TopDeepLearning
1.0.0
与深度学习相关的流行GitHub项目列表（由Stars排名）。
上次更新：2020.07.09
| 项目名称 | 星星 | 描述 |
|---|---|---|
| 张量 | 146K | 每个人的开源机器学习框架 |
| 凯拉斯 | 48.9k | 对人类的深度学习 |
| OPENCV | 46.1k | 开源计算机视觉库 |
| Pytorch | 40k | Python中的张量和动态神经网络具有强GPU加速度 |
| TensorFlow-餐具 | 38.1k | 初学者的TensorFlow教程和示例（支持TF V1和V2） |
| 特塞拉克 | 35.3k | Tesseract开源OCR引擎（主存储库） |
| face_recognition | 35.2k | 世界上最简单的面部识别API和命令行 |
| 脸部 | 31.4k | 所有人的DeepFakes软件 |
| 变压器 | 30.4k | “变形金刚：Pytorch和Tensorflow 2.0的最先进的自然语言处理”。 |
| 100天ML代码 | 29.1k | 100天的ML编码 |
| 朱莉娅 | 28.1k | 朱莉娅语言：一种新的技术计算方法。 |
| 金矿器 | 26.6k | ？掘金翻译计划，可能是世界最大最好的英译中技术社区，最懂读者和译者的翻译平台：： |
| 很棒的量表 | 26.6k | 可扩展，可靠和性能的大规模系统的模式 |
| 基础 | 24.5k | 用干净的代码，简化的数学和说明性视觉效果学习ML。 |
| 伯特 | 23.9k | BERT的TensorFlow代码和预训练的模型 |
| funnlp | 22.1k | （机器学习）nlp 面试中常考到的知识点和代码实现、 nlp4han：中文自然语言处理工具集（断句/分词/词性标注/组块/句法分析/语义分析/语义分析/ner/ner/n元语法/hmm/代词消解/情感分析/拼写检查、/xlm：face…face… |
| xgboost | 19.4k | 对于Python，R，Java，Scala，C ++等，可扩展，便携式和分布式梯度提升（GBDT，GBRT或GBM）库。在单个机器，Hadoop，Spark，Flink和DataFlow上运行 |
| 实时派遣 | 18.4k | 在5秒内克隆声音，以实时产生任意语音 |
| D2L-ZH | 17.9k | 《动手学深度学习》：面向中文读者、能运行、可讨论。英文版即伯克利“深度学习导论”教材。 |
| 敞开 | 17.8k | OpenPose：实时多人关键点检测库，用于身体，脸部，手和脚部估算 |
| coursera-ml-andrewngnotes | 17.7k | 吴恩达老师的机器学习课程个人笔记 |
| Deepfacelab | 17.3k | DeepFacelab是创建Deepfakes的领先软件。 |
| Pytorch-Tutearial | 17.3k | 深度学习研究人员的Pytorch教程 |
| mask_rcnn | 17.2k | 蒙版R-CNN用于对象检测和实例分割，并在tensorflow上进行分割 |
| Spacy | 16.8k | ？带有Python和Cython的工业强度自然语言处理（NLP） |
| NLP-Progress | 16.2k | 存储库跟踪自然语言处理的进度（NLP），包括数据集和最常见的NLP任务的当前最新设备。 |
| 100天ML代码 | 15.6k | 100天ML代码中文版 |
| CS-Video-Courses | 14.9k | 带视频讲座的计算机科学课程列表。 |
| 波函数崩溃 | 14.7k | 在量子力学的想法的帮助下，从一个示例中生成了位图和tilemap。 |
| 讲座 | 14.7k | 牛津深NLP 2017课程 |
| 加强学习 | 14.7k | 实施强化学习算法。 Python，OpenAi Gym，Tensorflow。练习和解决方案…… |
| PWC | 14.7k | 用代码的论文。由星星分类。每周更新。 |
| TensorFlow课程 | 14.6k | 张量流的简单且可用的教程 |
| 深史 | 14.4k | Baidu的DeepSpeech体系结构的张量实现 |
| 南瓜书 | 14k | （《机器学习》（西瓜书）公式推导解析，在线阅读地址：https：//datawhalechina.github.io/pumpkin-book |
| TFJS | 13.5k | WebGL加速了JavaScript库，用于培训和部署ML模型。 |
| 例子 | 13.5k | 围绕着视觉，文本，增强学习等的Pytorch的一组例子。 |
| 开放式 | 13.5k | 深层神经网络的面部识别。 |
| QIX | 13.3k | 机器学习，深度学习，postgresql，分布式系统，node.js，golang |
| 脾脏 | 12.7k | Deezer源分离库，包括预验证的模型。 |
| 维吉利奥 | 12.7k | 您的数据科学电子学习导师。 |
| nndl.github.io | 12.7k | 《神经网络与深度学习》神经网络和深度学习 |
| 屏幕截图 | 12.7k | 神经网络将设计模型转换为静态网站。 |
| pytorch-cyclegan and-pix2pix | 12.4k | pytorch中的图像到图像翻译 |
| Pytorch手册 | 11.9k | pytorch手册是一本开源的书籍，目标是帮助那些希望和使用pytorch进行深度学习开发和研究的朋友快速入门，其中包含的pytorch教程全部通过测试保证可以成功运行 |
| 枪 | 11.9k | 用于同步分散图数据的开源网络安全协议。 |
| 桨 | 11.8k | 平行分布式深度学习：来自工业实践的机器学习框架（『飞桨』核心框架，深度学习＆机器学习高性能单机、分布式训… |
| TensorFlow-ZH | 11.8k | tensorflow官方文档中文版 |
| darknet | 11.4k | YOLOV4-用于对象检测的神经网络（DarkNet的Windows和Linux版本） |
| Learnopencv | 11.4k | 学习OpenCV：C ++和Python示例 |
| 神经网络和深度学习 | 11.3k | 我的书“神经网络和深度学习”的代码样本 |
| Google-Research | 11.2k | Google研究 |
| Labelimg | 11.2k | ？labelimg是图像图像注释工具和标签对象边界框 |
| Gensim | 11k | 人类的主题建模 |
| pix2code | 10.9k | pix2code：从图形用户界面屏幕截图生成代码 |
| 面部 | 10.8k | 使用TensorFlow的面部识别 |
| 去染色 | 10.7k | 一个基于深度学习的项目，用于着色和恢复旧图像（以及视频！） |
| Python-Machine-Learning-Book | 10.7k | “ Python机器学习（第一版）”书籍代码存储库和信息资源 |
| Stanford-CS-229-Machine学习 | 10.6k | Stanford的CS 229机器学习的VIP备忘单 |
| mmdetection | 10.5k | OpenMMLAB检测工具箱和基准测试 |
| face-api.js | 10.4k | JavaScript API，用于浏览器和Nodejs中的面部检测和面部识别。 |
| 很棒的pytorch列表 | 10.4k | GitHub上有关Pytorch相关内容的综合列表，例如不同的模型，实现，助手库，T… |
| NSFW_DATA_SCRAPER | 10.2k | 为了培训NSFW图像分类器的目的，汇总脚本以汇总图像数据 |
| convnetjs | 10k | JavaScript中的深度学习。浏览器中的火车卷积神经网络（或普通网络）。 |
| 自行车 | 9.8k | 可以从绘画中生成照片，将马变成斑马，执行样式转移等的软件。 |
| 简化 | 9.8k | 简化 - 在Python中构建数据应用的最快方法 |
| deepcreampy | 9.7k | 通过深神网络进行衰减 |
| Stylegan | 9.7k | StyleGan-官方张量实现 |
| 潜水式dl-pytorch | 9.6k | 本项目将《动手学深度学习》（深入学习）原书中的mxnet实现改为pytorch实现。 |
| Stanford-Tensorflow-Tutearials | 9.6k | 该存储库包含斯坦福课程的代码示例：深度学习研究的张量。 |
| Horovod | 9.6k | Tensorflow，Keras，Pytorch和Apache MXNET的分布式培训框架。 |
| 深度学习带有浓度的书籍 | 9.4k | 深度学习入门开源书，基于TensorFlow 2.0框架，tensorflow 2.0案例实战。开放源深度学习书籍。 |
| 神经食用食品 | 9.4k | 将您的两位数涂鸦变成具有深层神经网络的美术作品，从照片中产生无缝的纹理，从一个图像转移到另一个图像，执行基于示例的升级，但是等等...还有更多！ （语义样式转移的实现。） |
| 凯尔 | 9.3k | 内容意识到图像大小库 |
| 快速转移 | 9.2k | 快速风格转移的TensorFlow CNN ？？？ |
| NCNN | 9.2k | NCNN是针对移动平台优化的高性能神经网络推理框架 |
| kubeflow | 9.1k | Kubernetes的机器学习工具包 |
| NLTK | 9k | NLTK源 |
| 天赋 | 9k | 最先进的自然语言处理（NLP）的非常简单的框架 |
| ML代理 | 9k | 统一机器学习代理工具包 |
| Allennlp | 8.8k | 开源NLP研究库，建于Pytorch。 |
| botpress | 8.8k | ？具有内置语言理解（NLU），精美的图形接口和对话框（DM）的对话平台。轻松创建聊天机器人和基于AI的虚拟助手。 |
| gan-zoo | 8.7k | 所有名字甘斯的清单！ |
| 有效的语音流 | 8.6k | Tensorflow教程和最佳实践。 |
| TFJS核 | 8.5k | WebGL加速ML // javaScript的线性代数//自动差异化。 |
| Fairseq | 8.4k | Facebook AI研究顺序到序列工具包用Python编写。 |
| 十四行诗 | 8.4k | 基于张量流的神经网络库 |
| 麻省理工学院 - 深度学习书籍pdf | 8.3k | MIT深度学习书籍以PDF格式（完整和零件），伊恩·古德法洛（Ian Goodfellow），Yoshua Bengio和Aaron Courville |
| TensorFlow-Tutorials | 8.3k | 带有YouTube视频的TensorFlow教程 |
| pytorch_ geometric | 8.2k | Pytorch的几何深度学习扩展库 |
| 教程 | 8.2k | 机器学习相关教程 |
| 时尚狂热 | 8k | 类似MNIST的时尚产品数据库。基准 |
| Bert-As-Service | 7.9k | 使用BERT模型将可变长度的句子映射到固定长度的载体 |
| PIX2PIX | 7.8k | 带有条件对抗网的图像到图像翻译 |
| Mediapipe | 7.7k | MediaPipe是研究人员和开发人员为移动，边缘，云和网络构建世界一流的ML解决方案和应用程序的最简单方法。 |
| 推荐人 | 7.7k | 推荐系统的最佳实践 |
| 麻省理工学院 - 深度学习 | 7.7k | MIT深度学习与课程的教程，作业和竞赛。 |
| Pytorch-Book | 7.6k | Pytorch教程和有趣的项目，包括神经谈话，神经风格，诗作，动漫一代（《深度学习框架 pytorch：入门与实战》） |
| 风 | 7.6k | 由GetTream.io提供动力的美丽开源RSS和播客应用 |
| vid2vid | 7.4k | 我们的高分辨率方法（例如2048x1024）的Pytorch实现了逼真的视频与视频翻译。 |
| Learn_machine_learning_in_3_months | 7.3k | 这是Siraj Raval在YouTube上的“ 3个月内学习机器学习”的代码 |
| 古勒恩 | 7.3k | GO的机器学习 |
| Keras-Gan | 7.2k | KERAS的生成对抗网络的实现。 |
| mlcourse.ai | 7k | 开放机器学习课程 |
| 地面 | 7k | 一款入门级的人脸、视频、文字检测以及识别的项目。 |
| PYSC2 | 6.9k | Starcraft II学习环境 |
| 预审计的模型.pytorch | 6.9k | 预估计的pytorch：nasnet，resnext，resnet，inceptionv4，inceptionResnetv2，xception，dpn，等等。 |
| pytorch-gan | 6.7k | 生成对抗网络的Pytorch实现。 |
| 想象 | 6.7k | 数据集，转换和特定于计算机视觉的模型 |
| NLP教程 | 6.6k | 深度学习研究人员的自然语言处理教程 |
| 子弹3 | 6.6k | Bullet Physics SDK：VR，游戏，视觉效果，机器人技术的实时碰撞检测和多物理模拟 |
| dcgan-tensorflow | 6.6k | “深度卷积生成对抗网络”的张量实现 |
| TFJS模型 | 6.5k | 预处理的TensorFlow.js模型 |
| 阿布 | 6.5k | 阿布量化交易系统（股票，期权，期货，比特币 |
| pytorch灯 | 6.5k | ML研究人员的轻量级Pytorch包装纸。扩展您的模型。少写样板 |
| TensorboardX | 6.4k | Pytorch的张板（以及Chainer，Mxnet，Numpy，...） |
| 机器学习课程 | 6.4k | 使用Python的机器学习课程： |
| 猜测 | 6.3k | ？用于启用机器学习驱动用户体验的库和工具 |
| pyro | 6.3k | 与Python和Pytorch的深度通用概率编程 |
| 实验室 | 6.2k | 用于基于代理的AI研究的可自定义的3D平台 |
| mml-book.github.io | 6.2k | 伴侣网页，“机器学习数学”一书 |
| 面试 | 6.2k | 访谈=简历指南 + leetcode + kaggle |
| Tensorlayer | 6.2k | 深入学习和强化学习库，用于科学家和工程师 |
| 生成模型 | 6.1k | 收集生成模型的收集，例如gan，pytorch和Tensorflow中的vae。 |
| 机器学习年度CN | 6.1k | 机器学习向往 - 《机器学习训练秘籍》- 《机器学习训练秘籍》 -Andrew ng着 |
| Keras-Yolo3 | 6k | Yolov3的KERAS实现（TensorFlow Backend） |
| 老板 | 5.9k | 老板接近时隐藏屏幕。 |
| tensorflow2_tutorials_chinese | 5.9k | tensorflow2中文教程，持续更新（当前版本：tensorflow2.0），标签：tensorflow 2.0教程 |
| TensorFlow-Tutorials | 5.9k | 使用Google的TensorFlow框架的简单教程 |
| Argo | 5.9k | Argo Workflows：使用Kubernetes完成工作。 |
| Python-Machine-Learning-Book-2nd-Edition | 5.8k | “ Python机器学习（第二版）”书籍代码存储库和信息资源 |
| DVC | 5.7k | ？数据版本控制 |
| Easypr | 5.7k | 在不受约束的情况下，对于中国许可证的一个简单，灵活且准确的板块识别项目。 |
| Aversarialnetspaper | 5.6k | 带有有关生成对抗网的代码的经典纸张列表 |
