[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-hfawaz--dl-4-tsc":3,"tool-hfawaz--dl-4-tsc":64},[4,17,27,35,43,56],{"id":5,"name":6,"github_repo":7,"description_zh":8,"stars":9,"difficulty_score":10,"last_commit_at":11,"category_tags":12,"status":16},3808,"stable-diffusion-webui","AUTOMATIC1111\u002Fstable-diffusion-webui","stable-diffusion-webui 是一个基于 Gradio 构建的网页版操作界面，旨在让用户能够轻松地在本地运行和使用强大的 Stable Diffusion 图像生成模型。它解决了原始模型依赖命令行、操作门槛高且功能分散的痛点，将复杂的 AI 绘图流程整合进一个直观易用的图形化平台。\n\n无论是希望快速上手的普通创作者、需要精细控制画面细节的设计师，还是想要深入探索模型潜力的开发者与研究人员，都能从中获益。其核心亮点在于极高的功能丰富度：不仅支持文生图、图生图、局部重绘（Inpainting）和外绘（Outpainting）等基础模式，还独创了注意力机制调整、提示词矩阵、负向提示词以及“高清修复”等高级功能。此外，它内置了 GFPGAN 和 CodeFormer 等人脸修复工具，支持多种神经网络放大算法，并允许用户通过插件系统无限扩展能力。即使是显存有限的设备，stable-diffusion-webui 也提供了相应的优化选项，让高质量的 AI 艺术创作变得触手可及。",162132,3,"2026-04-05T11:01:52",[13,14,15],"开发框架","图像","Agent","ready",{"id":18,"name":19,"github_repo":20,"description_zh":21,"stars":22,"difficulty_score":23,"last_commit_at":24,"category_tags":25,"status":16},1381,"everything-claude-code","affaan-m\u002Feverything-claude-code","everything-claude-code 是一套专为 AI 编程助手（如 Claude Code、Codex、Cursor 等）打造的高性能优化系统。它不仅仅是一组配置文件，而是一个经过长期实战打磨的完整框架，旨在解决 AI 代理在实际开发中面临的效率低下、记忆丢失、安全隐患及缺乏持续学习能力等核心痛点。\n\n通过引入技能模块化、直觉增强、记忆持久化机制以及内置的安全扫描功能，everything-claude-code 能显著提升 AI 在复杂任务中的表现，帮助开发者构建更稳定、更智能的生产级 AI 代理。其独特的“研究优先”开发理念和针对 Token 消耗的优化策略，使得模型响应更快、成本更低，同时有效防御潜在的攻击向量。\n\n这套工具特别适合软件开发者、AI 研究人员以及希望深度定制 AI 工作流的技术团队使用。无论您是在构建大型代码库，还是需要 AI 协助进行安全审计与自动化测试，everything-claude-code 都能提供强大的底层支持。作为一个曾荣获 Anthropic 黑客大奖的开源项目，它融合了多语言支持与丰富的实战钩子（hooks），让 AI 真正成长为懂上",138956,2,"2026-04-05T11:33:21",[13,15,26],"语言模型",{"id":28,"name":29,"github_repo":30,"description_zh":31,"stars":32,"difficulty_score":23,"last_commit_at":33,"category_tags":34,"status":16},2271,"ComfyUI","Comfy-Org\u002FComfyUI","ComfyUI 是一款功能强大且高度模块化的视觉 AI 引擎，专为设计和执行复杂的 Stable Diffusion 图像生成流程而打造。它摒弃了传统的代码编写模式，采用直观的节点式流程图界面，让用户通过连接不同的功能模块即可构建个性化的生成管线。\n\n这一设计巧妙解决了高级 AI 绘图工作流配置复杂、灵活性不足的痛点。用户无需具备编程背景，也能自由组合模型、调整参数并实时预览效果，轻松实现从基础文生图到多步骤高清修复等各类复杂任务。ComfyUI 拥有极佳的兼容性，不仅支持 Windows、macOS 和 Linux 全平台，还广泛适配 NVIDIA、AMD、Intel 及苹果 Silicon 等多种硬件架构，并率先支持 SDXL、Flux、SD3 等前沿模型。\n\n无论是希望深入探索算法潜力的研究人员和开发者，还是追求极致创作自由度的设计师与资深 AI 绘画爱好者，ComfyUI 都能提供强大的支持。其独特的模块化架构允许社区不断扩展新功能，使其成为当前最灵活、生态最丰富的开源扩散模型工具之一，帮助用户将创意高效转化为现实。",107662,"2026-04-03T11:11:01",[13,14,15],{"id":36,"name":37,"github_repo":38,"description_zh":39,"stars":40,"difficulty_score":23,"last_commit_at":41,"category_tags":42,"status":16},3704,"NextChat","ChatGPTNextWeb\u002FNextChat","NextChat 是一款轻量且极速的 AI 助手，旨在为用户提供流畅、跨平台的大模型交互体验。它完美解决了用户在多设备间切换时难以保持对话连续性，以及面对众多 AI 模型不知如何统一管理的痛点。无论是日常办公、学习辅助还是创意激发，NextChat 都能让用户随时随地通过网页、iOS、Android、Windows、MacOS 或 Linux 端无缝接入智能服务。\n\n这款工具非常适合普通用户、学生、职场人士以及需要私有化部署的企业团队使用。对于开发者而言，它也提供了便捷的自托管方案，支持一键部署到 Vercel 或 Zeabur 等平台。\n\nNextChat 的核心亮点在于其广泛的模型兼容性，原生支持 Claude、DeepSeek、GPT-4 及 Gemini Pro 等主流大模型，让用户在一个界面即可自由切换不同 AI 能力。此外，它还率先支持 MCP（Model Context Protocol）协议，增强了上下文处理能力。针对企业用户，NextChat 提供专业版解决方案，具备品牌定制、细粒度权限控制、内部知识库整合及安全审计等功能，满足公司对数据隐私和个性化管理的高标准要求。",87618,"2026-04-05T07:20:52",[13,26],{"id":44,"name":45,"github_repo":46,"description_zh":47,"stars":48,"difficulty_score":23,"last_commit_at":49,"category_tags":50,"status":16},2268,"ML-For-Beginners","microsoft\u002FML-For-Beginners","ML-For-Beginners 是由微软推出的一套系统化机器学习入门课程，旨在帮助零基础用户轻松掌握经典机器学习知识。这套课程将学习路径规划为 12 周，包含 26 节精炼课程和 52 道配套测验，内容涵盖从基础概念到实际应用的完整流程，有效解决了初学者面对庞大知识体系时无从下手、缺乏结构化指导的痛点。\n\n无论是希望转型的开发者、需要补充算法背景的研究人员，还是对人工智能充满好奇的普通爱好者，都能从中受益。课程不仅提供了清晰的理论讲解，还强调动手实践，让用户在循序渐进中建立扎实的技能基础。其独特的亮点在于强大的多语言支持，通过自动化机制提供了包括简体中文在内的 50 多种语言版本，极大地降低了全球不同背景用户的学习门槛。此外，项目采用开源协作模式，社区活跃且内容持续更新，确保学习者能获取前沿且准确的技术资讯。如果你正寻找一条清晰、友好且专业的机器学习入门之路，ML-For-Beginners 将是理想的起点。",84991,"2026-04-05T10:45:23",[14,51,52,53,15,54,26,13,55],"数据工具","视频","插件","其他","音频",{"id":57,"name":58,"github_repo":59,"description_zh":60,"stars":61,"difficulty_score":10,"last_commit_at":62,"category_tags":63,"status":16},3128,"ragflow","infiniflow\u002Fragflow","RAGFlow 是一款领先的开源检索增强生成（RAG）引擎，旨在为大语言模型构建更精准、可靠的上下文层。它巧妙地将前沿的 RAG 技术与智能体（Agent）能力相结合，不仅支持从各类文档中高效提取知识，还能让模型基于这些知识进行逻辑推理和任务执行。\n\n在大模型应用中，幻觉问题和知识滞后是常见痛点。RAGFlow 通过深度解析复杂文档结构（如表格、图表及混合排版），显著提升了信息检索的准确度，从而有效减少模型“胡编乱造”的现象，确保回答既有据可依又具备时效性。其内置的智能体机制更进一步，使系统不仅能回答问题，还能自主规划步骤解决复杂问题。\n\n这款工具特别适合开发者、企业技术团队以及 AI 研究人员使用。无论是希望快速搭建私有知识库问答系统，还是致力于探索大模型在垂直领域落地的创新者，都能从中受益。RAGFlow 提供了可视化的工作流编排界面和灵活的 API 接口，既降低了非算法背景用户的上手门槛，也满足了专业开发者对系统深度定制的需求。作为基于 Apache 2.0 协议开源的项目，它正成为连接通用大模型与行业专有知识之间的重要桥梁。",77062,"2026-04-04T04:44:48",[15,14,13,26,54],{"id":65,"github_repo":66,"name":67,"description_en":68,"description_zh":69,"ai_summary_zh":69,"readme_en":70,"readme_zh":71,"quickstart_zh":72,"use_case_zh":73,"hero_image_url":74,"owner_login":75,"owner_name":76,"owner_avatar_url":77,"owner_bio":78,"owner_company":79,"owner_location":80,"owner_email":81,"owner_twitter":82,"owner_website":83,"owner_url":84,"languages":85,"stars":90,"forks":91,"last_commit_at":92,"license":93,"difficulty_score":10,"env_os":94,"env_gpu":95,"env_ram":96,"env_deps":97,"category_tags":110,"github_topics":111,"view_count":10,"oss_zip_url":119,"oss_zip_packed_at":119,"status":16,"created_at":120,"updated_at":121,"faqs":122,"releases":158},441,"hfawaz\u002Fdl-4-tsc","dl-4-tsc","Deep Learning for Time Series Classification","dl-4-tsc 是一个专注于时间序列分类任务的深度学习代码库，源自一篇发表在权威期刊上的综述论文。它主要解决了研究人员在进行时间序列分析时，需要从头搭建、调试各类神经网络模型的繁琐问题。dl-4-tsc 整合了九种主流深度学习分类器（包括 FCN、ResNet 和 InceptionTime 等），并适配了 UCR 和 MTS 等标准数据集，为算法对比和基准测试提供了极大的便利。\n\n这个项目特别适合机器学习领域的研究人员和算法开发者使用。无论是复现论文结果，还是寻找适合特定业务场景的时间序列分类模型，dl-4-tsc 都能提供现成的解决方案。其技术亮点在于不仅提供了基于 TensorFlow 2.0 的统一代码框架，还通过实验验证了深度残差网络在该领域的优越性能。此外，项目支持 Docker 容器化部署，有效降低了环境配置的门槛，让用户能更专注于算法本身的研究。","# Deep Learning for Time Series Classification\nThis is the companion repository for [our paper](https:\u002F\u002Flink.springer.com\u002Farticle\u002F10.1007%2Fs10618-019-00619-1) titled \"Deep learning for time series classification: a review\" published in [Data Mining and Knowledge Discovery](https:\u002F\u002Flink.springer.com\u002Fjournal\u002F10618), also available on [ArXiv](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1809.04356.pdf). \n\n![architecture resnet](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fhfawaz_dl-4-tsc_readme_e0501925540d.png)\n\n## Docker\nAssuming you have [docker](https:\u002F\u002Fhub.docker.com) installed.