Skip to content
프로젝트

jonbarron/robust_loss_pytorch

GitHub에서 보기

jonbarron/robust_loss_pytorch has 706 GitHub stars and 88 forks. GitHot measured 0 stars in 24 hours. Last checked 2026-11-20 20:03 UTC. Last push 2025-09-04.

이 수치를 측정하는 방법

측정된 스타 증가

in 24h
0
in 7 days
기록 수집 중
in 15 days
기록 수집 중
in 1 month
기록 수집 중

서로 겹치는 기간의 순증가량이며 일별 합계가 아닙니다. 측정값이 없으면 비워 둡니다. 스타는 관심도를 나타내며 품질을 보장하지 않습니다.

소개

A pytorch port of google-research/google-research/robust_loss/

머신러닝

README.md

Original

A General and Adaptive Robust Loss Function

This directory contains reference code for the paper A General and Adaptive Robust Loss Function, Jonathan T. Barron CVPR, 2019

The code is implemented in Pytorch, and is a port of the TensorFlow implementation at: https://github.com/google-research/google-research/tree/master/robust_loss.

Installation

Typical Install

pip install git+https://github.com/jonbarron/robust_loss_pytorch

Development

git clone https://github.com/jonbarron/robust_loss_pytorch
cd robust_loss_pytorch/
pip install -e .[dev]

Tests can then be run from the root of the project using:

nosetests

Usage

To use this code import lossfun, or AdaptiveLossFunction and call the loss function. general.py implements the "general" form of the loss, which assumes you are prepared to set and tune hyperparameters yourself, and adaptive.py implements the "adaptive" form of the loss, which tries to adapt the hyperparameters automatically and also includes support for imposing losses in different image representations. The probability distribution underneath the adaptive loss is implemented in distribution.py.

from robust_loss_pytorch import lossfun

or

from robust_loss_pytorch import AdaptiveLossFunction

A toy example of how this code can be used is in example.ipynb.

Citation

If you use this code, please cite it:

@article{BarronCVPR2019,
  Author = {Jonathan T. Barron},
  Title = {A General and Adaptive Robust Loss Function},
  Journal = {CVPR},
  Year = {2019}
}