| Tensorpack | 5.6k | Tensorflow上的神经网训练接口，重点介绍速度 +灵活性 |
| 光特性 | 5.6k | 由GO和Google Tensorflow提供动力的个人照片管理 |
| tensorflow_cookbook | 5.6k | Tensorflow Machine学习食谱的代码 |
| 符号 | 5.6k | 快速图像增强库，易于使用其他库周围的包装器 |
| 迅速 | 5.6k | 快速进行张量 |
| 暗流 | 5.6k | 将darknet转换为张量。负载训练有素的重量，使用TensorFlow进行重新训练/微调，导出恒定图形DEF到移动设备 |
| tensorflow_tutorials | 5.5k | 从基础到TensorFlow的更有趣的应用 |
| 深度学习环境 | 5.5k | Andrew Ng在Coursera上的深度学习专业化。 |
| 转移学习 | 5.5k | 有关转移学习和域适应的一切 - 迁移学习 |
| ML-NLP | 5.5k | 此项目是机器学习（机器学习）、深度学习（深度学习），nlp面试中常考到的知识点和代码实现，也是作为一个算法工程师必会的理论基础知识。，也是作为一个算法工程师必会的理论基础知识。 |
| NMT | 5.5k | 张量流神经机器翻译教程 |
| 更快的rcnn.pytorch | 5.5k | 更快的pytorch实现速度更快的R-CNN |
| ugatit | 5.4k | U-GAT-IT的官方TensorFlow实现：无监督的生成注意网络，具有自适应层 - 在... |
| 熊猫pro养 | 5.4k | 从pandas dataframe对象创建HTML分析报告 |
| 深层网络 | 5.4k | 图像识别的深度残留学习 |
| xlnet | 5.3k | XLNET：通用自动回报预处理以了解语言理解 |
| leeml notes | 5.2k | 李宏毅《机器学习》笔记，在线阅读地址：https：//datawhalechina.github.io/leeml-notes |
| wav2letter | 5.2k | Facebook AI研究的自动语音识别工具包 |
| 神经风格 | 5.2k | TensorFlow中的神经风格！ ？ |
| CVPR2020纸质代码解释 | 5.2k | CVPR2020/CVPR2019／CVPR2018/CVPR2017论文，极市团队整理 |
| TensorFlow-2.x-Tutorials | 5.2k | Tensorflow 2.x版本的教程和示例，包括CNN，RNN，GAN，AUTO-编码器，Fasterrcnn，GPT，Bert Exippl… |
| Yolov3 | 5.2k | yolov3在pytorch> onnx> coreml> ios中 |
| CNN-Text-Classification-TF | 5.2k | 卷积神经网络用于张量的文本分类 |
| seq2seq | 5.2k | TensorFlow的通用编码器框架 |
| Chineseocr_lite | 5.1k | 超轻量级中文ocr，支持竖排文字识别，支持ncnn推理，dbnet（1.7m） + crnn（6.3m） + anglenet（1.5m）总模型仅10m |
| 特色 | 5k | 用于自动化功能工程的开源Python库 |
| 标签 | 5k | 图像多边形注释（多边形，矩形，圆，线，点，点和图像级标志注释）。 |
| 成像 | 5k | python库构建，旨在使开发人员能够构建具有独立计算机视觉功能的应用程序和系统 |
| NLP重型 | 5k | 自然语言处理最佳实践和示例 |
| 拥有福音 - 手机学习 | 4.9k | 通过神经网络的机器学习和图像分类的绝对初学者指南 |
| eat_tensorflow2_in_30_days | 4.9k | tensorflow2.0 ??很美味，只吃！ ？ |
| TensorFlow-Wavenet | 4.9k | DeepMind的Wavenet纸的张量实现 |
| Pytorch-Tutearial | 4.9k | 轻松快捷地构建您的神经网络 |
| stylegan2 | 4.9k | stylegan2-官方张量集实现 |
| H2O-3 | 4.9k | 开源快速可扩展的机器学习平台，用于智能应用程序：深度学习，梯度提升和XGBO… |
| 很棒的机器源代码编码 | 4.8K | 与源代码应用的机器学习有关的酷链接和研究论文（mloncode） |
| 学习到黑暗 | 4.8K | 学会在黑暗中看到。 CVPR 2018 |
| Pytorch-Yolov3 | 4.8K | Yolov3的最小Pytorch实施 |
| 一阶模型 | 4.8K | 该存储库包含图像动画的纸张一阶运动模型的源代码 |
| 型号 | 4.8K | 预先训练和再现了深度学习模型（『飞桨』官方模型库，包含多种学术前沿和工业场景验证的深度学习模型） |
| 微笑 | 4.8K | 统计机器智能与学习引擎 |
| keras-js | 4.7k | 在浏览器中运行KERAS模型，并使用WebGL支持GPU支持 |
| 卡拉 | 4.7k | 用于自动驾驶研究的开源模拟器。 |
| keras-rl | 4.7k | 针对凯拉斯的深度加强学习。 |
| 有用的java-links | 4.7k | 有用的Java框架，库，软件和Hello Worlds示例的列表 |
| 很棒的coreml模型 | 4.7k | 核心ML的最大型号列表（iOS 11+） |
| Python-small-evarmples | 4.7k | 告别枯燥，致力于打造python 富有体系且实用的小例子、小案例。 |
| GCN | 4.7k | 在TensorFlow中实现图形卷积网络 |
| 简介_to_ml_with_python | 4.7k | “用python的机器学习简介”的笔记本和代码 |
| Stargan | 4.6k | Stargan-官方Pytorch实施（CVPR 2018） |
| pix2pixhd | 4.6k | 综合和操纵2048x1024图像有条件gan |
| 数据科学wiki | 4.6k | DataScience，统计，数学，R，Python，AI，机器学习，自动化，DevOps工具，Bash，Linux Tutor… |
| mvision | 4.6k | 机器人视觉机器人视觉vs-slam orb-slam2 y yolov3行为检测opencv pcl机器学习机器学习 |
| 聪明的人 | 4.6k | 一个对抗性示例库，用于构建攻击，建筑防御和基准测试 |
| VAEX | 4.6k | Python，ML，可视化和探索大型表格数据以每秒十亿行可视化和探索大型表格数据框 |
| 深入学习 | 4.6k | 该存储库伴随着“ Grokking深度学习”一书 |
| trax | 4.5k | Trax - 清晰的代码和速度深度学习 |
| graph_nets | 4.5k | 在TensorFlow中构建图形网 |
| 爱德华 | 4.5k | Tensorflow中的概率编程语言。深层生成模型，变异推断。 |
| TensorFlow-World | 4.5k | ？张量流的简单且可用的教程 |
| 不平衡的学习 | 4.5k | 一个python包，以应对机器学习中不平衡数据集的诅咒 |
| 机器学习示意图 | 4.5k | 思维图总结了机器学习概念，从数据分析到深度学习。 |
| seq2seq-couplet | 4.5k | 使用SEQ2SEQ模型播放对联。 用深度学习对对联。 |
| 效率网络 | 4.4k | pytorch实施有效网络 |
| TensorFlow-Book | 4.4k | 伴随使用TensorFlow的机器学习的源代码。请参阅本书以进行分步解释。 |
| Stanza | 4.4k | 斯坦福官方NLP Python图书馆，用于许多人类语言 |
| Amazon-DSSTNE | 4.4k | 深度可扩展的稀疏张量网络引擎（DSSTNE）是一个亚马逊开发的图书馆，用于建造深度学习（DL）MA… |
| CNN-解释器 | 4.4k | 学习具有交互式可视化的卷积神经网络。 |
| REALTIME_MULTI-PERSON_POSE_ESTIMATION | 4.4k | CVPR'17（口头）中实时多人姿势估计的代码回购 |
| Stanford-CS-230深度学习 | 4.3k | 斯坦福大学CS 230深度学习的VIP作弊表 |
| 实时人驱动 | 4.3k | 使用tensorflow.js在网络浏览器中实时删除复杂背景的人 |
| OpenNMT-PY | 4.3k | pytorch中的开源神经机器翻译 |
| tensorflow_practice | 4.3k | TensorFlow实战练习，包括强化学习、推荐系统、 nlp等 |
| Pytorch-CNN-Visualization | 4.2k | 卷积神经网络可视化技术的Pytorch实施 |
| 张力空间 | 4.2k | 神经网络3D可视化框架，在浏览器中构建交互式和直观的模型，支持预先训练的深度… |
| 深度学习示例 | 4.2k | 深度学习的例子 |
| 草图代码 | 4.2k | KERAS模型从手绘网站模型中生成HTML代码。将图像字幕架构实现为DRA… |
| 深度学习的模子 | 4.2k | 有关深度学习研究论文的摘要和注释 |
| 顶点 | 4.2k | pytorch扩展：用于Pytorch的易于混合精度和分布式培训的工具 |
| 字母 | 4.1k | 实时准确的多人姿势估计和跟踪系统 |
| 注意所有您需要的Pytorch | 4.1k | “注意就是您所需要的”中变压器模型的Pytorch实现。 |
| nmap | 4.1k | NMAP-网络映射器。官方SVN存储库的GitHub镜子。 |
| 机器学习学习音符 | 4.1k | 周志华《机器学习》又称西瓜书是一本较为全面的书籍，书中详细介绍了机器学习领域不同类型的算法（例如：监督学习、无监督学习、半监督学习、强化学习、集成降维、特征选择等），记录了本人在学习过程中的理解思路与扩展知识点，希望对新人阅读西瓜书有… |
| Serenata-de-amor | 4.1k | ？公共管理社会控制的人工智能 |
| 实用pytorch | 4.1k | 弃用且未维护 - 请参阅https://github.com/pytorch/tutorials的官方回购 |
| Pytorch-image模型 | 4.1k | Pytorch映像模型，脚本，预处理的重量 - （SE）RESNET/RESNET，DPN，EFIDENDNET，MIXENET，MOBILENET-V3/V2，MNASNET，MNASNET，SINSE-PATH NAS，FBNET等 |
| 面对面 | 4K | 使用Pytorch的2D和3D脸对齐库构建 |
| 学习对学习 | 4K | 学习在TensorFlow中学习 |
| 机器学习音符 | 4K | 我不断更新的机器学习，概率模型以及深度学习笔记和演示（1500多个幻灯片）我不间断更… |
| UMAP | 4K | 统一的歧管近似和投影 |
| 深度学习介子 | 4K | Tensorflow基本教程实验室 |
| Gluon-CV | 4K | Gluon CV工具包 |
| 管道 | 4K | Pipelineai kubeflow分布 |
| 浮潜 | 4K | 一个用于快速生成培训数据的系统，以较弱的监督 |
| 数字 | 4K | 深度学习GPU培训系统 |
| Densenet | 4K | CVPR 2017（最佳纸张奖），密集连接的卷积网络。 |
| 很棒的项目 | 4K | 精心策划的机器学习清单，NLP，视觉，推荐系统项目想法 |
| 教程 | 4K | Pytorch教程。 |
| 深度学习-21例 | 3.9k | 《21个项目玩转深度学习-——基于tensorflow 的实践详解》配套代码 |
| 深度学习学历 | 3.9k | 深度学习教程注释和代码。有关更多信息，请参见Wiki。 |
| textgenrnn | 3.9k | 在任何文本数据集上都可以轻松训练您自己的文本生成的神经网络，该网络具有几行... |
| 清醒 | 3.8k | 用于神经网络可解释性研究的基础架构和工具的集合。 |
| NSFWJS | 3.8k | 通过TensorFlow.js在客户端检测NSFW |
| SSD.Pytorch | 3.8k | 单镜头多贝克斯检测器的Pytorch实现 |
| 机械学习 | 3.8k | 基本的机器学习和深度学习 |
| TensorFlow-Tutorial | 3.8k | 从基本到硬的TensorFlow教程 |
| 令人敬畏的ml-for-cybersecurity | 3.8k | 网络安全的机器学习 |
| 日常纸计算机视频 | 3.8k | 记录每天整理的计算机视觉/深度学习/机器学习相关方向的论文 |
| SSD-TensorFlow | 3.8k | TensorFlow中的单镜头多伯克斯检测器 |
| CVAT | 3.8k | 强大而有效的计算机视觉注释工具（CVAT） |
| 深度学习路 | 3.8k | ？关于深度学习，您需要了解的一切 |
| SQLFlow | 3.8k | 将SQL和AI带到一起。 |
| MMF | 3.7k | Facebook AI研究（公平）的视觉和语言多模式研究的模块化框架 |
| TensorFlow-Docs | 3.7k | TensorFlow最新官方文档中文版 |
| 伊根 | 3.7k | 通过生成对抗网络生成交互式图像 |
| capsnet-tensorflow | 3.7k | 胶囊之间的纸质动态路由中的capsnet（胶囊网）的张量实现 |
| 迄今为止效率的det-pytorch | 3.6k | 官方有效的官方效率重新实现，并实时进行SOTA性能和预算的重量。 |
| pytorch-evarmples | 3.6k | 简单的示例来介绍pytorch |
| ml_for_hackers | 3.6k | “黑客机器学习”一书附带的代码 |
| 文档 | 3.6k | TensorFlow文档 |
| Tensorflow基因建模收集 | 3.6k | 张量集的生成模型的收集 |
| 深度学习 | 3.6k | 该存储库包含我的个人笔记和摘要。我很喜欢…… |
| Bert-Pytorch | 3.6k | Google AI 2018 Bert Pytorch实施 |
| pwnagotchi | 3.5k | （⌐■_■） - wifi pwning的深钢筋学习仪器更好。 |
| Hyperlpr | 3.5k | 基于深度学习高性能中文车牌识别高性能中国车牌识别框架。 |
| 深度学习 | 3.5k | 深度学习Nanodegree基础计划的存储库。 |
| TensorFlowonSpark | 3.5k | TensorFlowonSpark将张量程序程序带到Apache Spark簇。 |
| Bigdl | 3.5k | BigDL：Apache Spark的分布式深度学习框架 |
| Algowiki | 3.5k | 存储库，其中包含有关计算机科学不同主题的链接和资源。 |
| 例子 | 3.5k | TensorFlow示例 |
| TF-FASTER-RCNN | 3.4k | 张量子流更快的RCNN用于对象检测 |
| TF置端 | 3.4k | 使用TensorFlow和自定义体系结构进行快速推理实施的深度姿势估计。 |
| 很棒的机器学习CN | 3.4k | 机器学习资源大全中文版，包括机器学习领域的框架、库以及软件 |
| 元流 | 3.4k | 轻松构建和管理现实生活中的数据科学项目。 |
| 深入的学习 | 3.3k | 深钢筋学习纳米模板程序的回购 |
| 语义细分式 - 托尔奇 | 3.3k | 在MIT ADE20K数据集上用于语义细分/场景的Pytorch实现 |
| GOCV | 3.3k | 使用OpENCV 4及以后的计算机视觉包装。 |
| D2L-Pytorch | 3.3k | 该项目将本书重现为深度学习（www.d2l.ai），将代码从MXNET调整为Pytorch。 |