\nYou can now use the docker image provided [here](https:\u002F\u002Fhub.docker.com\u002Frepository\u002Fdocker\u002Fhassanfawaz\u002Fdl-4-tsc\u002Fgeneral). \n\nAccess the docker container via: \n```bash\ndocker run --name somename --gpus all  -idt hassanfawaz\u002Fdl-4-tsc:0.3\ndocker exec -it somename bash\n```\n\nTo run you will need to manually download the UCR archive into `\u002Fdl-4-tsc\u002Farchives\u002F`: \n\n```bash\ncd \u002Fdl-4-tsc\u002Farchives\nwget https:\u002F\u002Fwww.cs.ucr.edu\u002F~eamonn\u002Ftime_series_data_2018\u002FUCRArchive_2018.zip\nunzip -P $password UCRArchive_2018.zip\n```\n\nThe password can be found [here](https:\u002F\u002Fwww.cs.ucr.edu\u002F~eamonn\u002Ftime_series_data_2018\u002F).\n\nNow that you have the data and the code you can just run the code.\n\n```bash\ncd \u002Fdl-4-tsc\npython -m main UCRArchive_2018 Coffee fcn _itr_0\n```\n\nYou can also try and install with pip on your env.\n\n## Data \nThe data used in this project comes from two sources: \n* The [UCR\u002FUEA archive](http:\u002F\u002Ftimeseriesclassification.com\u002FTSC.zip), which contains the 85 univariate time series datasets. \n* The [MTS archive](http:\u002F\u002Fwww.mustafabaydogan.com\u002Ffiles\u002Fviewcategory\u002F20-data-sets.html), which contains the 13 multivariate time series datasets.\n\n## Code \nThe code is divided as follows: \n* The [main.py](https:\u002F\u002Fgithub.com\u002Fhfawaz\u002Fdl-4-tsc\u002Fblob\u002Fmaster\u002Fmain.py) python file contains the necessary code to run an experiement. \n* The [utils](https:\u002F\u002Fgithub.com\u002Fhfawaz\u002Fdl-4-tsc\u002Ftree\u002Fmaster\u002Futils) folder contains the necessary functions to read the datasets and visualize the plots.\n* The [classifiers](https:\u002F\u002Fgithub.com\u002Fhfawaz\u002Fdl-4-tsc\u002Ftree\u002Fmaster\u002Fclassifiers) folder contains nine python files one for each deep neural network tested in our paper. \n\nTo run a model on one dataset you should issue the following command: \n```\npython3 main.py TSC Coffee fcn _itr_8\n```\nwhich means we are launching the [fcn](https:\u002F\u002Fgithub.com\u002Fhfawaz\u002Fdl-4-tsc\u002Fblob\u002Fmaster\u002Fclassifiers\u002Ffcn.py) model on the univariate UCR archive for the Coffee dataset (see [constants.py](https:\u002F\u002Fgithub.com\u002Fhfawaz\u002Fdl-4-tsc\u002Fblob\u002Fmaster\u002Futils\u002Fconstants.py) for a list of possible options).\n\n## Prerequisites\nAll python packages needed are listed in [pip-requirements.txt](https:\u002F\u002Fgithub.com\u002Fhfawaz\u002Fdl-4-tsc\u002Fblob\u002Fmaster\u002Futils\u002Fpip-requirements.txt) file and can be installed simply using the pip command. \nThe code now uses Tensorflow 2.0.\nThe results in the paper were generated using the Tensorflow 1.14 implementation which can be found [here](https:\u002F\u002Fgithub.com\u002Fhfawaz\u002Fdl-4-tsc\u002Fcommit\u002F7ab94a02aedf3a9688e248603bd43c5d405f039b). \nUsing Tensorflow 2.0 should give the same results.  \nNow [InceptionTime](https:\u002F\u002Fgithub.com\u002Fhfawaz\u002FInceptionTime) is included in the mix, feel free to send a pull request to add another classifier. \n\n* [numpy](http:\u002F\u002Fwww.numpy.org\u002F)  \n* [pandas](https:\u002F\u002Fpandas.pydata.org\u002F)  \n* [sklearn](http:\u002F\u002Fscikit-learn.org\u002Fstable\u002F)  \n* [scipy](https:\u002F\u002Fwww.scipy.org\u002F)  \n* [matplotlib](https:\u002F\u002Fmatplotlib.org\u002F)  \n* [tensorflow-gpu](https:\u002F\u002Fwww.tensorflow.org\u002F)  \n* [keras](https:\u002F\u002Fkeras.io\u002F)  \n* [h5py](http:\u002F\u002Fdocs.h5py.org\u002Fen\u002Flatest\u002Fbuild.html)\n* [keras_contrib](https:\u002F\u002Fwww.github.com\u002Fkeras-team\u002Fkeras-contrib.git)\n\n## Results\nI added the [results](https:\u002F\u002Fgithub.com\u002Fhfawaz\u002Fdl-4-tsc\u002Fblob\u002Fmaster\u002Fresults\u002Fresults-ucr-128.csv) on the 128 datasets from the [UCR archive 2018](https:\u002F\u002Fwww.cs.ucr.edu\u002F~eamonn\u002Ftime_series_data_2018\u002F).\nOur [results](https:\u002F\u002Fgithub.com\u002Fhfawaz\u002Fdl-4-tsc\u002Ftree\u002Fmaster\u002Fresults) in the paper showed that a deep residual network architecture performs best for the time series classification task. \n\nThe following table contains the averaged accuracy over 10 runs of each implemented model on the UCR\u002FUEA archive, with the standard deviation between parentheses. \n\n| Datasets                       | MLP       | FCN        | ResNet     | Encoder    | MCNN       | t-LeNet   | MCDCNN     | Time-CNN  | TWIESN     | \n|--------------------------------|-----------|------------|------------|------------|------------|-----------|------------|-----------|------------| \n| 50words                        | 68.4(7.1) | 62.7(6.1)  | 74.0(1.5)  | 72.3(1.0)  | 22.0(24.3) | 12.5(0.0) | 58.9(5.3)  | 62.1(1.0) | 49.6(2.6)  | \n| Adiac                          | 39.7(1.9) | 84.4(0.7)  | 82.9(0.6)  | 48.4(2.5)  | 2.2(0.6)   | 2.0(0.0)  | 61.0(8.7)  | 37.9(2.0) | 41.6(4.5)  | \n| ArrowHead                      | 77.8(1.2) | 84.3(1.5)  | 84.5(1.2)  | 80.4(2.9)  | 33.9(4.7)  | 30.3(0.0) | 68.5(6.7)  | 72.3(2.6) | 65.9(9.4)  | \n| Beef                           | 72.0(2.8) | 69.7(4.0)  | 75.3(4.2)  | 64.3(5.0)  | 20.0(0.0)  | 20.0(0.0) | 56.3(7.8)  | 76.3(1.1) | 53.7(14.9) | \n| BeetleFly                      | 87.0(2.6) | 86.0(9.7)  | 85.0(2.4)  | 74.5(7.6)  | 50.0(0.0)  | 50.0(0.0) | 58.0(9.2)  | 89.0(3.2) | 73.0(7.9)  | \n| BirdChicken                    | 77.5(3.5) | 95.5(3.7)  | 88.5(5.3)  | 66.5(5.8)  | 50.0(0.0)  | 50.0(0.0) | 58.0(10.3) | 60.5(9.0) | 74.0(15.6) | \n| CBF                            | 87.2(0.7) | 99.4(0.1)  | 99.5(0.3)  | 94.7(1.2)  | 33.2(0.1)  | 33.2(0.1) | 82.0(20.5) | 95.7(1.0) | 89.0(4.9)  | \n| Car                            | 76.7(2.6) | 90.5(1.4)  | 92.5(1.4)  | 75.8(2.0)  | 24.0(2.7)  | 31.7(0.0) | 73.0(3.0)  | 78.2(1.2) | 78.3(4.0)  | \n| ChlorineConcentration          | 80.2(1.1) | 81.4(0.9)  | 84.4(1.0)  | 57.3(1.1)  | 53.3(0.0)  | 53.3(0.0) | 64.3(3.8)  | 60.0(0.8) | 55.3(0.3)  | \n| CinC\\_ECG\\_torso                 | 84.0(1.0) | 82.4(1.2)  | 82.6(2.4)  | 91.1(2.7)  | 38.1(28.0) | 25.0(0.1) | 73.6(15.2) | 74.5(4.9) | 30.0(2.9)  | \n| Coffee                         | 99.6(1.1) | 100.0(0.0) | 100.0(0.0) | 97.9(1.8)  | 51.4(3.5)  | 53.6(0.0) | 98.2(2.5)  | 99.6(1.1) | 97.1(2.8)  | \n| Computers                      | 56.3(1.6) | 82.2(1.0)  | 81.5(1.2)  | 57.4(2.2)  | 52.2(4.8)  | 50.0(0.0) | 55.9(3.3)  | 54.8(1.5) | 62.9(4.1)  | \n| Cricket\\_X                      | 59.1(1.1) | 79.2(0.7)  | 79.1(0.6)  | 69.4(1.6)  | 18.9(23.8) | 7.4(0.0)  | 49.5(5.3)  | 55.2(2.9) | 62.2(2.1)  | \n| Cricket\\_Y                      | 60.0(0.8) | 78.7(1.2)  | 80.3(0.8)  | 67.5(1.0)  | 18.4(22.0) | 8.5(0.0)  | 49.7(4.3)  | 57.0(2.4) | 65.6(1.3)  | \n| Cricket\\_Z                      | 61.7(0.8) | 81.1(1.0)  | 81.2(1.4)  | 69.2(1.0)  | 18.3(24.4) | 6.2(0.0)  | 49.8(3.6)  | 48.8(2.8) | 62.2(2.3)  | \n| DiatomSizeReduction            | 91.0(1.4) | 31.3(3.6)  | 30.1(0.2)  | 91.3(1.8)  | 30.1(0.7)  | 30.1(0.0) | 70.3(28.9) | 95.4(0.7) | 88.0(6.6)  | \n| DistalPhalanxOutlineAgeGroup   | 65.7(1.1) | 71.0(1.3)  | 71.7(1.3)  | 73.7(1.6)  | 46.8(0.0)  | 44.6(2.3) | 74.4(2.2)  | 75.2(1.4) | 71.0(2.1)  | \n| DistalPhalanxOutlineCorrect    | 72.6(1.3) | 76.0(1.5)  | 77.1(1.0)  | 74.1(1.4)  | 58.3(0.0)  | 58.3(0.0) | 75.3(1.8)  | 75.9(2.0) | 71.3(1.0)  | \n| DistalPhalanxTW                | 61.7(1.3) | 69.0(2.1)  | 66.5(1.6)  | 68.8(1.6)  | 30.2(0.0)  | 28.3(0.7) | 67.7(1.8)  | 67.3(2.8) | 60.9(3.0)  | \n| ECG200                         | 91.6(0.7) | 88.9(1.0)  | 87.4(1.9)  | 92.3(1.1)  | 64.0(0.0)  | 64.0(0.0) | 83.3(3.9)  | 81.4(1.3) | 84.2(5.1)  | \n| ECG5000                        | 92.9(0.1) | 94.0(0.1)  | 93.4(0.2)  | 94.0(0.2)  | 61.8(10.9) | 58.4(0.0) | 93.7(0.6)  | 92.8(0.2) | 91.9(0.2)  | \n| ECGFiveDays                    | 97.0(0.5) | 98.7(0.3)  | 97.5(1.9)  | 98.2(0.7)  | 49.9(0.3)  | 49.7(0.0) | 76.2(13.4) | 88.2(1.8) | 69.8(14.1) | \n| Earthquakes                    | 71.7(1.3) | 72.7(1.7)  | 71.2(2.0)  | 74.8(0.7)  | 74.8(0.0)  | 74.8(0.0) | 74.9(0.2)  | 70.0(1.9) | 74.8(0.0)  | \n| ElectricDevices                | 59.2(1.1) | 70.2(1.2)  | 72.9(0.9)  | 67.4(1.1)  | 33.6(19.8) | 24.2(0.0) | 64.4(1.2)  | 68.1(1.0) | 60.7(0.7)  | \n| FISH                           | 84.8(0.8) | 95.8(0.6)  | 97.9(0.8)  | 86.6(0.9)  | 13.4(1.3)  | 12.6(0.0) | 75.8(3.9)  | 84.9(0.5) | 87.5(3.4)  | \n| FaceAll                        | 79.3(1.1) | 94.5(0.9)  | 83.9(2.0)  | 79.3(0.8)  | 17.0(19.5) | 8.0(0.0)  | 71.7(2.3)  | 76.8(1.1) | 65.7(2.5)  | \n| FaceFour                       | 84.0(1.4) | 92.8(0.9)  | 95.5(0.0)  | 81.5(2.6)  | 26.8(5.7)  | 29.5(0.0) | 71.2(13.5) | 90.6(1.1) | 85.5(6.2)  | \n| FacesUCR                       | 83.3(0.3) | 94.6(0.2)  | 95.5(0.4)  | 87.4(0.4)  | 15.3(2.7)  | 14.3(0.0) | 75.6(5.1)  | 86.9(0.7) | 64.4(2.0)  | \n| FordA                          | 73.0(0.4) | 90.4(0.2)  | 92.0(0.4)  | 92.3(0.3)  | 51.3(0.0)  | 51.0(0.8) | 79.5(2.6)  | 88.1(0.7) | 52.8(2.1)  | \n| FordB                          | 60.3(0.3) | 87.8(0.6)  | 91.3(0.3)  | 89.0(0.5)  | 49.8(1.2)  | 51.2(0.0) | 53.3(2.9)  | 80.6(1.5) | 50.3(1.2)  | \n| Gun\\_Point                      | 92.7(1.1) | 100.0(0.0) | 99.1(0.7)  | 93.6(3.2)  | 51.3(3.9)  | 49.3(0.0) | 86.7(9.6)  | 93.2(1.9) | 96.1(2.3)  | \n| Ham                            | 69.1(1.4) | 71.8(1.4)  | 75.7(2.7)  | 72.7(1.2)  | 50.6(1.4)  | 51.4(0.0) | 73.3(4.2)  | 71.1(2.0) | 72.3(6.3)  | \n| HandOutlines                   | 91.8(0.5) | 80.6(7.9)  | 91.1(1.4)  | 89.9(2.3)  | 64.1(0.0)  | 64.1(0.0) | 90.9(0.6)  | 88.8(1.2) | 66.0(0.7)  | \n| Haptics                        | 43.3(1.4) | 48.0(2.4)  | 51.9(1.2)  | 42.7(1.6)  | 20.9(3.5)  | 20.8(0.0) | 40.4(3.3)  | 36.6(2.4) | 40.4(4.5)  | \n| Herring                        | 52.8(3.9) | 60.8(7.7)  | 61.9(3.8)  | 58.6(4.8)  | 59.4(0.0)  | 59.4(0.0) | 60.0(5.2)  | 53.9(1.7) | 59.1(6.5)  | \n| InlineSkate                    | 33.7(1.0) | 33.9(0.8)  | 37.3(0.9)  | 29.2(0.9)  | 16.7(1.6)  | 16.5(1.1) | 21.5(2.2)  | 28.7(1.2) | 33.0(6.8)  | \n| InsectWingbeatSound            | 60.7(0.4) | 39.3(0.6)  | 50.7(0.9)  | 63.3(0.6)  | 15.8(14.2) | 9.1(0.0)  | 58.3(2.6)  | 58.3(0.6) | 43.7(2.0)  | \n| ItalyPowerDemand               | 95.4(0.2) | 96.1(0.3)  | 96.3(0.4)  | 96.5(0.5)  | 50.0(0.2)  | 49.9(0.0) | 95.5(1.9)  | 95.5(0.4) | 88.0(2.2)  | \n| LargeKitchenAppliances         | 47.3(0.6) | 90.2(0.4)  | 90.0(0.5)  | 61.9(2.6)  | 41.0(16.5) | 33.3(0.0) | 43.4(2.8)  | 66.6(5.0) | 77.9(1.8)  | \n| Lighting2                      | 67.0(2.1) | 73.9(1.4)  | 77.0(1.7)  | 69.2(4.6)  | 55.7(5.2)  | 54.1(0.0) | 63.0(5.9)  | 63.6(2.5) | 70.3(4.1)  | \n| Lighting7                      | 63.0(1.7) | 82.7(2.3)  | 84.5(2.0)  | 62.5(2.3)  | 31.0(11.3) | 26.0(0.0) | 53.4(5.9)  | 65.1(3.3) | 66.4(6.6)  | \n| MALLAT                         | 91.8(0.6) | 96.7(0.9)  | 97.2(0.3)  | 87.6(2.0)  | 13.5(3.7)  | 12.3(0.1) | 90.1(5.7)  | 92.0(0.7) | 59.6(9.8)  | \n| Meat                           | 89.7(1.7) | 85.3(6.9)  | 96.8(2.5)  | 74.2(11.0) | 33.3(0.0)  | 33.3(0.0) | 70.5(8.8)  | 90.2(1.8) | 96.8(2.0)  | \n| MedicalImages                  | 72.1(0.7) | 77.9(0.4)  | 77.0(0.7)  | 73.4(1.5)  | 51.4(0.0)  | 51.4(0.0) | 64.0(1.4)  | 67.6(1.1) | 64.9(2.7)  | \n| MiddlePhalanxOutlineAgeGroup   | 53.1(1.8) | 55.3(1.8)  | 56.9(2.1)  | 57.9(2.9)  | 18.8(0.0)  | 57.1(0.0) | 58.5(3.8)  | 56.6(1.5) | 58.1(2.6)  | \n| MiddlePhalanxOutlineCorrect    | 77.0(1.1) | 80.1(1.0)  | 80.9(1.2)  | 76.1(2.3)  | 57.0(0.0)  | 57.0(0.0) | 81.1(1.6)  | 76.6(1.3) | 74.4(2.3)  | \n| MiddlePhalanxTW                | 53.4(1.6) | 51.2(1.8)  | 48.4(2.0)  | 59.2(1.0)  | 27.3(0.0)  | 28.6(0.0) | 58.1(2.4)  | 54.9(1.7) | 53.9(2.9)  | \n| MoteStrain                     | 85.8(0.9) | 93.7(0.5)  | 92.8(0.5)  | 84.0(1.0)  | 50.8(4.0)  | 53.9(0.0) | 76.5(14.4) | 88.2(0.9) | 78.5(4.2)  | \n| NonInvasiveFatalECG\\_Thorax1    | 91.6(0.4) | 95.6(0.3)  | 94.5(0.3)  | 91.6(0.4)  | 16.1(29.3) | 2.9(0.0)  | 90.5(1.2)  | 86.5(0.5) | 49.4(4.2)  | \n| NonInvasiveFatalECG\\_Thorax2    | 91.7(0.3) | 95.3(0.3)  | 94.6(0.3)  | 93.2(0.9)  | 16.0(29.2) | 2.9(0.0)  | 91.5(1.5)  | 89.8(0.3) | 52.5(3.2)  | \n| OSULeaf                        | 55.7(1.0) | 97.7(0.9)  | 97.9(0.8)  | 57.6(2.0)  | 24.3(12.8) | 18.2(0.0) | 37.8(4.6)  | 46.2(2.7) | 59.5(5.4)  | \n| OliveOil                       | 66.7(3.8) | 72.3(16.6) | 83.0(8.5)  | 40.0(0.0)  | 38.0(4.2)  | 38.0(4.2) | 40.0(0.0)  | 40.0(0.0) | 79.0(6.1)  | \n| PhalangesOutlinesCorrect       | 73.5(2.1) | 82.0(0.5)  | 83.9(1.2)  | 76.7(1.4)  | 61.3(0.0)  | 61.3(0.0) | 80.3(1.1)  | 77.1(4.7) | 65.4(0.4)  | \n| Phoneme                        | 9.6(0.3)  | 32.5(0.5)  | 33.4(0.7)  | 17.2(0.8)  | 13.2(4.0)  | 11.3(0.0) | 13.0(1.0)  | 9.5(0.3)  | 12.8(1.4)  | \n| Plane                          | 97.8(0.5) | 100.0(0.0) | 100.0(0.0) | 97.6(0.8)  | 13.0(4.5)  | 13.4(1.4) | 96.5(3.2)  | 96.5(1.4) | 100.0(0.0) | \n| ProximalPhalanxOutlineAgeGroup | 85.6(0.5) | 83.1(1.3)  | 85.3(0.8)  | 84.4(1.3)  | 48.8(0.0)  | 48.8(0.0) | 83.8(0.8)  | 82.8(1.6) | 84.4(0.5)  | \n| ProximalPhalanxOutlineCorrect  | 73.3(1.8) | 90.3(0.7)  | 92.1(0.6)  | 79.1(1.8)  | 68.4(0.0)  | 68.4(0.0) | 87.3(1.8)  | 81.2(2.6) | 82.1(0.9)  | \n| ProximalPhalanxTW              | 76.7(0.7) | 76.7(0.9)  | 78.0(1.7)  | 