[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tool-astorfi--TensorFlow-World":3,"similar-astorfi--TensorFlow-World":105},{"id":4,"github_repo":5,"name":6,"description_en":7,"description_zh":8,"ai_summary_zh":8,"readme_en":9,"readme_zh":10,"quickstart_zh":11,"use_case_zh":12,"hero_image_url":13,"owner_login":14,"owner_name":15,"owner_avatar_url":16,"owner_bio":17,"owner_company":18,"owner_location":19,"owner_email":20,"owner_twitter":21,"owner_website":22,"owner_url":23,"languages":24,"stars":37,"forks":38,"last_commit_at":39,"license":40,"difficulty_score":41,"env_os":42,"env_gpu":43,"env_ram":43,"env_deps":44,"category_tags":50,"github_topics":53,"view_count":41,"oss_zip_url":21,"oss_zip_packed_at":21,"status":60,"created_at":61,"updated_at":62,"faqs":63,"releases":99},7780,"astorfi\u002FTensorFlow-World","TensorFlow-World",":earth_americas: Simple and ready-to-use tutorials for TensorFlow","TensorFlow-World 是一个专为 TensorFlow 打造的开源教程仓库，致力于提供简单易懂、即拿即用的学习资源。面对深度学习框架功能强大但入门门槛较高的问题，尤其是 TensorFlow 高度模块化设计让初学者容易感到困惑，该项目通过结构化的实战案例填补了这一空白。\n\n每个教程都包含了完整的源代码和配套的详细文档，并托管在项目的 Wiki 中，帮助用户从零开始理解模型构建的每一个细节。它不仅涵盖了基础算法实现，还展示了如何利用高级 API 简化开发流程，让用户能快速上手并复现经典架构。\n\n无论是刚接触深度学习的学生、希望快速验证想法的研究人员，还是寻求工程落地的开发者，都能从中受益。如果你正在寻找一条清晰的学习路径，或者需要参考高质量的代码范例来加速项目进展，TensorFlow-World 都是一个值得信赖的起点。其社区驱动的模式也确保了内容能紧跟技术前沿，持续更新以适配最新的框架特性。","  \n********************\n`TensorFlow World`_\n********************\n.. image:: https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcontributions-welcome-brightgreen.svg?style=flat\n    :target: https:\u002F\u002Fgithub.com\u002Fastorfi\u002FTensorFlow-World\u002Fissues\n.. image:: https:\u002F\u002Fbadges.frapsoft.com\u002Fos\u002Fv2\u002Fopen-source.svg?v=102\n    :target: https:\u002F\u002Fgithub.com\u002Fellerbrock\u002Fopen-source-badge\u002F\n.. image:: https:\u002F\u002Fcoveralls.io\u002Frepos\u002Fgithub\u002Fastorfi\u002FTensorFlow-World\u002Fbadge.svg?branch=master\n    :target: https:\u002F\u002Fcoveralls.io\u002Fgithub\u002Fastorfi\u002FTensorFlow-World?branch=master\n.. image:: https:\u002F\u002Fzenodo.org\u002Fbadge\u002F86115145.svg\n   :target: https:\u002F\u002Fzenodo.org\u002Fbadge\u002Flatestdoi\u002F86115145\n.. image:: https:\u002F\u002Fimg.shields.io\u002Ftwitter\u002Ffollow\u002Famirsinatorfi.svg?label=Follow&style=social\n      :target: https:\u002F\u002Ftwitter.com\u002Famirsinatorfi\n\n.. _TensorFlow World: http:\u002F\u002Ftensorflow-world.readthedocs.io\u002Fen\u002Flatest\u002F\n\nTo support maintaining and upgrading this project, please kindly consider `Sponsoring the project developer \u003Chttps:\u002F\u002Fgithub.com\u002Fsponsors\u002Fastorfi\u002Fdashboard>`_.\n\nAny level of support is a great contribution here :heart:\n\n.. raw:: html\n\n   \u003Cdiv align=\"center\">\n\n.. raw:: html\n\n \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fastorfi\u002Fdashboard\" target=\"_blank\">\n  \u003Cimg width=\"600\" height=\"500\" align=\"center\" src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fastorfi_TensorFlow-World_readme_f47972565d7a.jpg\"\u002F>\n \u003C\u002Fa>\n\n.. raw:: html\n\n   \u003C\u002Fdiv>  \n\nThis repository aims to provide simple and ready-to-use tutorials for TensorFlow. The explanations are present in the wiki_ associated with this repository.\n\nEach tutorial includes ``source code`` and associated ``documentation``.\n\n.. The links.\n.. _wiki: https:\u002F\u002Fgithub.com\u002Fastorfi\u002FTensorFlow-World\u002Fwiki\n.. _TensorFlow: https:\u002F\u002Fwww.tensorflow.org\u002Finstall\u002F\n\n\n.. raw:: html\n\n   \u003Cdiv align=\"center\">\n\n.. raw:: html\n\n \u003Ca href=\"http:\u002F\u002Fwww.machinelearningmindset.com\u002Ftensorflow-roadmap-ebook\u002F\" target=\"_blank\">\n  \u003Cimg width=\"850\" height=\"600\" align=\"center\" src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fastorfi_TensorFlow-World_readme_1bb1678f6fbd.png\"\u002F>\n \u003C\u002Fa>\n\n.. raw:: html\n\n   \u003C\u002Fdiv>\n   \n###################################################\nSlack Group\n###################################################\n\n.. raw:: html\n\n   \u003Cdiv align=\"center\">\n\n.. raw:: html\n\n \u003Ca href=\"https:\u002F\u002Fwww.machinelearningmindset.com\u002Fslack-group\u002F\" target=\"_blank\">\n  \u003Cimg width=\"1033\" height=\"350\" align=\"center\" src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fastorfi_TensorFlow-World_readme_2f07fac72f26.png\"\u002F>\n \u003C\u002Fa>\n\n.. raw:: html\n\n   \u003C\u002Fdiv>\n\n#################\nTable of Contents\n#################\n.. contents::\n  :local:\n  :depth: 3\n\n============\nMotivation\n============\n\nThere are different motivations for this open source project. TensorFlow (as we write this document) is one of \u002F the best deep learning frameworks available. The question that should be asked is why has this repository been created when there are so many other tutorials about TensorFlow available on the web?