| 中文 - 伯特wm | 3.3k | 用整个单词掩盖的中文bert （中文 bert-wwm（（（（bert-wm系列模型））的预训练 |
| SmartCropper | 3.3k | 以智能方式裁剪图像的库，可以识别边界并纠正裁剪图像。 智能图片裁剪框架。自动识别边框，手动调节选区，使用透视变换裁剪并矫正选区；适用于身份证，名片，文档等照片的裁剪。，文档等照片的裁剪。 |
| Pytorchzerotoall | 3.3k | 简单的pytorch教程零！ |
| Pyaudioanalysis | 3.3k | Python音频分析库：特征提取，分类，分割和应用程序 |
| Dixplyablemlbook | 3.3k | 《可解释的机器学习- 黑盒模型可解释性理解指南》，该书为《，该书为《可解释的机器学习》中文版 |
| swips-nlu | 3.3k | 剪切python库从文本中提取含义 |
| pyod | 3.3k | 可扩展离群检测的Python工具箱（异常检测） |
| 深度学习 | 3.2k | 深度学习入门教程，优秀文章，深度学习教程 |
| Vespa | 3.2k | VESPA是用于大型数据集的低延迟计算的引擎。 |
| 深度转换 | 3.2k | 深度神经网络，用于语音转换（语音样式传输） |
| Lightfm | 3.2k | python实施LightFM，一种混合建议算法。 |
| 机器学习 | 3.2k | Udacity的机器学习课程的内容 |
| Skflow | 3.2k | 张量流的简化界面（模仿Scikit学习） |
| TensorFlow-Project-Template | 3.2k | Tensorflow项目模板体系结构的最佳实践。 |
| Easyocr | 3.2k | 可用的40多种语言的现成OCR，包括中文，日语，韩语和泰语 |
| 文本分类-CNN-RNN | 3.1k | CNN-RNN中文文本分类，tensorflow |
| MachineLearning_Python | 3.1k | python实现 |
| 成像 | 3.1k | ？查找重复的图像很容易！ |
| Matchzoo | 3.1k | 促进深文匹配模型的设计，比较和共享。 |
| 变压器 | 3.1k | 变压器的张量实现：注意是您需要的 |
| tensorflow_poems | 3.1k | 中文古诗自动作诗机器人，屌炸天，基于tensorflow1.10 api，正在积极维护升级中 |
| 深度学习路 | 3.1k | ？为深度学习研究人员和开发人员有组织的资源 |
| 标签studio | 3.1k | 标签工作室是具有标准化输出格式的多型数据标签和注释工具 |
| ASRT_SpeechRevention | 3.1k | 基于深度学习的中国语音识别系统基于深度学习的中文语音识别系统 |
| Benchmark_results | 3.1k | 视觉跟踪纸列表 |
| 机器学习 | 3k | python3）：knn 、决策树、贝叶斯、逻辑回归、 svm 、线性回归、树回归 |
| yolact | 3k | 实时实例分割的简单，完全卷积的模型。 |
| trfl | 3k | Tensorflow增强学习 |
| pytorch-cifar | 3k | pytorch的CIFAR10上的95.16％ |
| 神圣 | 3k | 神圣是一种工具，可以帮助您在IDSIA开发，组织，日志和复制实验。 |
| Yolov5 | 3k | yolov5在pytorch> onnx> coreml> ios中 |
| 加强学习 | 3k | 在60天内学习深入的增强学习！ Python的讲座和代码。强化学习 +深度学习 |
| 蒸馏器 | 3k | Intel AI实验室的神经网络蒸馏器：用于神经网络压缩研究的Python软件包。 https：//神经... |
| FastMaskRcnn | 3k | tensorflow中的蒙版rcnn |
| 可能性 | 3k | 概率推理和统计分析 |
| DeepVideoAnalytics | 2.9k | 分布式视觉搜索和视觉数据分析平台。 |
| TensorWatch | 2.9k | 调试，监视和可视化Python机器学习和数据科学 |
| 飞镖 | 2.9k | 可区分的架构搜索卷积和经常性网络 |
| ComputerVision-Recipes | 2.9k | 用于计算机视觉的最佳实践，代码样本和文档。 |
| 文本检测-CTPN | 2.9k | 文本检测主要基于TensorFlow，ID卡检测，连接师文本建议网络的CTPN模型 |
| TensorFlow-Windows-wheel | 2.9k | TensorFlow预构建的Windows二进制 |
| TensorFlow-Yolov3 | 2.9k | pure tensorflow的Yolov3实现，并支持训练您自己的数据集 |
| Zhihu | 2.9k | 此存储库包含我的个人列（https://zhuanlan.zhihu.com/zhaoyeyu）中的源代码，该源代码使用Python 3.6实施。包括自然语言处理和计算机视觉项目，例如文本生成，机器翻译，深度卷积GAN和其他实际战斗代码。 |
| BERT-BILSTM-CRF-NER | 2.9k | 使用BILSTM-CRF模型的NER任务解决方案与Google Bert微调和专用服务器服务 |
| TensorFlowSharp | 2.9k | .NET语言的TensorFlow API |
| 点燃 | 2.9k | 高级图书馆，可帮助培训和评估Pytorch中的神经网络。 |
| TensorFlow-Tutorial | 2.9k | 示例TensorFlow代码和Caicloud TensorFlow作为服务开发环境。 |
| 100天ML代码 - 中国跨 | 2.9k | 机器学习信息图表中文翻译 |
| 深度学习的PAPER-翻译 | 2.9k | 深度学习论文翻译，包括分类论文，检测论文等 |
| DMTK | 2.8k | 微软分布式机器学习工具包 |
| caffe-tensorflow | 2.8k | tensorflow中的CAFFE模型 |
| libpostal | 2.8k | AC图书馆在世界各地进行解析/归一化街道地址。由统计NLP和开放地理数据提供支持。 |
| Pigo | 2.8k | 纯GO面部检测，学生/眼睛本地化和面部标志点检测库 |
| MINDSDB | 2.8k | 一行代码中的机器学习 |
| Tensorflow-cookbook | 2.8k | 简单的TensorFlow食谱，可易于使用 |
| 易于浓度 | 2.8k | TensorFlow中的简单而全面的教程 |
| 深度学习 | 2.8k | 深度学习（Python，C，C ++，Java，Scala，Go） |
| Pytorch-Yolo-V3 | 2.8k | Yolo V3对象检测算法的Pytorch实现 |
| 自动点唱机 | 2.8k | 纸上的代码“自动点唱机：音乐的生成模型” |
| makegirlsmoe_web | 2.8k | 使用MakeGirlSmoe创建动漫角色 |
| 深度学习 - keras-tensorflow | 2.8k | 深度神经网络的简介与Keras和TensorFlow |
| 暹罗 | 2.7k | [CVPR2019]快速在线对象跟踪和细分：一种统一的方法 |
| 腾讯-ML图像 | 2.7k | 最大的多标签图像数据库； RESNET-101模型； Imagenet上的80.73％Top-1 ACC |
| 达利 | 2.7k | 包含高度优化的构件和执行引擎的库，用于在Deep Le中进行数据预处理… |
| Shogun | 2.7k | shōgun |
| Optuna | 2.7k | 超参数优化框架 |
| automatic_speech_recognition | 2.7k | tensorflow中Madarian和英语的端到端自动语音识别 |
| pytorch-semseg | 2.7k | pytorch实现的语义分割体系结构 |
| pygcn | 2.7k | Pytorch中的图形卷积网络 |
| 深度学习书 | 2.7k | “人工神经网络和深度学习介绍的存储库：一项实用指南，其应用 |
| 点网 | 2.7k | PointNet：3D分类和细分的点集深度学习 |
| CVPR2020代码 | 2.7k | CVPR 2020论文开源项目合集 |
| 检测 | 2.7k | 检测器的Pytorch实现。两者都是从头开始的训练和直接从验证的检测中推断的我们… |
| LSTM-Human-Activity-Reckention | 2.6k | 人类活动识别示例使用智能手机传感器数据集上的TensorFlow和LSTM RNN。分类六个活动类别中的运动类型-Guillaume Chevalier |
| 神经风格-TF | 2.6k | Tensorflow（Python API）神经风格的实现 |
| Pytorch-Unet | 2.6k | U-NET的Pytorch实现用于图像语义分割的高质量图像 |
| 科尼亚 | 2.6k | Pytorch的开源可区分计算机视觉库 |
| 广告纸 | 2.6k | 计算广告论文 |
| 深度分辨率网型 | 2.6k | 该项目是我们CVPR2019论文的正式实施，“嗡嗡作响的深层高分辨率表示学习…… |
| Vott | 2.6k | 可视化对象标记工具：用于从图像和视频构建最终对象检测模型的电子应用程序。 |
| ESPNET | 2.6k | 端到端语音处理工具包 |
| LTP | 2.6k | 语言技术平台 |
| Learn_deep_learning_in_6_weeks | 2.6k | 这是Siraj Raval在YouTube上的“在6周内学习深度学习”的课程 |
| Keras-Vis | 2.6k | Keras的神经网络可视化工具包 |
| Onnxruntime | 2.6k | ONNX运行时：跨平台，高性能ML推断和训练加速器 |
| 3DDFA | 2.6k | Pytorch改进的TPAMI 2017论文：全姿势范围的面部对齐方式：3D总解决方案。 |
| 奥利维亚 | 2.6k | ♀️您的新最好的朋友由人工神经网络提供动力 |
| Albert_zh | 2.6k | 一个用于自我监督语言表征的学习的精简版，海量中文预训练阿尔伯特模型 |
| AI-Deadlines | 2.6k | ⏰AI会议截止日期倒计时 |
| OPENCVSHARP | 2.5k | .NET框架包装器openCV |
| 电报列表 | 2.5k | List of telegram groups, channels & bots // Список интересных групп, каналов и ботов телеграма // Список чатов для программистов |
| easy12306 | 2.5k | 使用机器学习算法完成对12306验证码的自动识别 |
| 锈 | 2.5k | Rust language bindings for TensorFlow |
| miles-deep | 2.5k | Deep Learning Porn Video Classifier/Editor with Caffe |
| VisualDL | 2.5k | Deep Learning Visualization Toolkit（『飞桨』深度学习可视化工具 ） |
| SinGAN | 2.5k | Official pytorch implementation of the paper: "SinGAN: Learning a Generative Model from a Single Natural Image" |
| t81_558_deep_learning | 2.5k | Washington University (in St. Louis) Course T81-558: Applications of Deep Neural Networks |
| 训练 | 2.5k | ？ Custom Object Detection and Classification Training |
| PocketFlow | 2.5k | An Automatic Model Compression (AutoMC) framework for developing smaller and faster AI applications. |
| autogluon | 2.5k | AutoGluon: AutoML Toolkit for Deep Learning |
| simple-faster-rcnn-pytorch | 2.5k | A simplified implemention of Faster R-CNN that replicate performance from origin paper |
| MITIE | 2.5k | MITIE: library and tools for information extraction |
| reinforcement-learning | 2.5k | Minimal and Clean Reinforcement Learning Examples |
| ISLR-python | 2.4k | An Introduction to Statistical Learning (James, Witten, Hastie, Tibshirani, 2013): Python code |
| 东方 | 2.4k | A tensorflow implementation of EAST text detector |
| DeepNLP-models-Pytorch | 2.4k | Pytorch implementations of various Deep NLP models in cs-224n(Stanford Univ) |
| Machine-Learning-with-Python | 2.4k | Python code for common Machine Learning Algorithms |
| stanford_dl_ex | 2.4k | Programming exercises for the Stanford Unsupervised Feature Learning and Deep Learning Tutorial |
| tensorflow-internals | 2.4k | It is open source ebook about TensorFlow kernel and implementation mechanism. |
| DeepLearning | 2.4k | Python for《Deep Learning》，该书为《深度学习》(花书) 数学推导、原理剖析与源码级别代码实现 |
| 文本 | 2.4k | Data loaders and abstractions for text and NLP |
| ALAE | 2.4k | [CVPR2020] Adversarial Latent Autoencoders |
| pytorch-summary | 2.4k | Model summary in PyTorch similar to model.summary() in Keras |
| pytorch-doc-zh | 2.4k | Pytorch 中文文档 |
| Deep_reinforcement_learning_Course | 2.4k | Implementations from the free course Deep Reinforcement Learning with Tensorflow |
| ML-Tutorial-Experiment | 2.4k | Coding the Machine Learning Tutorial for Learning to Learn |