81.2(1.1)  | 35.1(0.0)  | 34.6(1.0) | 79.7(1.3)  | 78.3(1.2) | 78.1(0.7)  | \n| RefrigerationDevices           | 37.9(2.1) | 50.8(1.0)  | 52.5(2.5)  | 48.8(1.9)  | 33.3(0.0)  | 33.3(0.0) | 36.9(3.8)  | 43.9(1.0) | 50.1(1.5)  | \n| ScreenType                     | 40.3(1.0) | 62.5(1.6)  | 62.2(1.4)  | 38.3(2.2)  | 34.1(2.4)  | 33.3(0.0) | 42.7(1.8)  | 38.9(0.9) | 43.1(4.7)  | \n| ShapeletSim                    | 50.3(3.1) | 72.4(5.6)  | 77.9(15.0) | 53.0(4.7)  | 50.0(0.0)  | 50.0(0.0) | 50.7(4.1)  | 50.0(1.3) | 61.7(10.2) | \n| ShapesAll                      | 77.1(0.5) | 89.5(0.4)  | 92.1(0.4)  | 75.8(0.9)  | 13.2(24.3) | 1.7(0.0)  | 61.3(5.3)  | 61.9(0.9) | 62.9(2.6)  | \n| SmallKitchenAppliances         | 37.1(1.9) | 78.3(1.3)  | 78.6(0.8)  | 59.6(1.8)  | 36.9(11.3) | 33.3(0.0) | 48.5(3.6)  | 61.5(2.7) | 65.6(1.9)  | \n| SonyAIBORobotSurface           | 67.2(1.3) | 96.0(0.7)  | 95.8(1.3)  | 74.3(1.9)  | 44.3(4.5)  | 42.9(0.0) | 65.3(10.9) | 68.7(2.3) | 63.8(9.9)  | \n| SonyAIBORobotSurfaceII         | 83.4(0.7) | 97.9(0.5)  | 97.8(0.5)  | 83.9(1.0)  | 59.4(7.4)  | 61.7(0.0) | 77.4(6.7)  | 84.1(1.7) | 69.7(4.3)  | \n| StarLightCurves                | 94.9(0.2) | 96.1(0.9)  | 97.2(0.3)  | 95.7(0.5)  | 65.4(16.1) | 57.7(0.0) | 93.9(1.2)  | 92.6(0.2) | 85.0(0.2)  | \n| Strawberry                     | 96.1(0.5) | 97.2(0.3)  | 98.1(0.4)  | 94.6(0.9)  | 64.3(0.0)  | 64.3(0.0) | 95.6(0.6)  | 95.9(0.3) | 89.5(2.0)  | \n| SwedishLeaf                    | 85.1(0.5) | 96.9(0.5)  | 95.6(0.4)  | 93.0(1.1)  | 11.8(13.2) | 6.5(0.4)  | 84.6(3.6)  | 88.4(1.1) | 82.5(1.4)  | \n| Symbols                        | 83.2(1.0) | 95.5(1.0)  | 90.6(2.3)  | 82.1(1.9)  | 22.6(16.9) | 17.4(0.0) | 75.6(11.5) | 81.0(0.7) | 75.0(8.8)  | \n| ToeSegmentation1               | 58.3(0.9) | 96.1(0.5)  | 96.3(0.6)  | 65.9(2.6)  | 50.5(2.7)  | 52.6(0.0) | 49.0(2.5)  | 59.5(2.2) | 86.5(3.2)  | \n| ToeSegmentation2               | 74.5(1.9) | 88.0(3.3)  | 90.6(1.7)  | 79.5(2.8)  | 63.2(30.9) | 81.5(0.0) | 44.3(15.2) | 73.8(2.8) | 84.2(4.6)  | \n| Trace                          | 80.7(0.7) | 100.0(0.0) | 100.0(0.0) | 96.0(1.8)  | 35.4(27.7) | 24.0(0.0) | 86.3(5.4)  | 95.0(2.5) | 95.9(1.9)  | \n| TwoLeadECG                     | 76.2(1.3) | 100.0(0.0) | 100.0(0.0) | 86.3(2.6)  | 50.0(0.0)  | 50.0(0.0) | 76.0(16.8) | 87.2(2.1) | 85.2(11.5) | \n| Two\\_Patterns                   | 94.6(0.3) | 87.1(0.3)  | 100.0(0.0) | 100.0(0.0) | 40.3(31.1) | 25.9(0.0) | 97.8(0.6)  | 99.2(0.3) | 87.1(1.1)  | \n| UWaveGestureLibraryAll         | 95.5(0.2) | 81.7(0.3)  | 86.0(0.4)  | 95.4(0.1)  | 28.9(34.7) | 12.8(0.2) | 92.9(1.1)  | 91.8(0.4) | 55.6(2.5)  | \n| Wine                           | 56.5(7.1) | 58.7(8.3)  | 74.4(8.5)  | 50.0(0.0)  | 50.0(0.0)  | 50.0(0.0) | 50.0(0.0)  | 51.7(5.1) | 75.9(9.1)  | \n| WordsSynonyms                  | 59.8(0.8) | 56.4(1.2)  | 62.2(1.5)  | 61.3(0.9)  | 28.4(13.6) | 21.9(0.0) | 46.3(6.1)  | 56.6(0.8) | 49.0(3.0)  | \n| Worms                          | 45.7(2.4) | 76.5(2.2)  | 79.1(2.5)  | 57.1(3.7)  | 42.9(0.0)  | 42.9(0.0) | 42.6(5.5)  | 38.3(2.5) | 46.6(4.5)  | \n| WormsTwoClass                  | 60.1(1.5) | 72.6(2.7)  | 74.7(3.3)  | 63.9(4.4)  | 57.1(0.0)  | 55.7(4.5) | 57.0(1.9)  | 53.8(2.6) | 57.0(2.3)  | \n| synthetic\\_control              | 97.6(0.4) | 98.5(0.3)  | 99.8(0.2)  | 99.6(0.3)  | 29.8(27.8) | 16.7(0.0) | 98.3(1.2)  | 99.0(0.4) | 87.4(1.6)  | \n| uWaveGestureLibrary\\_X          | 76.7(0.3) | 75.4(0.4)  | 78.0(0.4)  | 78.6(0.4)  | 18.9(21.3) | 12.5(0.4) | 71.1(1.5)  | 71.1(1.1) | 60.6(1.5)  | \n| uWaveGestureLibrary\\_Y          | 69.8(0.2) | 63.9(0.6)  | 67.0(0.7)  | 69.6(0.6)  | 23.7(24.0) | 12.1(0.0) | 63.6(1.2)  | 62.6(0.7) | 52.0(2.1)  | \n| uWaveGestureLibrary\\_Z          | 69.7(0.2) | 72.6(0.5)  | 75.0(0.4)  | 71.1(0.5)  | 18.0(18.4) | 12.1(0.0) | 65.0(1.8)  | 64.2(0.9) | 56.5(2.0)  | \n| wafer                          | 99.6(0.0) | 99.7(0.0)  | 99.9(0.1)  | 99.6(0.0)  | 91.3(4.4)  | 89.2(0.0) | 99.2(0.3)  | 96.1(0.1) | 91.4(0.5)  | \n| yoga                           | 85.5(0.4) | 83.9(0.7)  | 87.0(0.9)  | 82.0(0.6)  | 53.6(0.0)  | 53.6(0.0) | 76.2(3.9)  | 78.1(0.7) | 60.7(1.9)  | \n| **Average\\_Rank**               | 4.611765  | 2.682353   | 1.994118   | 3.682353   | 8.017647   | 8.417647  | 5.376471   | 4.970588  | 5.247059   | \n| **Wins**                       | 4         | 18         | 41         | 10         | 0          | 0         | 3          | 4         | 1          | \n\nThe following table contains the averaged accuracy over 10 runs of each implemented model on the MTS archive, with the standard deviation between parentheses. \n\n| Datasets              | MLP        | FCN        | ResNet     | Encoder    | MCNN      | t-LeNet    | MCDCNN     | Time-CNN   | TWIESN     | \n|-----------------------|------------|------------|------------|------------|-----------|------------|------------|------------|------------| \n| AUSLAN                | 93.3(0.5)  | 97.5(0.4)  | 97.4(0.3)  | 93.8(0.5)  | 1.1(0.0)  | 1.1(0.0)   | 85.4(2.7)  | 72.6(3.5)  | 72.4(1.6)  | \n| ArabicDigits          | 96.9(0.2)  | 99.4(0.1)  | 99.6(0.1)  | 98.1(0.1)  | 10.0(0.0) | 10.0(0.0)  | 95.9(0.2)  | 95.8(0.3)  | 85.3(1.4)  | \n| CMUsubject16          | 60.0(16.9) | 100.0(0.0) | 99.7(1.1)  | 98.3(2.4)  | 53.1(4.4) | 51.0(5.3)  | 51.4(5.0)  | 97.6(1.7)  | 89.3(6.8)  | \n| CharacterTrajectories | 96.9(0.2)  | 99.0(0.1)  | 99.0(0.2)  | 97.1(0.2)  | 5.4(0.8)  | 6.7(0.0)   | 93.8(1.7)  | 96.0(0.8)  | 92.0(1.3)  | \n| ECG                   | 74.8(16.2) | 87.2(1.2)  | 86.7(1.3)  | 87.2(0.8)  | 67.0(0.0) | 67.0(0.0)  | 50.0(17.9) | 84.1(1.7)  | 73.7(2.3)  | \n| JapaneseVowels        | 97.6(0.2)  | 99.3(0.2)  | 99.2(0.3)  | 97.6(0.6)  | 9.2(2.5)  | 23.8(0.0)  | 94.4(1.4)  | 95.6(1.0)  | 96.5(0.7)  | \n| KickvsPunch           | 61.0(12.9) | 54.0(13.5) | 51.0(8.8)  | 61.0(9.9)  | 54.0(9.7) | 50.0(10.5) | 56.0(8.4)  | 62.0(6.3)  | 67.0(14.2) | \n| Libras                | 78.0(1.0)  | 96.4(0.7)  | 95.4(1.1)  | 78.3(0.9)  | 6.7(0.0)  | 6.7(0.0)   | 65.1(3.9)  | 63.7(3.3)  | 79.4(1.3)  | \n| NetFlow               | 55.0(26.1) | 89.1(0.4)  | 62.7(23.4) | 77.7(0.5)  | 77.9(0.0) | 72.3(17.6) | 63.0(18.2) | 89.0(0.9)  | 94.5(0.4)  | \n| UWave                 | 90.1(0.3)  | 93.4(0.3)  | 92.6(0.4)  | 90.8(0.4)  | 12.5(0.0) | 12.5(0.0)  | 84.5(1.6)  | 85.9(0.7)  | 75.4(6.3)  | \n| Wafer                 | 89.4(0.0)  | 98.2(0.5)  | 98.9(0.4)  | 98.6(0.2)  | 89.4(0.0) | 89.4(0.0)  | 65.8(38.1) | 94.8(2.1)  | 94.9(0.6)  | \n| WalkvsRun             | 70.0(15.8) | 100.0(0.0) | 100.0(0.0) | 