A PyTorch Library for Multi-Task Learning
multitask-learning 开源项目推荐(320 个)
multitask-learning 话题在 GitHub 上没有填写简介,这里按 Star 数汇总最相关的热门仓库。
热门项目 前 20
按 Star 数排序展示前 20 个 · GitHub 共 320 个仓库Benchmarking Knowledge Transfer in Lifelong Robot Learning
The Natural Language Decathlon: A Multitask Challenge for NLP
You Only Look Once for Panopitic Driving Perception.(MIR2022)
jiant is an nlp toolkit
HybridNets: End-to-End Perception Network
PromptCLUE, 全中文任务支持零样本学习模型
Reference code for the paper: Deep White-Balance Editing (CVPR 2020). Our method is a deep learning multi-task framework for white-balance editing.
BERT for Multitask Learning
Crosslingual Generalization through Multitask Finetuning
Official Pytorch implementation of "OmniNet: A unified architecture for multi-modal multi-task learning" | Authors: Subhojeet Pramanik, Priyanka Agrawal, Aman Hussain
快速最佳子集选择库
Library for Jacobian descent with PyTorch. It enables the optimization of neural networks with multiple losses (e.g. multi-task learning).
A list of multi-task learning papers and projects.
multi_task_NLP is a utility toolkit enabling NLP developers to easily train and infer a single model for multiple tasks.
MTReclib provides a PyTorch implementation of multi-task recommendation models and common datasets.
中文NER的那些事儿
深度学习推断多重免疫荧光用于 IHC 图像定量(https://deepliif.org)[Nature Machine Intelligence'22, CVPR'22, MICCAI'23, Histopathology'23, MICCAI'24]
[CVPR2023] Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspective
[ECCV 2020] Self-Supervised Monocular Depth Estimation: Solving the Dynamic Object Problem by Semantic Guidance
关于这个话题
- 清单取自 GitHub 话题页并按 Star 数排序,每次展示前 20 个项目;原始页面见 https://github.com/topics/multitask-learning。
- 该话题在 GitHub 上共有 320 个仓库, 本站收录的是其中最热门的 20 个,不是全量列表。
- Star / Fork 每日自动刷新一次,实时数据以 GitHub 为准。
- 当前 20 个项目累计 1.8 万 Star,覆盖 3 种主要语言,数据更新于 2026-11-07。
- 中文介绍来自 GitHub 官方话题说明(github/explore)的机器翻译,可点「查看原文」对照;译文缺失时会先展示原文。