORAL or CORN  as part of your workflow in a scientific publication, please consider citing the corresponding paper:

**CORAL**

- Wenzhi Cao, Vahid Mirjalili, and Sebastian Raschka (2020).  *Rank Consistent Ordinal Regression for Neural Networks with Application to Age Estimation*. Pattern Recognition Letters 140, pp. 325-331; [https://doi.org/10.1016/j.patrec.2020.11.008](https://doi.org/10.1016/j.patrec.2020.11.008).

```
@article{coral2020,
title={Rank consistent ordinal regression for neural networks with application to age estimation},
journal={Pattern Recognition Letters},
volume={140},
pages={325-331},
year={2020},
issn={0167-8655},
doi={https://doi.org/10.1016/j.patrec.2020.11.008},
url={http://www.sciencedirect.com/science/article/pii/S016786552030413X},
author={Wenzhi Cao and Vahid Mirjalili and Sebastian Raschka}
}
```

**CORN**

- Xintong Shi, Wenzhi Cao, and Sebastian Raschka (2021). Deep Neural Networks for Rank-Consistent Ordinal Regression Based On Conditional Probabilities. Arxiv preprint;  [https://arxiv.org/abs/2111.08851](https://arxiv.org/abs/2111.08851)

```
@misc{shi2021deep,
      title={Deep Neural Networks for Rank-Consistent Ordinal Regression Based On Conditional Probabilities}, 
      author={Xintong Shi and Wenzhi Cao and Sebastian Raschka},
      year={2021},
      eprint={2111.08851},
      archivePrefix={arXiv},
      primaryClass={cs.LG}
}
```