100.0(0.0) | 75.0(0.0) | 60.0(24.2) | 45.0(25.8) | 100.0(0.0) | 94.4(9.1)  | \n| **Average\\_Rank**          | 5.208333   | 2.000000   | 2.875000   | 3.041667   | 7.583333  | 8.000000   | 6.833333   | 4.625000   | 4.833333   | \n| **Wins**                  | 0          | 5          | 3          | 0          | 0         | 0          | 0          | 0          | 2          | \n\nThese results should give an insight of deep learning for TSC therefore encouraging researchers to consider the DNNs as robust classifiers for time series data. \n\nIf you would like to generate the critical difference diagrams using Wilcoxon Signed Rank test with Holm's alpha correction, check out [the cd-diagram repository](https:\u002F\u002Fgithub.com\u002Fhfawaz\u002Fcd-diagram). \n\n## Reference\n\nIf you re-use this work, please cite:\n\n```\n@article{IsmailFawaz2018deep,\n  Title                    = {Deep learning for time series classification: a review},\n  Author                   = {Ismail Fawaz, Hassan and Forestier, Germain and Weber, Jonathan and Idoumghar, Lhassane and Muller, Pierre-Alain},\n  journal                  = {Data Mining and Knowledge Discovery},\n  Year                     = {2019},\n  volume                   = {33},\n  number                   = {4},\n  pages                    = {917--963},\n}\n```\n## Acknowledgement\n\nWe would like to thank the providers of the [UCR\u002FUEA archive](http:\u002F\u002Ftimeseriesclassification.com\u002FTSC.zip). \nWe would also like to thank NVIDIA Corporation for the Quadro P6000 grant and the Mésocentre of Strasbourg for providing access to the cluster.\nWe would also like to thank [François Petitjean](https:\u002F\u002Fwww.francois-petitjean.com\u002F) and [Charlotte Pelletier](https:\u002F\u002Fsites.google.com\u002Fsite\u002Fcharpelletier\u002F) for the fruitful discussions, their feedback and comments while writing this paper.\n","# 时间序列分类的深度学习\n\n这是发表于 [Data Mining and Knowledge Discovery](https:\u002F\u002Flink.springer.com\u002Fjournal\u002F10618) 的 [我们论文](https:\u002F\u002Flink.springer.com\u002Farticle\u002F10.1007%2Fs10618-019-00619-1) 的配套代码库，论文题为“Deep learning for time series classification: a review”（时间序列分类的深度学习：综述），也可在 [ArXiv](https:\u002F\u002Farxiv.org\u002Fpdf\u002F1809.04356.pdf) 上获取。\n\n![architecture resnet](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fhfawaz_dl-4-tsc_readme_e0501925540d.png)\n\n## Docker\n\n假设您已经安装了 [docker](https:\u002F\u002Fhub.docker.com)。\n您现在可以使用 [此处](https:\u002F\u002Fhub.docker.com\u002Frepository\u002Fdocker\u002Fhassanfawaz\u002Fdl-4-tsc\u002Fgeneral) 提供的 Docker 镜像。\n\n通过以下方式访问 Docker 容器：\n\n```bash\ndocker run --name somename --gpus all  -idt hassanfawaz\u002Fdl-4-tsc:0.3\ndocker exec -it somename bash\n```\n\n要运行程序，您需要手动将 UCR 档案下载到 `\u002Fdl-4-tsc\u002Farchives\u002F` 目录中：\n\n```bash\ncd \u002Fdl-4-tsc\u002Farchives\nwget https:\u002F\u002Fwww.cs.ucr.edu\u002F~eamonn\u002Ftime_series_data_2018\u002FUCRArchive_2018.zip\nunzip -P $password UCRArchive_2018.zip\n```\n\n密码可以在 [这里](https:\u002F\u002Fwww.cs.ucr.edu\u002F~eamonn\u002Ftime_series_data_2018\u002F) 找到。\n\n既然您已经有了数据和代码，就可以直接运行代码了。\n\n```bash\ncd \u002Fdl-4-tsc\npython -m main UCRArchive_2018 Coffee fcn _itr_0\n```\n\n您也可以尝试在您的环境中使用 pip 进行安装。\n\n## 数据\n\n本项目使用的数据来自两个来源：\n* [UCR\u002FUEA archive](http:\u002F\u002Ftimeseriesclassification.com\u002FTSC.zip)，包含 85 个单变量时间序列数据集。\n* [MTS archive](http:\u002F\u002Fwww.mustafabaydogan.com\u002Ffiles\u002Fviewcategory\u002F20-data-sets.html)，包含 13 个多变量时间序列数据集。\n\n## 代码\n\n代码结构划分如下：\n* [main.py](https:\u002F\u002Fgithub.com\u002Fhfawaz\u002Fdl-4-tsc\u002Fblob\u002Fmaster\u002Fmain.py) Python 文件包含了运行实验所需的代码。\n* [utils](https:\u002F\u002Fgithub.com\u002Fhfawaz\u002Fdl-4-tsc\u002Ftree\u002Fmaster\u002Futils) 文件夹包含了读取数据集和可视化图表所需的函数。\n* [classifiers](https:\u002F\u002Fgithub.com\u002Fhfawaz\u002Fdl-4-tsc\u002Ftree\u002Fmaster\u002Fclassifiers) 文件夹包含九个 Python 文件，分别对应我们论文中测试的每个深度神经网络。\n\n要在单个数据集上运行模型，您应该执行以下命令：\n```\npython3 main.py TSC Coffee fcn _itr_8\n```\n这意味着我们要在单变量 UCR 档案的 Coffee 数据集上启动 [fcn](https:\u002F\u002Fgithub.com\u002Fhfawaz\u002Fdl-4-tsc\u002Fblob\u002Fmaster\u002Fclassifiers\u002Ffcn.py) 模型（可选列表请参见 [constants.py](https:\u002F\u002Fgithub.com\u002Fhfawaz\u002Fdl-4-tsc\u002Fblob\u002Fmaster\u002Futils\u002Fconstants.py)）。\n\n## 环境依赖\n\n所有需要的 Python 包都列在 [pip-requirements.txt](https:\u002F\u002Fgithub.com\u002Fhfawaz\u002Fdl-4-tsc\u002Fblob\u002Fmaster\u002Futils\u002Fpip-requirements.txt) 文件中，可以直接使用 pip 命令安装。\n代码目前使用 Tensorflow 2.0。\n论文中的结果是基于 Tensorflow 1.14 实现生成的，该版本可以在 [这里](https:\u002F\u002Fgithub.com\u002Fhfawaz\u002Fdl-4-tsc\u002Fcommit\u002F7ab94a02aedf3a9688e248603bd43c5d405f039b) 找到。\n使用 Tensorflow 2.0 应该能得到相同的结果。\n现在 [InceptionTime](https:\u002F\u002Fgithub.com\u002Fhfawaz\u002FInceptionTime) 也已包含在内，欢迎发送 pull request（合并请求）来添加其他分类器。\n\n* [numpy](http:\u002F\u002Fwww.numpy.org\u002F)\n* [pandas](https:\u002F\u002Fpandas.pydata.org\u002F)\n* [sklearn](http:\u002F\u002Fscikit-learn.org\u002Fstable\u002F)\n* [scipy](https:\u002F\u002Fwww.scipy.org\u002F)\n* [matplotlib](https:\u002F\u002Fmatplotlib.org\u002F)\n* [tensorflow-gpu](https:\u002F\u002Fwww.tensorflow.org\u002F)\n* [keras](https:\u002F\u002Fkeras.io\u002F)\n* [h5py](http:\u002F\u002Fdocs.h5py.org\u002Fen\u002Flatest\u002Fbuild.html)\n* [keras_contrib](https:\u002F\u002Fwww.github.com\u002Fkeras-team\u002Fkeras-contrib.git)\n\n## 结果\n\n我添加了来自 [UCR archive 2018](https:\u002F\u002Fwww.cs.ucr.edu\u002F~eamonn\u002Ftime_series_data_2018\u002F) 的 128 个数据集的 [结果](https:\u002F\u002Fgithub.com\u002Fhfawaz\u002Fdl-4-tsc\u002Fblob\u002Fmaster\u002Fresults\u002Fresults-ucr-128.csv)。\n我们论文中的 [结果](https:\u002F\u002Fgithub.com\u002Fhfawaz\u002Fdl-4-tsc\u002Ftree\u002Fmaster\u002Fresults) 表明，深度残差网络架构在时间序列分类任务中表现最佳。\n\n下表包含了在 UCR\u002FUEA 档案上每个实现模型运行 10 次的平均准确率，括号内为标准差。