| pytorch-Deep-Learning | 2.4k | Deep Learning (with PyTorch) |
| 型号 | 2.4k | A collection of pre-trained, state-of-the-art models in the ONNX format |
| 书 | 2.4k | Deep Learning 101 with PaddlePaddle （『飞桨』深度学习框架入门教程） |
| PyTorch_Tutorial | 2.4k | 《Pytorch模型训练实用教程》中配套代码 |
| Dive-into-DL-TensorFlow2.0 | 2.4k | 本项目将《动手学深度学习》(Dive into Deep Learning)原书中的MXNet实现改为TensorFlow 2.0实现，项目已得到李沐老师的同意 |
| Artificial-Intelligence-Deep-Learning-Machine-Learning-Tutorials | 2.4k | A comprehensive list of Deep Learning / Artificial Intelligence and Machine Learning tutorials - rapidly expanding in… |
| segmentation_models | 2.4k | Segmentation models with pretrained backbones. Keras and TensorFlow Keras. |
| Awesome-PyTorch-Chinese | 2.3k | 【干货】史上最全的PyTorch学习资源汇总 |
| Flux.jl | 2.3k | 放松！ Flux is the ML library that doesn't make you tensor |
| 焊接 | 2.3k | High-performance runtime for data analytics applications |
| PyTorch-BigGraph | 2.3k | Generate embeddings from large-scale graph-structured data. |
| byteps | 2.3k | A high performance and generic framework for distributed DNN training |
| AI-Job-Notes | 2.3k | AI算法岗求职攻略（涵盖准备攻略、刷题指南、内推和AI公司清单等资料） |
| luminoth | 2.3k | |
| Alink | 2.3k | Alink is the Machine Learning algorithm platform based on Flink, developed by the PAI team of Alibaba computing platf… |
| introtodeeplearning | 2.3k | Lab Materials for MIT 6.S191: Introduction to Deep Learning |
| TensorFlow-and-DeepLearning-Tutorial | 2.3k | A TensorFlow & Deep Learning online course I taught in 2016 |
| srgan | 2.3k | Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network |
| colorization | 2.3k | Automatic colorization using deep neural networks. "Colorful Image Colorization." In ECCV, 2016. |
| OpenNMT | 2.3k | Open Source Neural Machine Translation in Torch (deprecated) |
| Super-SloMo | 2.3k | PyTorch implementation of Super SloMo by Jiang et al. |
| orange3 | 2.3k | ？ Orange: Interactive data analysis https://orange.biolab.si |
| ENAS-pytorch | 2.3k | PyTorch implementation of "Efficient Neural Architecture Search via Parameters Sharing" |
| 3D-ResNets-PyTorch | 2.3k | 3D ResNets for Action Recognition (CVPR 2018) |
| 石榴 | 2.3k | Fast, flexible and easy to use probabilistic modelling in Python. |
| Faster-RCNN_TF | 2.3k | Faster-RCNN in Tensorflow |
| datascience | 2.3k | Curated list of Python resources for data science. |
| deep-learning-from-scratch | 2.3k | 『ゼロから作る Deep Learning』(O'Reilly Japan, 2016) |
| covid-chestxray-dataset | 2.2k | We are building an open database of COVID-19 cases with chest X-ray or CT images. |
| 深化 | 2.2k | Democratizing Deep-Learning for Drug Discovery, Quantum Chemistry, Materials Science and Biology |
| awesome-learning-resources | 2.2k | Awesome list of resources on Web Development. |
| omniscidb | 2.2k | OmniSciDB (formerly MapD Core) |
| tablesaw | 2.2k | Java dataframe and visualization library |
| Semantic-Segmentation-Suite | 2.2k | Semantic Segmentation Suite in TensorFlow. Implement, train, and test new Semantic Segmentation models easily! |
| FCOS | 2.2k | FCOS: Fully Convolutional One-Stage Object Detection (ICCV'19) |
| 聚光灯 | 2.2k | Deep recommender models using PyTorch. |
| 数据集 | 2.2k | TFDS is a collection of datasets ready to use with TensorFlow, Jax, ... |
| Deep-Learning-for-Recommendation-Systems | 2.2k | This repository contains Deep Learning based articles , paper and repositories for Recommender Systems |
| gluon-nlp | 2.1k | NLP made easy |
| dowhy | 2.1k | DoWhy is a Python library for causal inference that supports explicit modeling and testing of causal assumptions. DoWhy is based on a unified language for causal inference, combining causal graphical models and potential outcomes frameworks. |
| keras-attention-mechanism | 2.1k | Attention mechanism Implementation for Keras. |
| Meta-Learning-Papers | 2.1k | Meta Learning / Learning to Learn / One Shot Learning / Few Shot Learning |
| tacotron | 2.1k | A TensorFlow implementation of Google's Tacotron speech synthesis with pre-trained model (unofficial) |
| machinelearninginaction | 2.1k | Source Code for the book: Machine Learning in Action published by Manning |
| BuildingMachineLearningSystemsWithPython | 2.1k | Source Code for the book Building Machine Learning Systems with Python |
| CHINESE-OCR | 2.1k | [python3.6] 运用tf实现自然场景文字检测,keras/pytorch实现ctpn+crnn+ctc实现不定长场景文字OCR识别 |
| deepdetect | 2.1k | Deep Learning API and Server in C++11 support for Caffe, Caffe2, PyTorch,TensorRT, Dlib, NCNN, Tensorflow, XGBoost an… |
| XLM | 2.1k | PyTorch original implementation of Cross-lingual Language Model Pretraining. |
| tensorflow-on-raspberry-pi | 2.1k | TensorFlow for Raspberry Pi |
| decaNLP | 2.1k | The Natural Language Decathlon: A Multitask Challenge for NLP |
| AlphaZero_Gomoku | 2.1k | An implementation of the AlphaZero algorithm for Gomoku (also called Gobang or Five in a Row) |
| Pytorch-Beginner | 2.1k | pytorch tutorial for beginners |
| 切线 | 2.1k | Source-to-Source Debuggable Derivatives in Pure Python |
| Person_reID_baseline_pytorch | 2.1k | A tiny, friendly, strong pytorch implement of person re-identification baseline. Tutorial https://github.com/layumi/… |
| mmlspark | 2k | Microsoft Machine Learning for Apache Spark |
| 命运 | 2k | An Industrial Level Federated Learning Framework |
| 文本对图像 | 2k | Text to image synthesis using thought vectors |
| pytorch-sentiment-analysis | 2k | Tutorials on getting started with PyTorch and TorchText for sentiment analysis. |
| 精灵 | 2k | An End-To-End, Lightweight and Flexible Platform for Game Research |
| 催化剂 | 2k | Accelerated DL R&D |
| neuralcoref | 2k | Fast Coreference Resolution in spaCy with Neural Networks |
| DeepRL-Agents | 2k | A set of Deep Reinforcement Learning Agents implemented in Tensorflow. |
| RL-Adventure | 2k | Pytorch Implementation of DQN / DDQN / Prioritized replay/ noisy networks/ distributional values/ Rainbow/ hierarchic… |
| fe4ml-zh | 2k | [译] 面向机器学习的特征工程 |
| lingvo | 2k | Lingvo |
| pytorch-generative-model-collections | 2k | Collection of generative models in Pytorch version. |
| ResNeSt | 2k | ResNeSt: Split-Attention Networks |
| TensorFlow-Tutorials | 2k | 텐서플로우를 기초부터 응용까지 단계별로 연습할 수 있는 소스 코드를 제공합니다 |
| MUNIT | 2k | Multimodal Unsupervised Image-to-Image Translation |
| oneDNN | 2k | oneAPI Deep Neural Network Library (oneDNN) |
| deepvariant | 2k | DeepVariant is an analysis pipeline that uses a deep neural network to call genetic variants from next-generation DNA sequencing data. |
| texar | 2k | Toolkit for Machine Learning, Natural Language Processing, and Text Generation, in TensorFlow |
| kaolin | 2k | A PyTorch Library for Accelerating 3D Deep Learning Research |
| Clairvoyant | 2k | Software designed to identify and monitor social/historical cues for short term stock movement |
| 隐式 | 2k | Fast Python Collaborative Filtering for Implicit Feedback Datasets |
| DeepRL | 2k | Modularized Implementation of Deep RL Algorithms in PyTorch |
| lgo | 2k | Interactive Go programming with Jupyter |
| kcws | 2k | Deep Learning Chinese Word Segment |