\n\n~~~~~~~~~~~~~~~~~~~~~\nWhy use TensorFlow?\n~~~~~~~~~~~~~~~~~~~~~\n\nDeep Learning is in very high interest these days - there's a crucial need for rapid and optimized implementations of the algorithms and architectures. TensorFlow is designed to facilitate this goal.\n\nThe strong advantage of TensorFlow is it flexibility in designing highly modular models which can also be a disadvantage for beginners since a lot of the pieces must be considered together when creating the model.\n\nThis issue has been facilitated as well by developing high-level APIs such as `Keras \u003Chttps:\u002F\u002Fkeras.io\u002F>`_ and `Slim \u003Chttps:\u002F\u002Fgithub.com\u002Ftensorflow\u002Fmodels\u002Fblob\u002Fmaster\u002Finception\u002Finception\u002Fslim\u002FREADME.md\u002F\u002F>`_ which abstract a lot of the pieces used in designing machine learning algorithms.\n\nThe interesting thing about TensorFlow is that **it can be found anywhere these days**. Lots of the researchers and developers are using it and *its community is growing at the speed of light*! So many issues can be dealt with easily since they're usually the same issues that a lot of other people run into considering the large number of people involved in the TensorFlow community.\n\n~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\nWhat's the point of this repository?\n~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n\n**Developing open source projects for the sake of just developing something is not the reason behind this effort**.\nConsidering the large number of tutorials that are being added to this large community, this repository has been created to break the jump-in and jump-out process that usually happens to most of the open source projects, **but why and how**?\n\nFirst of all, what's the point of putting effort into something that most of the people won't stop by and take a look? What's the point of creating something that does not help anyone in the developers and researchers community? Why spend time for something that can easily be forgotten? But **how we try to do it?** Even up to this\nvery moment there are countless tutorials on TensorFlow whether on the model design or TensorFlow\nworkflow.\n\nMost of them are too complicated or suffer from a lack of documentation. There are only a few available tutorials which are concise and well-structured and provide enough insight for their specific implemented models.\n\nThe goal of this project is to help the community with structured tutorials and simple and optimized code implementations to provide better insight about how to use TensorFlow *quick and effectively*.\n\nIt is worth noting that, **the main goal of this project is to provide well-documented tutorials and less-complicated code**!\n\n=================================================\nTensorFlow Installation and Setup the Environment\n=================================================\n\n.. image:: _img\u002Fmainpage\u002Finstallation-logo.gif\n   :height: 100px\n   :width: 200 px\n   :scale: 50 %\n   :alt: alternate text\n   :align: right\n   :target: https:\u002F\u002Fgithub.com\u002Fastorfi\u002FTensorFlow-World\u002Ftree\u002Fmaster\u002Fdocs\u002Ftutorials\u002Finstallation\n\n.. _TensorFlow Installation: https:\u002F\u002Fgithub.com\u002Fastorfi\u002FTensorFlow-World\u002Ftree\u002Fmaster\u002Fdocs\u002Ftutorials\u002Finstallation\n\nIn order to install TensorFlow please refer to the following link:\n\n  * `TensorFlow Installation`_\n\n\n.. image:: _img\u002Fmainpage\u002Finstallation.gif\n    :target: https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=_3JFEPk4qQY&t=2s\n\nThe virtual environment installation is recommended in order to prevent package conflict and having the capacity to customize the working environment.\n\n====================\nTensorFlow Tutorials\n====================\n\nThe tutorials in this repository are partitioned into relevant categories.