\n\n| 数据集 | MLP | FCN | ResNet | Encoder | MCNN | t-LeNet | MCDCNN | Time-CNN | TWIESN | \n|--------------------------------|-----------|------------|------------|------------|------------|-----------|------------|-----------|------------| \n| 50words | 68.4(7.1) | 62.7(6.1) | 74.0(1.5) | 72.3(1.0) | 22.0(24.3) | 12.5(0.0) | 58.9(5.3) | 62.1(1.0) | 49.6(2.6) | \n| Adiac | 39.7(1.9) | 84.4(0.7) | 82.9(0.6) | 48.4(2.5) | 2.2(0.6) | 2.0(0.0) | 61.0(8.7) | 37.9(2.0) | 41.6(4.5) | \n| ArrowHead | 77.8(1.2) | 84.3(1.5) | 84.5(1.2) | 80.4(2.9) | 33.9(4.7) | 30.3(0.0) | 68.5(6.7) | 72.3(2.6) | 65.9(9.4) | \n| Beef | 72.0(2.8) | 69.7(4.0) | 75.3(4.2) | 64.3(5.0) | 20.0(0.0) | 20.0(0.0) | 56.3(7.8) | 76.3(1.1) | 53.7(14.9) | \n| BeetleFly | 87.0(2.6) | 86.0(9.7) | 85.0(2.4) | 74.5(7.6) | 50.0(0.0) | 50.0(0.0) | 58.0(9.2) | 89.0(3.2) | 73.0(7.9) | \n| BirdChicken | 77.5(3.5) | 95.5(3.7) | 88.5(5.3) | 66.5(5.8) | 50.0(0.0) | 50.0(0.0) | 58.0(10.3) | 60.5(9.0) | 74.0(15.6) | \n| CBF | 87.2(0.7) | 99.4(0.1) | 99.5(0.3) | 94.7(1.2) | 33.2(0.1) | 33.2(0.1) | 82.0(20.5) | 95.7(1.0) | 89.0(4.9) | \n| Car | 76.7(2.6) | 90.5(1.4) | 92.5(1.4) | 75.8(2.0) | 24.0(2.7) | 31.7(0.0) | 73.0(3.0) | 78.2(1.2) | 78.3(4.0) | \n| ChlorineConcentration | 80.2(1.1) | 81.4(0.9) | 84.4(1.0) | 57.3(1.1) | 53.3(0.0) | 53.3(0.0) | 64.3(3.8) | 60.0(0.8) | 55.3(0.3) | \n| CinC\\_ECG\\_torso | 84.0(1.0) | 82.4(1.2) | 82.6(2.4) | 91.1(2.7) | 38.1(28.0) | 25.0(0.1) | 73.6(15.2) | 74.5(4.9) | 30.0(2.9) | \n| Coffee | 99.6(1.1) | 100.0(0.0) | 100.0(0.0) | 97.9(1.8) | 51.4(3.5) | 53.6(0.0) | 98.2(2.5) | 99.6(1.1) | 97.1(2.8) | \n| Computers | 56.3(1.6) | 82.2(1.0) | 81.5(1.2) | 57.4(2.2) | 52.2(4.8) | 50.0(0.0) | 55.9(3.3) | 54.8(1.5) | 62.9(4.1) | \n| Cricket\\_X | 59.1(1.1) | 79.2(0.7) | 79.1(0.6) | 69.4(1.6) | 18.9(23.8) | 7.4(0.0) | 49.5(5.3) | 55.2(2.9) | 62.2(2.1) | \n| Cricket\\_Y | 60.0(0.8) | 78.7(1.2) | 80.3(0.8) | 67.5(1.0) | 18.4(22.0) | 8.5(0.0) | 49.7(4.3) | 57.0(2.4) | 65.6(1.3) | \n| Cricket\\_Z | 61.7(0.8) | 81.1(1.0) | 81.2(1.4) | 69.2(1.0) | 18.3(24.4) | 6.2(0.0) | 49.8(3.6) | 48.8(2.8) | 62.2(2.3) | \n| DiatomSizeReduction | 91.0(1.4) | 31.3(3.6) | 30.1(0.2) | 91.3(1.8) | 30.1(0.7) | 30.1(0.0) | 70.3(28.9) | 95.4(0.7) | 88.0(6.6) | \n| DistalPhalanxOutlineAgeGroup | 65.7(1.1) | 71.0(1.3) | 71.7(1.3) | 73.7(1.6) | 46.8(0.0) | 44.6(2.3) | 74.4(2.2) | 75.2(1.4) | 71.0(2.1) | \n| DistalPhalanxOutlineCorrect | 72.6(1.3) | 76.0(1.5) | 77.1(1.0) | 74.1(1.4) | 58.3(0.0) | 58.3(0.0) | 75.3(1.8) | 75.9(2.0) | 71.3(1.0) | \n| DistalPhalanxTW | 61.7(1.3) | 69.0(2.1) | 66.5(1.6) | 68.8(1.6) | 30.2(0.0) | 28.3(0.7) | 67.7(1.8) | 67.3(2.8) | 60.9(3.0) | \n| ECG200 | 91.6(0.7) | 88.9(1.0) | 87.4(1.9) | 92.3(1.1) | 64.0(0.0) | 64.0(0.0) | 83.3(3.9) | 81.4(1.3) | 84.2(5.1) | \n| ECG5000 | 92.9(0.1) | 94.0(0.1) | 93.4(0.2) | 94.0(0.2) | 61.8(10.9) | 58.4(0.0) | 93.7(0.6) | 92.8(0.2) | 91.9(0.2) | \n| ECGFiveDays | 97.0(0.5) | 98.7(0.3) | 97.5(1.9) | 98.2(0.7) | 49.9(0.3) | 49.7(0.0) | 76.2(13.4) | 88.2(1.8) | 69.8(14.1) | \n| Earthquakes | 71.7(1.3) | 72.7(1.7) | 71.2(2.0) | 74.8(0.7) | 74.8(0.0) | 74.8(0.0) | 74.9(0.2) | 70.0(1.9) | 74.8(0.0) | \n| ElectricDevices | 59.2(1.1) | 70.2(1.2) | 72.9(0.9) | 67.4(1.1) | 33.6(19.8) | 24.2(0.0) | 64.4(1.2) | 68.1(1.0) | 60.7(0.7) | \n| FISH | 84.8(0.8) | 95.8(0.6) | 97.9(0.8) | 86.6(0.9) | 13.4(1.3) | 12.6(0.0) | 75.8(3.9) | 84.9(0.5) | 87.5(3.4) | \n| FaceAll | 79.3(1.1) | 94.5(0.9) | 83.9(2.0) | 79.3(0.8) | 17.0(19.5) | 8.0(0.0) | 71.7(2.3) | 76.8(1.1) | 65.7(2.5) | \n| FaceFour | 84.0(1.4) | 92.8(0.9) | 95.5(0.0) | 81.5(2.6) | 26.8(5.7) | 29.5(0.0) | 71.2(13.5) | 90.6(1.1) | 85.5(6.2) | \n| FacesUCR | 83.3(0.3) | 94.6(0.2) | 95.5(0.4) | 87.4(0.4) | 15.3(2.7) | 14.3(0.0) | 75.6(5.1) | 86.9(0.7) | 64.4(2.0) | \n| FordA | 73.0(0.4) | 90.4(0.2) | 92.0(0.4) | 92.3(0.3) | 51.3(0.0) | 51.0(0.8) | 79.5(2.6) | 88.1(0.7) | 52.8(2.1) | \n| FordB | 60.3(0.3) | 87.8(0.6) | 91.3(0.3) | 89.0(0.5) | 49.8(1.2) | 51.2(0.0) | 53.3(2.9) | 80.6(1.5) | 50.3(1.2) | \n| Gun\\_Point | 92.7(1.1) | 100.0(0.0) | 99.1(0.7) | 93.6(3.2) | 51.3(3.9) | 49.3(0.0) | 86.7(9.6) | 93.2(1.9) | 96.1(2.3) | \n| Ham | 69.1(1.4) | 71.8(1.4) | 75.7(2.7) | 72.7(1.2) | 50.6(1.4) | 51.4(0.0) | 73.3(4.2) | 71.1(2.0) | 72.3(6.3) | \n| HandOutlines | 91.8(0.5) | 80.6(7.9) | 91.1(1.4) | 89.9(2.3) | 64.1(0.0) | 64.1(0.0) | 90.9(0.6) | 88.8(1.2) | 66.0(0.7) | \n| Haptics | 43.3(1.4) | 48.0(2.4) | 51.9(1.2) | 42.7(1.6) | 20.9(3.5) | 20.8(0.0) | 40.4(3.3) | 36.6(2.4) | 40.4(4.5) | \n| Herring | 52.8(3.9) | 60.8(7.7) | 61.9(3.8) | 58.6(4.8) | 59.4(0.0) | 59.4(0.0) | 60.0(5.2) | 53.9(1.7) | 59.1(6.5) | \n| InlineSkate | 33.7(1.0) | 33.9(0.8) | 37.3(0.9) | 29.2(0.9) | 16.7(1.6) | 16.5(1.1) | 21.5(2.2) | 28.7(1.2) | 33.0(6.8) | \n| InsectWingbeatSound | 60.7(0.4) | 39.3(0.6) | 50.7(0.9) | 63.3(0.6) | 15.8(14.2) | 9.1(0.0) | 58.3(2.6) | 58.3(0.6) | 43.7(2.0) | \n| ItalyPowerDemand | 95.4(0.2) | 96.1(0.3) | 96.3(0.4) | 96.5(0.5) | 50.0(0.2) | 49.9(0.0) | 95.5(1.9) | 95.5(0.4) | 88.0(2.2) | \n| LargeKitchenAppliances | 47.3(0.6) | 90.2(0.4) | 90.0(0.5) | 61.9(2.6) | 41.0(16.5) | 33.3(0.0) | 43.4(2.8) | 66.6(5.0) | 77.9(1.8) | \n| Lighting2 | 67.0(2.1) | 73.9(1.4) | 77.0(1.7) | 69.2(4.6) | 55.7(5.2) | 54.1(0.0) | 63.0(5.9) | 63.6(2.5) | 70.3(4.1) | \n| Lighting7 | 63.0(1.7) | 82.7(2.3) | 84.5(2.0) | 62.5(2.3) | 31.0(11.3) | 26.0(0.0) | 53.4(5.9) | 65.1(3.3) | 66.4(6.6) | \n| MALLAT | 91.8(0.6) | 96.7(0.9) | 97.2(0.3) | 87.6(2.0) | 13.5(3.7) | 12.3(0.1) | 90.1(5.7) | 92.0(0.7) | 59.6(9.8) | \n| Meat | 89.7(1.7) | 85.3(6.9) | 96.8(2.5) | 74.2(11.0) | 33.3(0.0) | 33.3(0.0) | 70.5(8.8) | 90.2(1.8) | 96.8(2.0) | \n| MedicalImages | 72.1(0.7) | 77.9(0.4) | 77.0(0.7) | 73.4(1.5) | 51.4(0.0) | 51.4(0.0) | 64.0(1.4) | 67.6(1.1) | 64.9(2.7) | \n| MiddlePhalanxOutlineAgeGroup | 53.1(1.8) | 55.3(1.8) | 56.9(2.1) | 57.9(2.9) | 18.8(0.0) | 57.1(0.0) | 58.5(3.8) | 56.6(1.5) | 58.1(2.6) | \n| MiddlePhalanxOutlineCorrect | 77.0(1.1) | 80.1(1.0) | 80.9(1.2) | 76.1(2.3) | 57.0(0.0) | 57.0(0.0) | 81.1(1.6) | 76.6(1.3) | 74.4(2.3) | \n| MiddlePhalanxTW | 53.4(1.6) | 51.2(1.8) | 48.4(2.0) | 59.2(1.0) | 27.3(0.0) | 28.6(0.0) | 58.1(2.4) | 54.9(1.7) | 53.9(2.9) | \n| MoteStrain | 85.8(0.9) | 93.7(0.5) | 92.8(0.5) | 84.0(1.0) | 50.8(4.0) | 53.9(0.0) | 76.5(14.4) | 88.2(0.9) | 78.5(4.2) | \n| NonInvasiveFatalECG\\_Thorax1 | 91.6(0.4) | 95.6(0.3) | 94.5(0.3) | 91.6(0.4) | 16.1(29.3) | 2.9(0.0) | 90.5(1.2) | 86.5(0.5) | 49.4(4.2) | \n| NonInvasiveFatalECG\\_Thorax2 | 91.7(0.3) | 95.3(0.3) | 94.6(0.3) | 93.2(0.9) | 16.0(29.2) | 2.9(0.0) | 91.5(1.5) | 89.8(0.3) | 52.5(3.2) | \n| OSULeaf | 55.7(1.0) | 97.7(0.9) | 97.9(0.8) | 57.6(2.0) | 24.3(12.8) | 18.2(0.0) | 37.8(4.6) | 46.2(2.7) | 59.5(5.4) | \n| OliveOil | 66.7(3.8) | 72.3(16.6) | 83.0(8.5) | 40.0(0.0) | 38.0(4.2) | 38.0(4.2) | 40.0(0.0) | 40.0(0.0) | 79.0(6.1) | \n| PhalangesOutlinesCorrect | 73.5(2.1) | 82.0(0.5) | 83.9(1.2) | 76.7(1.4) | 61.3(0.0) | 61.3(0.0) | 80.3(1.1) | 77.1(4.7) | 65.4(0.4) | \n| Phoneme | 9.6(0.3) | 32.5(0.5) | 33.4(0.7) | 17.2(0.8) | 13.2(4.0) | 11.3(0.0) | 13.0(1.0) | 9.5(0.3) | 12.8(1.4) | \n| Plane | 97.8(0.5) | 100.0(0.0) | 100.0(0.0) | 97.6(0.8) | 13.0(4.5) | 13.4(1.4) | 96.5(3.2) | 96.5(1.4) | 100.0(0.0) | \n| ProximalPhalanxOutlineAgeGroup | 85.6(0.5) | 83.1(1.3) | 