| tensorflow-build-archived | 2k | TensorFlow binaries supporting AVX, FMA, SSE |
| dm_control | 2k | DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo. |
| gpytorch | 2k | A highly efficient and modular implementation of Gaussian Processes in PyTorch |
| Neural-Photo-Editor | 1.9k | A simple interface for editing natural photos with generative neural networks. |
| alpha-zero-general | 1.9k | A clean implementation based on AlphaZero for any game in any framework + tutorial + Othello/Gobang/TicTacToe/Connect4 |
| tacotron2 | 1.9k | Tacotron 2 - PyTorch implementation with faster-than-realtime inference |
| siamese-triplet | 1.9k | Siamese and triplet networks with online pair/triplet mining in PyTorch |
| awesome-quant | 1.9k | 中国的Quant相关资源索引 |
| image-super-resolution | 1.9k | ？ Super-scale your images and run experiments with Residual Dense and Adversarial Networks. |
| generative_inpainting | 1.9k | DeepFill v1/v2 with Contextual Attention and Gated Convolution, CVPR 2018, and ICCV 2019 Oral |
| code-of-learn-deep-learning-with-pytorch | 1.9k | This is code of book "Learn Deep Learning with PyTorch" |
| gpt-2-simple | 1.9k | Python package to easily retrain OpenAI's GPT-2 text-generating model on new texts |
| DeepInterests | 1.9k | 深度有趣 |
| segmentation_models.pytorch | 1.9k | Segmentation models with pretrained backbones. Pytorch。 |
| human-pose-estimation.pytorch | 1.9k | The project is an official implement of our ECCV2018 paper "Simple Baselines for Human Pose Estimation and Tracking(h… |
| Biggan-Pytorch | 1.9k | 作者正式非官方的Pytorch Biggan实施。 |
| pytorch-playground | 1.9k | Base pretrained models and datasets in pytorch (MNIST, SVHN, CIFAR10, CIFAR100, STL10, AlexNet, VGG16, VGG19, ResNet, Inception, SqueezeNet) |
| bertviz | 1.9k | Tool for visualizing attention in the Transformer model (BERT, GPT-2, Albert, XLNet, RoBERTa, CTRL, etc.) |
| face.evoLVe.PyTorch | 1.9k | High-Performance Face Recognition Library on PyTorch |
| Reco-papers | 1.8K | Classic papers and resources on recommendation |
| 教练 | 1.8K | Reinforcement Learning Coach by Intel AI Lab enables easy experimentation with state of the art Reinforcement Learning algorithms |
| sling | 1.8K | SLING - A natural language frame semantics parser |
| pytorch-Deeplab-Xception | 1.8K | DeepLab v3+ model in PyTorch. Support different backbones. |
| mmskeleton | 1.8K | A OpenMMLAB toolbox for human pose estimation, skeleton-based action recognition, and action synthesis. |
| sru | 1.8K | Training RNNs as Fast as CNNs (https://arxiv.org/abs/1709.02755) |
| pytorch-seq2seq | 1.8K | Tutorials on implementing a few sequence-to-sequence (seq2seq) models with PyTorch and TorchText. |
| Deep-Learning-Interview-Book | 1.8K | 深度学习面试宝典（含数学、机器学习、深度学习、计算机视觉、自然语言处理和SLAM等方向） |
| pai | 1.8K | Resource scheduling and cluster management for AI |
| AI-Blocks | 1.8K | A powerful and intuitive WYSIWYG interface that allows anyone to create Machine Learning models! |
| scikit-optimize | 1.8K | Sequential model-based optimization with a scipy.optimize interface |
| sequence_tagging | 1.8K | Named Entity Recognition (LSTM + CRF) - Tensorflow |
| zh-NER-TF | 1.8K | A very simple BiLSTM-CRF model for Chinese Named Entity Recognition 中文命名实体识别 (TensorFlow) |
| donkeycar | 1.8K | Open source hardware and software platform to build a small scale self driving car. |
| edge-connect | 1.8K | EdgeConnect: Structure Guided Image Inpainting using Edge Prediction, ICCV 2019 https://arxiv.org/abs/1901.00212 |
| awd-lstm-lm | 1.7k | LSTM and QRNN Language Model Toolkit for PyTorch |
| pytorch-kaldi | 1.7k | pytorch-kaldi is a project for developing state-of-the-art DNN/RNN hybrid speech recognition systems. The DNN part is managed by pytorch, while feature extraction, label computation, and decoding are performed with the kaldi toolkit. |
| Bender | 1.7k | Easily craft fast Neural Networks on iOS! Use TensorFlow models. Metal under the hood. |
| zi2zi | 1.7k | Learning Chinese Character style with conditional GAN |
| automl-gs | 1.7k | Provide an input CSV and a target field to predict, generate a model + code to run it. |
| 统计 | 1.7k | A well tested and comprehensive Golang statistics library package with no dependencies. |
| 排行 | 1.7k | Learning to Rank in TensorFlow |
| mathAI | 1.7k | 一个拍照做题程序。输入一张包含数学计算题的图片，输出识别出的数学计算式以及计算结果。This is a mathematic expression recognition project. |
| spark-ml-source-analysis | 1.7k | spark ml 算法原理剖析以及具体的源码实现分析 |
| video-object-removal | 1.7k | Just draw a bounding box and you can remove the object you want to remove. |
| datascience-pizza | 1.7k | ？ Repositório para juntar informações sobre materiais de estudo em análise de dados e áreas afins, empresas que trabalham com dados e dicionário de conceitos |
| data-science-interviews | 1.7k | Data science interview questions and answers |
| yolov3-tf2 | 1.7k | YoloV3 Implemented in Tensorflow 2.0 |
| ComputeLibrary | 1.7k | The ARM Computer Vision and Machine Learning library is a set of functions optimised for both ARM CPUs and GPUs using SIMD technologies. |
| tacotron | 1.7k | A TensorFlow Implementation of Tacotron: A Fully End-to-End Text-To-Speech Synthesis Model |
| DeepLearn | 1.7k | Implementation of research papers on Deep Learning+ NLP+ CV in Python using Keras, Tensorflow and Scikit Learn. |
| analytics-zoo | 1.7k | Distributed Tensorflow, Keras and PyTorch on Apache Spark/Flink & Ray |
| PyTorch-NLP | 1.7k | Basic Utilities for PyTorch Natural Language Processing (NLP) |
| captcha_break | 1.7k | 验证码识别 |
| crnn | 1.7k | Convolutional Recurrent Neural Network (CRNN) for image-based sequence recognition. |
| DeblurGAN | 1.7k | Image Deblurring using Generative Adversarial Networks |
| robosat | 1.6k | Semantic segmentation on aerial and satellite imagery. Extracts features such as: buildings, parking lots, roads, water, clouds |
| pointnet2 | 1.6k | PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space |
| AutonomousDrivingCookbook | 1.6k | Scenarios, tutorials and demos for Autonomous Driving |
| imgclsmob | 1.6k | Sandbox for training convolutional networks for computer vision |
| tf_unet | 1.6k | Generic U-Net Tensorflow implementation for image segmentation |
| torchsample | 1.6k | High-Level Training, Data Augmentation, and Utilities for Pytorch |
| NLP | 1.6k | ?nlp – Datasets and evaluation metrics for Natural Language Processing in NumPy, Pandas, PyTorch and TensorFlow |
| hdbscan | 1.6k | A high performance implementation of HDBSCAN clustering. |
| m2cgen | 1.6k | Transform ML models into a native code (Java, C, Python, Go, JavaScript, Visual Basic, C#, R, PowerShell, PHP, Dart, Haskell, Ruby) with zero dependencies |
| fastNLP | 1.6k | fastNLP: A Modularized and Extensible NLP Framework. Currently still in incubation. |
| keras-yolo2 | 1.6k | Easy training on custom dataset. Various backends (MobileNet and SqueezeNet) supported. A YOLO demo to detect raccoon run entirely in brower is accessible at https://git.io/vF7vI (not on Windows). |
| Awesome-Chatbot | 1.6k | Awesome Chatbot Projects,Corpus,Papers,Tutorials.Chinese Chatbot =>: |
