深度学习PyTorch库,用于时间序列预测、分类和异常检测(最初用于洪水预测)。
state-of-the-art-models 开源项目推荐(28 个)
state-of-the-art-models 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 28 个仓库按发布日期编排的最新 AI 突破精选列表,包含清晰的视频讲解、更深入文章的链接和代码
[ECCV2024] DualDn: Dual-domain Denoising via Differentiable ISP. • State-of-the-art for real-image denoising • Strong performance & generalization
[SOTA] [92% 准确率] 786M-8k-44L-32H 多乐器音乐 Transformer,具备真实的完整 MIDI 乐器音域、高效编码、八档力度(octo-velocity)与结尾(outro)token
ICML 2024, Official Implementation of "Cross-view Masked Diffusion Transformers for Person Image Synthesis."
This repository contains a curated collection of notebooks for implementing state-of-the-art multimodal Vision-Language Models (VLMs).
IEEE Transactions on Affective Computing, 2022
CAPTCHA project for Machine Learning Course https://arxiv.org/pdf/2006.11373.pdf
Researchers who published code, models (in some cases), and demo apps (in few cases) along with their SOTA paper
该项目在 GitHub 上没有填写描述
Binding affinity prediction for drug discovery
Official Repository for different models based on MultiHead VGAEs.
Image-Scene-Classification with 30 different classes.
The repository contains the project of Advanced Machine Learning: Visual Geolocalization: mapping images to GPS. It has been forked from the implementation of a SOTA paper. My team pushed it furher
Computer Vision: State of the Art model implementation using PyTorch framework.
MB-ORES: A Multi-Branch Object Reasoner for Visual Grounding in Remote Sensing
Contributions to ML tasks in the form of Tools, Videos , Notebooks, Apps and APIs
Models and examples built with TensorFlow.
ORON is a state-of-the-art Digital Assistant that is backed by Machine-Learning.
该项目在 GitHub 上没有填写描述
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/state-of-the-art-models。
- 该话题在 GitHub 上共有 28 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 4944 Star,覆盖 3 种主要语言,数据更新于 2026-11-13。
- 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。