85.3(0.8) | 84.4(1.3) | 48.8(0.0) | 48.8(0.0) | 83.8(0.8) | 82.8(1.6) | 84.4(0.5) | \n| ProximalPhalanxOutlineCorrect | 73.3(1.8) | 90.3(0.7) | 92.1(0.6) | 79.1(1.8) | 68.4(0.0) | 68.4(0.0) | 87.3(1.8) | 81.2(2.6) | 82.1(0.9) | \n| ProximalPhalanxTW | 76.7(0.7) | 76.7(0.9) | 78.0(1.7) | 81.2(1.1) | 35.1(0.0) | 34.6(1.0) | 79.7(1.3) | 78.3(1.2) | 78.1(0.7) | \n| RefrigerationDevices | 37.9(2.1) | 50.8(1.0) | 52.5(2.5) | 48.8(1.9) | 33.3(0.0) | 33.3(0.0) | 36.9(3.8) | 43.9(1.0) | 50.1(1.5) | \n| ScreenType | 40.3(1.0) | 62.5(1.6) | 62.2(1.4) | 38.3(2.2) | 34.1(2.4) | 33.3(0.0) | 42.7(1.8) | 38.9(0.9) | 43.1(4.7) | \n| ShapeletSim | 50.3(3.1) | 72.4(5.6) | 77.9(15.0) | 53.0(4.7) | 50.0(0.0) | 50.0(0.0) | 50.7(4.1) | 50.0(1.3) | 61.7(10.2) | \n| ShapesAll | 77.1(0.5) | 89.5(0.4) | 92.1(0.4) | 75.8(0.9) | 13.2(24.3) | 1.7(0.0) | 61.3(5.3) | 61.9(0.9) | 62.9(2.6) | \n| SmallKitchenAppliances | 37.1(1.9) | 78.3(1.3) | 78.6(0.8) | 59.6(1.8) | 36.9(11.3) | 33.3(0.0) | 48.5(3.6) | 61.5(2.7) | 65.6(1.9) | \n| SonyAIBORobotSurface | 67.2(1.3) | 96.0(0.7) | 95.8(1.3) | 74.3(1.9) | 44.3(4.5) | 42.9(0.0) | 65.3(10.9) | 68.7(2.3) | 63.8(9.9) | \n| SonyAIBORobotSurfaceII | 83.4(0.7) | 97.9(0.5) | 97.8(0.5) | 83.9(1.0) | 59.4(7.4) | 61.7(0.0) | 77.4(6.7) | 84.1(1.7) | 69.7(4.3) | \n| StarLightCurves | 94.9(0.2) | 96.1(0.9) | 97.2(0.3) | 95.7(0.5) | 65.4(16.1) | 57.7(0.0) | 93.9(1.2) | 92.6(0.2) | 85.0(0.2) | \n| Strawberry | 96.1(0.5) | 97.2(0.3) | 98.1(0.4) | 94.6(0.9) | 64.3(0.0) | 64.3(0.0) | 95.6(0.6) | 95.9(0.3) | 89.5(2.0) | \n| SwedishLeaf | 85.1(0.5) | 96.9(0.5) | 95.6(0.4) | 93.0(1.1) | 11.8(13.2) | 6.5(0.4) | 84.6(3.6) | 88.4(1.1) | 82.5(1.4) | \n| Symbols | 83.2(1.0) | 95.5(1.0) | 90.6(2.3) | 82.1(1.9) | 22.6(16.9) | 17.4(0.0) | 75.6(11.5) | 81.0(0.7) | 75.0(8.8) | \n| ToeSegmentation1 | 58.3(0.9) | 96.1(0.5) | 96.3(0.6) | 65.9(2.6) | 50.5(2.7) | 52.6(0.0) | 49.0(2.5) | 59.5(2.2) | 86.5(3.2) | \n| ToeSegmentation2 | 74.5(1.9) | 88.0(3.3) | 90.6(1.7) | 79.5(2.8) | 63.2(30.9) | 81.5(0.0) | 44.3(15.2) | 73.8(2.8) | 84.2(4.6) | \n| Trace | 80.7(0.7) | 100.0(0.0) | 100.0(0.0) | 96.0(1.8) | 35.4(27.7) | 24.0(0.0) | 86.3(5.4) | 95.0(2.5) | 95.9(1.9) | \n| TwoLeadECG | 76.2(1.3) | 100.0(0.0) | 100.0(0.0) | 86.3(2.6) | 50.0(0.0) | 50.0(0.0) | 76.0(16.8) | 87.2(2.1) | 85.2(11.5) | \n| Two\\_Patterns | 94.6(0.3) | 87.1(0.3) | 100.0(0.0) | 100.0(0.0) | 40.3(31.1) | 25.9(0.0) | 97.8(0.6) | 99.2(0.3) | 87.1(1.1) | \n| UWaveGestureLibraryAll | 95.5(0.2) | 81.7(0.3) | 86.0(0.4) | 95.4(0.1) | 28.9(34.7) | 12.8(0.2) | 92.9(1.1) | 91.8(0.4) | 55.6(2.5) | \n| Wine | 56.5(7.1) | 58.7(8.3) | 74.4(8.5) | 50.0(0.0) | 50.0(0.0) | 50.0(0.0) | 50.0(0.0) | 51.7(5.1) | 75.9(9.1) | \n| WordsSynonyms | 59.8(0.8) | 56.4(1.2) | 62.2(1.5) | 61.3(0.9) | 28.4(13.6) | 21.9(0.0) | 46.3(6.1) | 56.6(0.8) | 49.0(3.0) | \n| Worms | 45.7(2.4) | 76.5(2.2) | 79.1(2.5) | 57.1(3.7) | 42.9(0.0) | 42.9(0.0) | 42.6(5.5) | 38.3(2.5) | 46.6(4.5) | \n| WormsTwoClass | 60.1(1.5) | 72.6(2.7) | 74.7(3.3) | 63.9(4.4) | 57.1(0.0) | 55.7(4.5) | 57.0(1.9) | 53.8(2.6) | 57.0(2.3) | \n| synthetic\\_control | 97.6(0.4) | 98.5(0.3) | 99.8(0.2) | 99.6(0.3) | 29.8(27.8) | 16.7(0.0) | 98.3(1.2) | 99.0(0.4) | 87.4(1.6) | \n| uWaveGestureLibrary\\_X | 76.7(0.3) | 75.4(0.4) | 78.0(0.4) | 78.6(0.4) | 18.9(21.3) | 12.5(0.4) | 71.1(1.5) | 71.1(1.1) | 60.6(1.5) | \n| uWaveGestureLibrary\\_Y | 69.8(0.2) | 63.9(0.6) | 67.0(0.7) | 69.6(0.6) | 23.7(24.0) | 12.1(0.0) | 63.6(1.2) | 62.6(0.7) | 52.0(2.1) | \n| uWaveGestureLibrary\\_Z | 69.7(0.2) | 72.6(0.5) | 75.0(0.4) | 71.1(0.5) | 18.0(18.4) | 12.1(0.0) | 65.0(1.8) | 64.2(0.9) | 56.5(2.0) | \n| wafer | 99.6(0.0) | 99.7(0.0) | 99.9(0.1) | 99.6(0.0) | 91.3(4.4) | 89.2(0.0) | 99.2(0.3) | 96.1(0.1) | 91.4(0.5) | \n| yoga | 85.5(0.4) | 83.9(0.7\n\n下表包含了在 MTS archive（多变量时间序列归档）上每个已实现模型运行 10 次的平均准确率，括号内为标准差。\n\n| Datasets              | MLP        | FCN        | ResNet     | Encoder    | MCNN      | t-LeNet    | MCDCNN     | Time-CNN   | TWIESN     | \n|-----------------------|------------|------------|------------|------------|-----------|------------|------------|------------|------------| \n| AUSLAN                | 93.3(0.5)  | 97.5(0.4)  | 97.4(0.3)  | 93.8(0.5)  | 1.1(0.0)  | 1.1(0.0)   | 85.4(2.7)  | 72.6(3.5)  | 72.4(1.6)  | \n| ArabicDigits          | 96.9(0.2)  | 99.4(0.1)  | 99.6(0.1)  | 98.1(0.1)  | 10.0(0.0) | 10.0(0.0)  | 95.9(0.2)  | 95.8(0.3)  | 85.3(1.4)  | \n| CMUsubject16          | 60.0(16.9) | 100.0(0.0) | 99.7(1.1)  | 98.3(2.4)  | 53.1(4.4) | 51.0(5.3)  | 51.4(5.0)  | 97.6(1.7)  | 89.3(6.8)  | \n| CharacterTrajectories | 96.9(0.2)  | 99.0(0.1)  | 99.0(0.2)  | 97.1(0.2)  | 5.4(0.8)  | 6.7(0.0)   | 93.8(1.7)  | 96.0(0.8)  | 92.0(1.3)  | \n| ECG                   | 74.8(16.2) | 87.2(1.2)  | 86.7(1.3)  | 87.2(0.8)  | 67.0(0.0) | 67.0(0.0)  | 50.0(17.9) | 84.1(1.7)  | 73.7(2.3)  | \n| JapaneseVowels        | 97.6(0.2)  | 99.3(0.2)  | 99.2(0.3)  | 97.6(0.6)  | 9.2(2.5)  | 23.8(0.0)  | 94.4(1.4)  | 95.6(1.0)  | 96.5(0.7)  | \n| KickvsPunch           | 61.0(12.9) | 54.0(13.5) | 51.0(8.8)  | 61.0(9.9)  | 54.0(9.7) | 50.0(10.5) | 56.0(8.4)  | 62.0(6.3)  | 67.0(14.2) | \n| Libras                | 78.0(1.0)  | 96.4(0.7)  | 95.4(1.1)  | 78.3(0.9)  | 6.7(0.0)  | 6.7(0.0)   | 65.1(3.9)  | 63.7(3.3)  | 79.4(1.3)  | \n| NetFlow               | 55.0(26.1) | 89.1(0.4)  | 62.7(23.4) | 77.7(0.5)  | 77.9(0.0) | 72.3(17.6) | 63.0(18.2) | 89.0(0.9)  | 94.5(0.4)  | \n| UWave                 | 90.1(0.3)  | 93.4(0.3)  | 92.6(0.4)  | 90.8(0.4)  | 12.5(0.0) | 12.5(0.0)  | 84.5(1.6)  | 85.9(0.7)  | 75.4(6.3)  | \n| Wafer                 | 89.4(0.0)  | 98.2(0.5)  | 98.9(0.4)  | 98.6(0.2)  | 89.4(0.0) | 89.4(0.0)  | 65.8(38.1) | 94.8(2.1)  | 94.9(0.6)  | \n| WalkvsRun             | 70.0(15.8) | 100.0(0.0) | 100.0(0.0) | 100.0(0.0) | 75.0(0.0) | 60.0(24.2) | 45.0(25.8) | 100.0(0.0) | 94.4(9.1)  | \n| **平均排名**          | 5.208333   | 2.000000   | 2.875000   | 3.041667   | 7.583333  | 8.000000   | 6.833333   | 4.625000   | 4.833333   | \n| **获胜次数**          | 0          | 5          | 3          | 0          | 0         | 0          | 0          | 0          | 2          | \n\n这些结果应能为 TSC（时间序列分类）的深度学习提供见解，从而鼓励研究人员将 DNNs（深度神经网络）视为时间序列数据的鲁棒分类器。\n\n如果您想使用 Wilcoxon Signed Rank test（威尔科克森符号秩检验）配合 Holm's alpha correction（Holm's alpha 校正）来生成 critical difference diagrams（临界差异图），请查看 [cd-diagram 仓库](https:\u002F\u002Fgithub.com\u002Fhfawaz\u002Fcd-diagram)。