| knockknock | 1.6k | ?✊Knock Knock: Get notified when your training ends with only two additional lines of code |
| MTBook | 1.6k | 《机器翻译：统计建模与深度学习方法》肖桐 朱靖波 著 - Machine Translation: Statistical Modeling and Deep Learning Methods |
| 火车 | 1.6k | TRAINS - Auto-Magical Experiment Manager & Version Control for AI - NOW WITH AUTO-MAGICAL DEVOPS! |
| self-driving-car | 1.6k | Udacity Self-Driving Car Engineer Nanodegree projects. |
| cnn_captcha | 1.6k | use cnn recognize captcha by tensorflow. 本项目针对字符型图片验证码，使用tensorflow实现卷积神经网络，进行验证码识别。 |
| XLearning | 1.6k | AI on Hadoop |
| Tacotron-2 | 1.6k | DeepMind's Tacotron-2 Tensorflow implementation |
| fast-wavenet | 1.6k | Speedy Wavenet generation using dynamic programming ⚡ |
| spacy-course | 1.6k | ？？ Advanced NLP with spaCy: A free online course |
| gandissect | 1.6k | Pytorch-based tools for visualizing and understanding the neurons of a GAN. https://gandissect.csail.mit.edu/ |
| NCRFpp | 1.6k | NCRF++, a Neural Sequence Labeling Toolkit. Easy use to any sequence labeling tasks (eg NER, POS, Segmentation). It includes character LSTM/CNN, word LSTM/CNN and softmax/CRF components. |
| stargan-v2 | 1.6k | StarGAN v2 - Official PyTorch Implementation (CVPR 2020) |
| tinyflow | 1.6k | Tutorial code on how to build your own Deep Learning System in 2k Lines |
| 单元 | 1.6k | Unsupervised Image-to-Image Translation |
| ssd_keras | 1.6k | A Keras port of Single Shot MultiBox Detector |
| cosin | 1.5k | ？ 春松客服，多渠道智能客服系统，开源客服系统 |
| foolbox | 1.5k | A Python toolbox to create adversarial examples that fool neural networks in PyTorch, TensorFlow, and JAX |
| capsule-networks | 1.5k | A PyTorch implementation of the NIPS 2017 paper "Dynamic Routing Between Capsules". |
| flogo | 1.5k | Project Flogo is an open source ecosystem of opinionated event-driven capabilities to simplify building efficient & modern serverless functions, microservices & edge apps. |
| lip-reading-deeplearning | 1.5k | ？ Lip Reading - Cross Audio-Visual Recognition using 3D Architectures |
| 蜂鸟 | 1.5k | Hummingbird compiles trained ML models into tensor computation for faster inference. |
| deep-rl-tensorflow | 1.5k | TensorFlow implementation of Deep Reinforcement Learning papers |
| practical-machine-learning-with-python | 1.5k | Master the essential skills needed to recognize and solve complex real-world problems with Machine Learning and Deep Learning by leveraging the highly popular Python Machine Learning Eco-system. |
| NeuroNER | 1.5k | Named-entity recognition using neural networks. Easy-to-use and state-of-the-art results. |
| wavenet_vocoder | 1.5k | Wavenet Vocoder |
| awesome-hand-pose-estimation | 1.5k | Awesome work on hand pose estimation/tracking |
| 地图 | 1.5k | mean Average Precision - This code evaluates the performance of your neural net for object recognition. |
| 代理商 | 1.5k | TF-Agents is a library for Reinforcement Learning in TensorFlow |
| CADL | 1.5k | ARCHIVED: Contains historical course materials/Homework materials for the FREE MOOC course on "Creative Applications of Deep Learning w/ Tensorflow" #CADL |
| tensorflow-DeepFM | 1.5k | Tensorflow implementation of DeepFM for CTR prediction. |
| tensorflow-1.4-billion-password-analysis | 1.5k | Deep Learning model to analyze a large corpus of clear text passwords. |
| DAT8 | 1.5k | General Assembly's 2015 Data Science course in Washington, DC |
| Nemo | 1.5k | NeMo: a toolkit for conversational AI |
| Machine-Learning-Flappy-Bird | 1.5k | Machine Learning for Flappy Bird using Neural Network and Genetic Algorithm |
| ml-visuals | 1.5k | Visuals contains figures and templates which you can reuse and customize to improve your scientific writing. |
| GANimation | 1.5k | GANimation: Anatomically-aware Facial Animation from a Single Image (ECCV'18 Oral) [PyTorch] |
| 鹰眼 | 1.5k | Stalk your Friends. Find their Instagram, FB and Twitter Profiles using Image Recognition and Reverse Image Search. |
| pytorch编码 | 1.5k | A PyTorch CV Toolkit |
| 火花 | 1.5k | .NET for Apache® Spark™ makes Apache Spark™ easily accessible to .NET developers. |
| 颤动 | 1.5k | Interactive convnet features visualization for Keras |
| MachineLearning | 1.5k | 一些关于机器学习的学习资料与研究介绍 |
| GAT | 1.5k | Graph Attention Networks (https://arxiv.org/abs/1710.10903) |
| mt-dnn | 1.4k | Multi-Task Deep Neural Networks for Natural Language Understanding |
| deep-neuroevolution | 1.4k | Deep Neuroevolution |
| a-PyTorch-Tutorial-to-Object-Detection | 1.4k | SSD: Single Shot MultiBox Detector |
| labelbox | 1.4k | Labelbox is the fastest way to annotate data to build and ship computer vision applications. |
| openvino | 1.4k | OpenVINO™ Toolkit repository |
| awesome-decision-tree-papers | 1.4k | A collection of research papers on decision, classification and regression trees with implementations. |
| project_alias | 1.4k | Alias is a teachable “parasite” that is designed to give users more control over their smart assistants, both when it comes to customisation and privacy. Through a simple app the user can train Alias to react on a custom wake-word/sound, and once trained, Alias can take control over your home assistant by activating it for you. |
| data-science-question-answer | 1.4k | A repo for data science related questions and answers |
| photo2cartoon | 1.4k | 人像卡通化探索项目 (photo-to-cartoon translation project) |
| Video2X | 1.4k | A lossless video/GIF/image upscaler achieved with waifu2x, Anime4K, SRMD and RealSR. Started in Hack the Valley 2, 2018. |
| tengine | 1.4k | Tengine is a lite, high performance, modular inference engine for embedded device |
| cuml | 1.4k | cuML - RAPIDS Machine Learning Library |
| BentoML | 1.4k | Model Serving Made Easy |
| GANotebooks | 1.4k | wgan, wgan2(improved, gp), infogan, and dcgan implementation in lasagne, keras, pytorch |
| Mobilenet | 1.4k | MobileNet build with Tensorflow |
| CRAFT-pytorch | 1.4k | Official implementation of Character Region Awareness for Text Detection (CRAFT) |
| MLR | 1.4k | Machine Learning in R |
| monodepth2 | 1.4k | Monocular depth estimation from a single image |
| TensorKart | 1.4k | self-driving MarioKart with TensorFlow |
| keras-contrib | 1.4k | Keras community contributions |
| stellargraph | 1.4k | StellarGraph - Machine Learning on Graphs |
| GDLnotes | 1.4k | Google Deep Learning Notes（TensorFlow教程） |
| pydensecrf | 1.4k | Python wrapper to Philipp Krähenbühl's dense (fully connected) CRFs with gaussian edge potentials. |
| seldon-server | 1.4k | Machine Learning Platform and Recommendation Engine built on Kubernetes |
| chainercv | 1.4k | ChainerCV: a Library for Deep Learning in Computer Vision |
| tensorflow-nlp | 1.4k | Building blocks for NLP and Text Generation in TensorFlow 2.x / 1.x |
| iOS_ML | 1.4k | List of Machine Learning, AI, NLP solutions for iOS. The most recent version of this article can be found on my blog. |
| tfgo | 1.4k | Tensorflow + Go, the gopher way |
| bi-att-flow | 1.4k | Bi-directional Attention Flow (BiDAF) network is a multi-stage hierarchical process that represents context at different levels of granularity and uses a bi-directional attention flow mechanism to achieve a query-aware context representation without early summarization. |