\n\n## 参考文献\n\n如果您重新使用这项工作，请引用：\n\n```\n@article{IsmailFawaz2018deep,\n  Title                    = {Deep learning for time series classification: a review},\n  Author                   = {Ismail Fawaz, Hassan and Forestier, Germain and Weber, Jonathan and Idoumghar, Lhassane and Muller, Pierre-Alain},\n  journal                  = {Data Mining and Knowledge Discovery},\n  Year                     = {2019},\n  volume                   = {33},\n  number                   = {4},\n  pages                    = {917--963},\n}\n```\n\n## 致谢\n\n我们要感谢 [UCR\u002FUEA archive](http:\u002F\u002Ftimeseriesclassification.com\u002FTSC.zip) 的提供者。\n我们还要感谢 NVIDIA Corporation 提供的 Quadro P6000 资助，以及斯特拉斯堡 Mésocentre 提供的集群访问权限。\n我们还要感谢 [François Petitjean](https:\u002F\u002Fwww.francois-petitjean.com\u002F) 和 [Charlotte Pelletier](https:\u002F\u002Fsites.google.com\u002Fsite\u002Fcharpelletier\u002F) 在撰写本文期间进行的富有成效的讨论、反馈和评论。","# dl-4-tsc 快速上手指南\n\n## 1. 环境准备\n\n**系统要求：**\n*   推荐使用支持 NVIDIA GPU 的环境，以加速深度学习模型训练。\n*   需安装 Docker（推荐方式）或配置本地 Python 环境。\n\n**主要依赖：**\n*   TensorFlow 2.0\n*   Keras\n*   numpy, pandas, scikit-learn, scipy, matplotlib, h5py\n\n## 2. 安装步骤\n\n### 方式一：使用 Docker（推荐）\n\n此方式环境配置最简单，无需手动安装依赖。\n\n1.  **启动容器**\n    拉取镜像并启动容器（确保已安装 NVIDIA Container Toolkit 以支持 GPU）：\n    ```bash\n    docker run --name somename --gpus all  -idt hassanfawaz\u002Fdl-4-tsc:0.3\n    docker exec -it somename bash\n    ```\n\n2.  **下载数据集**\n    进入容器后，需手动下载 UCR 数据集并解压。解压密码可在 [UCR 官网](https:\u002F\u002Fwww.cs.ucr.edu\u002F~eamonn\u002Ftime_series_data_2018\u002F) 找到。\n    ```bash\n    cd \u002Fdl-4-tsc\u002Farchives\n    wget https:\u002F\u002Fwww.cs.ucr.edu\u002F~eamonn\u002Ftime_series_data_2018\u002FUCRArchive_2018.zip\n    unzip -P $password UCRArchive_2018.zip\n    ```\n\n### 方式二：本地源码安装\n\n1.  **克隆代码**\n    ```bash\n    git clone https:\u002F\u002Fgithub.com\u002Fhfawaz\u002Fdl-4-tsc.git\n    cd dl-4-tsc\n    ```\n\n2.  **安装依赖**\n    建议使用国内镜像源加速安装：\n    ```bash\n    pip install -r utils\u002Fpip-requirements.txt -i https:\u002F\u002Fpypi.tuna.tsinghua.edu.cn\u002Fsimple\n    ```\n\n## 3. 基本使用\n\n本项目支持多种模型（如 FCN, ResNet, MLP 等），以下演示如何运行模型进行时间序列分类。\n\n**运行示例：**\n\n*   **Docker 环境下运行：**\n    在 Coffee 数据集上运行 FCN 模型：\n    ```bash\n    cd \u002Fdl-4-tsc\n    python -m main UCRArchive_2018 Coffee fcn _itr_0\n    ```\n\n*   **本地环境运行：**\n    在 TSC 数据集上运行 FCN 模型：\n    ```bash\n    python3 main.py TSC Coffee fcn _itr_8\n    ```\n\n**参数说明：**\n*   参数1：数据集存档名称（如 `UCRArchive_2018` 或 `TSC`）。\n*   参数2：具体数据集名称（如 `Coffee`，完整列表见 `utils\u002Fconstants.py`）。\n*   参数3：模型名称（可选 `fcn`, `resnet`, `mlp`, `encoder` 等）。\n*   参数4：迭代索引标识。","某工业物联网公司的算法工程师小李，正在开发一套电机故障诊断系统，需要根据传感器采集的振动波形数据，准确判断电机是处于正常运行状态还是发生了轴承故障。\n\n### 没有 dl-4-tsc 时\n- 必须花费大量时间进行繁琐的手动特征工程（如计算均值、方差、频谱特征），且特征提取效果高度依赖专家经验，泛化能力差。\n- 尝试从零编写深度学习模型（如 ResNet）时，经常因网络结构细节或超参数设置不当导致模型无法收敛，调试成本极高。\n- 缺乏统一的基准参考，难以判断自己训练的模型准确率是否达到了业界合格标准，对模型上线缺乏信心。\n\n### 使用 dl-4-tsc 后\n- 直接调用 dl-4-tsc 提供的 FCN 或 ResNet 等模型，无需人工提取特征，网络能自动从原始时间序列中学习深层特征，显著提升泛化性。\n- 利用仓库中现成的 SOTA（State-of-the-art）算法实现，只需简单命令即可切换不同模型架构，快速找到最适合当前数据的算法。\n- 通过 Docker 一键部署环境，并参考内置的 UCR 数据集基准测试结果，能迅速验证模型性能，确保算法达到学术界最佳实践水平。\n\ndl-4-tsc 将时间序列分类从繁琐的特征工程转变为高效的端到端学习，让工程师能快速复现学术界最前沿成果，大幅缩短了工业故障诊断模型的落地周期。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fhfawaz_dl-4-tsc_1f8aea2b.png","hfawaz","Hassan ISMAIL FAWAZ","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002Fhfawaz_45b5b112.png","Machine Learning Researcher - PhD in Data Science and Artificial Intelligence.","Beyond Limits","Dhahran","hassanismailfawaz@gmail.com","hassanfawaz93","hfawaz.github.io","https:\u002F\u002Fgithub.com\u002Fhfawaz",[86],{"name":87,"color":88,"percentage":89},"Python","#3572A5",100,1657,597,"2026-03-07T14:48:11","GPL-3.0","Linux, Windows, macOS","需要 NVIDIA GPU（依赖 tensorflow-gpu），具体型号、显存及 CUDA 版本未说明","未说明",{"notes":98,"python":99,"dependencies":100},"1. 官方提供 Docker 镜像，推荐使用 Docker 环境运行；2. 运行前需手动下载 UCR 数据集并解压到指定目录；3. 代码已迁移至 Tensorflow 2.0，论文原结果基于 Tensorflow 1.14；4. 依赖库 keras-contrib 需从 GitHub 安装。","Python 3.x（具体版本未说明，基于 Tensorflow 2.0 兼容性推测需 3.5-3.7）",[101,102,103,104,105,106,107,108,109],"tensorflow-gpu","keras","numpy","pandas","scikit-learn","scipy","matplotlib","h5py","keras-contrib",[13,54],[112,113,114,115,116,117,118],"deep-learning","deep-neural-networks","time-series-classification","review","empirical-research","research-paper","convolutional-neural-networks",null,"2026-03-27T02:49:30.150509","2026-04-06T07:15:04.234496",[123,128,133,138,143,148,153],{"id":124,"question_zh":125,"answer_zh":126,"source_url":127},1694,"如何加载多变量时间序列（MTS）数据集？","推荐使用 `aeon` 库来加载 MTS 数据集。该库是一个用于时间序列机器学习的 Python 包，包含了本仓库模型的实现。加载示例代码如下：\n```python\nfrom aeon.datasets import load_classification\ndataset_name = \"Libras\"\nxtrain, ytrain = load_classification(dataset_name, split=\"train\")\n```","https:\u002F\u002Fgithub.com\u002Fhfawaz\u002Fdl-4-tsc\u002Fissues\u002F35",{"id":129,"question_zh":130,"answer_zh":131,"source_url":132},1695,"如何运行 MTS 数据集的处理命令？","你需要运行 `transform_mts_to_ucr` 脚本来准备 .mat 格式的数据集。该脚本会在 `mts_out_dir` 指定的目录下创建 .npy 格式的数据集存档。如果遇到目录未创建的问题，请检查代码中是否存在用于调试的 `continue` 语句（例如在第 190 行），将其移除或手动创建所需的文件夹结构。","https:\u002F\u002Fgithub.com\u002Fhfawaz\u002Fdl-4-tsc\u002Fissues\u002F1",{"id":134,"question_zh":135,"answer_zh":136,"source_url":137},1696,"模型训练中如何处理验证集？代码中似乎缺少验证数据集。","目前的模型实现中未使用验证集，且超参数是固定的（这确实不是最优的）。建议从训练集中随机划分一部分作为验证集，或者使用交叉验证来确定最佳模型。","https:\u002F\u002Fgithub.com\u002Fhfawaz\u002Fdl-4-tsc\u002Fissues\u002F51",{"id":139,"question_zh":140,"answer_zh":141,"source_url":142},1697,"运行 MCNN 模型时报错 'AttributeError: Tensor object has no attribute assign' 怎么办？","这通常是由于 TensorFlow 或 Keras 版本不兼容导致的。本仓库代码基于较旧的框架版本编写，建议检查并调整环境版本，或者修改 `MCNN.py` 中的代码逻辑以适配你当前使用的 TensorFlow 版本。","https:\u002F\u002Fgithub.com\u002Fhfawaz\u002Fdl-4-tsc\u002Fissues\u002F2",{"id":144,"question_zh":145,"answer_zh":146,"source_url":147},1698,"运行 FCN 分类器时提示找不到 'best_model.hdf5' 文件怎么办？","对于某些特定数据集（如 DodgerLoopDay），它们可能包含缺失值或变长数据。请检查下载的 UCR 存档中是否有名为 \"Missing_value_and_variable_length_datasets_adjusted\" 的文件夹，使用其中经过调整的数据集版本即可解决此问题。","https:\u002F\u002Fgithub.com\u002Fhfawaz\u002Fdl-4-tsc\u002Fissues\u002F21",{"id":149,"question_zh":150,"answer_zh":151,"source_url":152},1699,"在多变量数据上使用类激活图（CAM）时遇到 reshape 错误怎么办？","当前的架构设计不支持为多变量数据的每个通道单独生成类激活图。如果你修改了输入数据的 reshape 逻辑以适配多变量数据，需要注意模型架构本身的限制，可能无法直接获得每个通道的独立可视化结果。","https:\u002F\u002Fgithub.com\u002Fhfawaz\u002Fdl-4-tsc\u002Fissues\u002F4",{"id":154,"question_zh":155,"answer_zh":156,"source_url":157},1700,"如何将深度学习模型与传统方法（如 SVM）进行比较或利用预训练？","SVM 被认为是一个很强的基准线，性能接近 Rotation Forest。如果你想尝试预训练网络，可以参考相关论文（如 arXiv:1805.03908），通过融合不同的 TSC 数据集进行多类分类预训练，然后尝试使用 ResNet 等架构进行微调以查看性能变化。","https:\u002F\u002Fgithub.com\u002Fhfawaz\u002Fdl-4-tsc\u002Fissues\u002F5",[]]