| CoreML-in-ARKit | 1.4k | Simple project to detect objects and display 3D labels above them in AR. This serves as a basic Template for an ARKit project to use CoreML. |
| 闪电 | 1.4k | Large-scale linear classification, regression and ranking in Python |
| DeepFace | 1.4k | Face analysis mainly based on Caffe. At this time, face analysis tasks like detection, alignment and recognition have been done. |
| torch2trt | 1.4k | An easy to use PyTorch to TensorRT converter |
| deepvoice3_pytorch | 1.4k | PyTorch implementation of convolutional neural networks-based text-to-speech synthesis models |
| sphereface | 1.4k | Implementation for <SphereFace: Deep Hypersphere Embedding for Face Recognition> in CVPR'17. |
| jeelizFaceFilter | 1.4k | Javascript/WebGL lightweight face tracking library designed for augmented reality webcam filters. Features : multiple faces detection, rotation, mouth opening. Various integration examples are provided (Three.js, Babylon.js, FaceSwap, Canvas2D, CSS3D...). |
| kaggle-web-traffic | 1.4k | 1st place solution |
| minimalRL | 1.4k | 具有最小代码行的基本RL算法的实现！ (pytorch based) |
| Machine-Learning-Notes | 1.4k | 周志华《机器学习》手推笔记 |
| Gen.jl | 1.4k | A general-purpose probabilistic programming system with programmable inference |
| faster_rcnn_pytorch | 1.4k | 更快的rcnn和pytorch |
| 草皮 | 1.4k | An Embedded Computer Vision & Machine Learning Library (CPU Optimized & IoT Capable) |
| keras_to_tensorflow | 1.4k | General code to convert a trained keras model into an inference tensorflow model |
| handtracking | 1.3k | Building a Real-time Hand-Detector using Neural Networks (SSD) on Tensorflow |
| word-rnn-tensorflow | 1.3k | Multi-layer Recurrent Neural Networks (LSTM, RNN) for word-level language models in Python using TensorFlow. |
| TorchCraft | 1.3k | Connecting Torch to StarCraft |
| AndroidTensorFlowMachineLearningExample | 1.3k | Android TensorFlow MachineLearning Example (Building TensorFlow for Android) |
| 震级 | 1.3k | A fast, efficient universal vector embedding utility package. |
| hackermath | 1.3k | Introduction to Statistics and Basics of Mathematics for Data Science - The Hacker's Way |
| pytorch-grad-cam | 1.3k | PyTorch implementation of Grad-CAM |
| 手榴弹 | 1.3k | Deep Learning in Haskell |
| captcha_trainer | 1.3k | [验证码识别-训练] This project is based on CNN/ResNet/DenseNet+GRU/LSTM+CTC/CrossEntropy to realize verification code identification. This project is only for training the model. |
| anago | 1.3k | Bidirectional LSTM-CRF and ELMo for Named-Entity Recognition, Part-of-Speech Tagging and so on. |
| mne-python | 1.3k | MNE : Magnetoencephalography (MEG) and Electroencephalography (EEG) in Python |
| EOS | 1.3k | A lightweight 3D Morphable Face Model fitting library in modern C++14 |
| ngraph | 1.3k | nGraph - open source C++ library, compiler and runtime for Deep Learning |
| NSFWDetector | 1.3k | A NSFW (aka porn) detector with CoreML |
| open_nsfw_android | 1.3k | 色情图片离线识别，基于TensorFlow实现。识别只需20ms,可断网测试，成功率99%，调用只要一行代码，从雅虎的开源项目open_nsfw移植，该模型文件可用于iOS、java、C++等平台 |
| cs230-code-examples | 1.3k | Code examples in pyTorch and Tensorflow for CS230 |
| pytorch-generative-adversarial-networks | 1.3k | A very simple generative adversarial network (GAN) in PyTorch |
| 预测 | 1.3k | Time Series Forecasting Best Practices & Examples |
| 氛围 | 1.3k | Official implementation of CVPR2020 paper "VIBE: Video Inference for Human Body Pose and Shape Estimation" |
| bulbea | 1.3k | ？ ？ Deep Learning based Python Library for Stock Market Prediction and Modelling |
| 伊莱克 | 1.3k | ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators |
| scattertext | 1.3k | Beautiful visualizations of how language differs among document types. |
| talos | 1.3k | Hyperparameter Optimization for TensorFlow, Keras and PyTorch |
| practicalAI-cn | 1.3k | AI实战-practicalAI 中文版 |
| 模仿者 | 1.3k | PyTorch implementation of our ICCV 2019 paper: Liquid Warping GAN: A Unified Framework for Human Motion Imitation, Appearance Transfer and Novel View Synthesis |
| gluon-ts | 1.3k | Probabilistic time series modeling in Python |
| dcgan-completion.tensorflow | 1.3k | Image Completion with Deep Learning in TensorFlow |
| EfficientDet.Pytorch | 1.3k | Implementation EfficientDet: Scalable and Efficient Object Detection in PyTorch |
| NeuronBlocks | 1.3k | NLP DNN Toolkit - Building Your NLP DNN Models Like Playing Lego |
| yolo2-pytorch | 1.3k | YOLOv2 in PyTorch |
| EmojiIntelligence | 1.3k | Neural Network built in Apple Playground using Swift |
| efficientnet | 1.3k | Implementation of EfficientNet model. Keras and TensorFlow Keras. |
| YOLOv3_TensorFlow | 1.3k | Complete YOLO v3 TensorFlow implementation. Support training on your own dataset. |
| TensorFlow.NET | 1.3k | .NET Standard bindings for Google's TensorFlow for developing, training and deploying Machine Learning models in C#. |
| pytextrank | 1.3k | Python implementation of TextRank for phrase extraction and summarization of text documents |
| 推断 | 1.3k | Infer.NET is a framework for running Bayesian inference in graphical models |
| UDA | 1.3k | Unsupervised Data Augmentation (UDA) |
| mmaction | 1.3k | An open-source toolbox for action understanding based on PyTorch |
| spark-nlp | 1.3k | State of the Art Natural Language Processing |
| pytorch-semantic-segmentation | 1.3k | 语义细分的pytorch |
| Deep-Learning-Boot-Camp | 1.2k | A community run, 5-day PyTorch Deep Learning Bootcamp |
| pytorch-openai-transformer-lm | 1.2k | ?A PyTorch implementation of OpenAI's finetuned transformer language model with a script to import the weights pre-trained by OpenAI |
| hiddenlayer | 1.2k | Neural network graphs and training metrics for PyTorch, Tensorflow, and Keras. |
| PaddleHub | 1.2k | Toolkit for Pre-trained Model Application of PaddlePaddle（『飞桨』预训练模型应用工具 ） |
| PhotographicImageSynthesis | 1.2k | Photographic Image Synthesis with Cascaded Refinement Networks |
| alpr-unconstrained | 1.2k | License Plate Detection and Recognition in Unconstrained Scenarios |
| Deep-Image-Analogy | 1.2k | The source code of 'Visual Attribute Transfer through Deep Image Analogy'. |
| spektral | 1.2k | Graph Neural Networks with Keras and Tensorflow 2. |
| DeepAA | 1.2k | make ASCII Art by Deep Learning |
| vvedenie-mashinnoe-obuchenie | 1.2k | Подборка ресурсов по машинному обучению |
| OpenSeq2Seq | 1.2k | Toolkit for efficient experimentation with Speech Recognition, Text2Speech and NLP |
| 锻造 | 1.2k | A neural network toolkit for Metal |
| keras-yolo3 | 1.2k | Training and Detecting Objects with YOLO3 |
| NiftyNet | 1.2k | [unmaintained] An open-source convolutional neural networks platform for research in medical image analysis and image-guided therapy |
| Awesome-TensorFlow-Chinese | 1.2k | Awesome-TensorFlow-Chinese，TensorFlow 中文资源精选，官方网站，安装教程，入门教程，视频教程，实战项目，学习路径。QQ群：167122861，公众号：磐创AI，微信群二维码：http://www.tensorflownews.com/ |
| StudyBook | 1.2k | Study E-Book(ComputerVision DeepLearning MachineLearning Math NLP Python ReinforcementLearning) |
| awesome-semantic-segmentation-pytorch | 1.2k | Semantic Segmentation on PyTorch (include FCN, PSPNet, Deeplabv3, Deeplabv3+, DANet, DenseASPP, BiSeNet, EncNet, DUNet, ICNet, ENet, OCNet, CCNet, PSANet, CGNet, ESPNet, LEDNet, DFANet) |
| RFBNet | 1.2k | Receptive Field Block Net for Accurate and Fast Object Detection, ECCV 2018 |
| GPflow | 1.2k | Gaussian processes in TensorFlow |
| dlwpt-code | 1.2k | Code for the book Deep Learning with PyTorch by Eli Stevens, Luca Antiga, and Thomas Viehmann. |
| dlcv_for_beginners | 1.2k | 《深度学习与计算机视觉》配套代码 |
| Deep-Learning-with-PyTorch-Tutorials | 1.2k | 深度学习与PyTorch入门实战视频教程 配套源代码和PPT |
| DLTK | 1.2k | Deep Learning Toolkit for Medical Image Analysis |
| FCN.tensorflow | 1.2k | Tensorflow implementation of Fully Convolutional Networks for Semantic Segmentation (http://fcn.berkeleyvision.org) |
| facenet-pytorch | 1.2k | Pretrained Pytorch face detection (MTCNN) and recognition (InceptionResnet) models |
| h2o-tutorials | 1.2k | Tutorials and training material for the H2O Machine Learning Platform |
| nlp-journey | 1.2k | Documents, papers and codes related to Natural Language Processing, including Topic Model, Word Embedding, Named Entity Recognition, Text Classificatin, Text Generation, Text Similarity, Machine Translation)，etc. All codes are implemented intensorflow 2.0. |
| object_detector_app | 1.2k | Real-Time Object Recognition App with Tensorflow and OpenCV |
| tnt | 1.2k | Simple tools for logging and visualizing, loading and training |
| tensorflow-deeplab-resnet | 1.2k | DeepLab-ResNet rebuilt in TensorFlow |
| reproducible-image-denoising-state-of-the-art | 1.2k | Collection of popular and reproducible image denoising works. |
| senet.pytorch | 1.2k | PyTorch implementation of SENet |
| pytorch-seq2seq | 1.2k | An open source framework for seq2seq models in PyTorch. |
| efficient_densenet_pytorch | 1.2k | A memory-efficient implementation of DenseNets |
| pytorch-retinanet | 1.2k | Pytorch implementation of RetinaNet object detection. |
| cakechat | 1.2k | CakeChat: Emotional Generative Dialog System |
| pytorch-fcn | 1.2k | PyTorch Implementation of Fully Convolutional Networks. (Training code to reproduce the original result is available.) |
| python-machine-learning-book-3rd-edition | 1.2k | The "Python Machine Learning (3rd edition)" book code repository |
| tf-quant-finance | 1.2k | High-performance TensorFlow library for quantitative finance. |
| gnes | 1.1k | GNES is Generic Neural Elastic Search, a cloud-native semantic search system based on deep neural network. |
| Image-OutPainting | 1.1k | ？ Keras Implementation of Painting outside the box |
| Fabrik | 1.1k | ？ Collaboratively build, visualize, and design neural nets in browser |
| attention-transfer | 1.1k | Improving Convolutional Networks via Attention Transfer (ICLR 2017) |
| pytorch-cifar100 | 1.1k | Practice on cifar100(ResNet, DenseNet, VGG, GoogleNet, InceptionV3, InceptionV4, Inception-ResNetv2, Xception, Resnet In Resnet, ResNext,ShuffleNet, ShuffleNetv2, MobileNet, MobileNetv2, SqueezeNet, NasNet, Residual Attention Network, SENet) |
| MONAI | 1.1k | AI Toolkit for Healthcare Imaging |
| tensorrec | 1.1k | A TensorFlow recommendation algorithm and framework in Python. |
| mleap | 1.1k | MLeap: Deploy Spark Pipelines to Production |
| noreward-rl | 1.1k | [ICML 2017] TensorFlow code for Curiosity-driven Exploration for Deep Reinforcement Learning |
| PyTorchNLPBook | 1.1k | Code and data accompanying Natural Language Processing with PyTorch published by O'Reilly Media https://nlproc.info |
| mtcnn | 1.1k | MTCNN face detection implementation for TensorFlow, as a PIP package. |
| WaveRNN | 1.1k | WaveRNN Vocoder + TTS |
| UNet-family | 1.1k | Paper and implementation of UNet-related model. |
| Awesome-pytorch-list-CNVersion | 1.1k | Awesome-pytorch-list 翻译工作进行中...... |
| tensorflow-fcn | 1.1k | An Implementation of Fully Convolutional Networks in Tensorflow. |
| BicycleGAN | 1.1k | Toward Multimodal Image-to-Image Translation |
| TensorFlow2.0-Examples | 1.1k | ？ Difficult algorithm, simple code. |
| fast-autoaugment | 1.1k | Official Implementation of 'Fast AutoAugment' in PyTorch. |
| fastai_deeplearn_part1 | 1.1k | Notes for Fastai Deep Learning Course |
| HyperGAN | 1.1k | Composable GAN framework with api and user interface |
| 家 | 1.1k | ApacheCN 开源组织：公告、介绍、成员、活动、交流方式 |
| tfx | 1.1k | TFX is an end-to-end platform for deploying production ML pipelines |
| handwriting-synthesis | 1.1k | Handwriting Synthesis with RNNs ✏️ |
| image-quality-assessment | 1.1k | Convolutional Neural Networks to predict the aesthetic and technical quality of images. |
| PerceptualSimilarity | 1.1k | Learned Perceptual Image Patch Similarity (LPIPS) metric. In CVPR, 2018. |
| lanenet-lane-detection | 1.1k | Unofficial implemention of lanenet model for real time lane detection using deep neural network model https://maybeshewill-cv.github.io/lanenet-lane-detection/ |
| uTensor | 1.1k | TinyML AI inference library |
| torchgan | 1.1k | Research Framework for easy and efficient training of GANs based on Pytorch |
| 梅林 | 1.1k | This is now the official location of the Merlin project. |
| 线索 | 1k | 中文语言理解基准测评 Chinese Language Understanding Evaluation Benchmark: datasets, baselines, pre-trained models, corpus and leaderboard |
| tfjs-node | 1k | TensorFlow powered JavaScript library for training and deploying ML models on Node.js. |
| CycleGAN-TensorFlow | 1k | An implementation of CycleGan using TensorFlow |
| EffectivePyTorch | 1k | PyTorch tutorials and best practices. |
| hercules | 1k | Gaining advanced insights from Git repository history. |
| AdvancedEAST | 1k | AdvancedEAST is an algorithm used for Scene image text detect, which is primarily based on EAST, and the significant improvement was also made, which make long text predictions more accurate. |
| one-pixel-attack-keras | 1k | Keras implementation of "One pixel attack for fooling deep neural networks" using differential evolution on Cifar10 and ImageNet |
| CRNN_Chinese_Characters_Rec | 1k | (CRNN) Chinese Characters Recognition. |
| hmtl | 1k | ?HMTL: Hierarchical Multi-Task Learning - A State-of-the-Art neural network model for several NLP tasks based on PyTorch and AllenNLP |
| rethinking-network-pruning | 1k | Rethinking the Value of Network Pruning (Pytorch) (ICLR 2019) |
| Pytorch分类 | 1k | Classification with PyTorch. |
| a-PyTorch-Tutorial-to-Image-Captioning | 1k | Show, Attend, and Tell |
| reformer-pytorch | 1k | Reformer, the efficient Transformer, in Pytorch |
| pytorch-YOLOv4 | 1k | PyTorch ,ONNX and TensorRT implementation of YOLOv4 |
| FaceMaskDetection | 1k | 开源人脸口罩检测模型和数据 Detect faces and determine whether people are wearing mask. |
| gen-efficientnet-pytorch | 1k | Pretrained EfficientNet, EfficientNet-Lite, MixNet, MobileNetV3 / V2, MNASNet A1 and B1, FBNet, Single-Path NAS |
| open-reid | 1k | Open source person re-identification library in python |
| wgan-gp | 1k | A pytorch implementation of Paper "Improved Training of Wasserstein GANs" |