\n\n==========================\n\n~~~~~~~~\nWarm-up\n~~~~~~~~\n\n.. image:: _img\u002Fmainpage\u002Fwelcome.gif\n   :height: 100px\n   :width: 200 px\n   :scale: 50 %\n   :alt: alternate text\n   :align: right\n\n+----+---------------------+----------------------------------------------------------------------------------------+----------------------------------------------+\n| #  |       topic         |   Source Code                                                                          |                                              |\n+====+=====================+========================================================================================+==============================================+\n| 1  | Start-up            | `Welcome \u003Cwelcomesourcecode_>`_  \u002F `IPython \u003Cipythonwelcome_>`_                        |  `Documentation \u003CDocumentationcnnwelcome_>`_ |\n+----+---------------------+----------------------------------------------------------------------------------------+----------------------------------------------+\n\n==========================\n\n~~~~~~\nBasics\n~~~~~~\n\n.. image:: _img\u002Fmainpage\u002Fbasics.gif\n   :height: 100px\n   :width: 200 px\n   :scale: 50 %\n   :alt: alternate text\n   :align: right\n\n+----+---------------------+----------------------------------------------------------------------------------------+----------------------------------------------+\n| #  |       topic         |   Source Code                                                                          |                                              |\n+====+=====================+========================================================================================+==============================================+\n| 2  | *TensorFLow Basics* | `Basic Math Operations \u003Cbasicmathsourcecode_>`_   \u002F `IPython \u003Cipythonbasicmath_>`_     |  `Documentation \u003CDocumentationbasicmath_>`_  |\n+----+---------------------+----------------------------------------------------------------------------------------+----------------------------------------------+\n| 3  | *TensorFLow Basics* | `TensorFlow Variables \u003Cvariablssourcecode_>`_   \u002F `IPython \u003Cipythonvariabls_>`_        |  `Documentation \u003CDocumentationvariabls_>`_   |\n+----+---------------------+----------------------------------------------------------------------------------------+----------------------------------------------+\n\n==========================\n\n~~~~~~~~~~~~~~~~~~~~~~\nBasic Machine Learning\n~~~~~~~~~~~~~~~~~~~~~~\n\n.. image:: _img\u002Fmainpage\u002Fbasicmodels.gif\n   :height: 100px\n   :width: 200 px\n   :scale: 50 %\n   :alt: alternate text\n   :align: right\n\n+----+----------------------------+----------------------------------------------------------------------------------------+----------------------------------------------+\n| #  |       topic                |   Source Code                                                                          |                                              |\n+====+============================+========================================================================================+==============================================+\n| 4  | *Linear Models*            |`Linear Regression`_  \u002F `IPython \u003CLinearRegressionipython_>`_                           | `Documentation \u003CDocumentationlr_>`_          |\n+----+----------------------------+----------------------------------------------------------------------------------------+----------------------------------------------+\n| 5  | *Predictive Models*        | `Logistic Regression`_  \u002F `IPython \u003CLogisticRegressionipython_>`_                      | `Documentation \u003CLogisticRegDOC_>`_           |\n+----+----------------------------+----------------------------------------------------------------------------------------+----------------------------------------------+\n| 6  | *Support Vector Machines*  | `Linear SVM`_  \u002F `IPython \u003CLinearSVMipython_>`_                                        |                                              |\n+----+----------------------------+----------------------------------------------------------------------------------------+----------------------------------------------+\n| 7  | *Support Vector Machines*  |`MultiClass Kernel SVM`_  \u002F `IPython \u003CMultiClassKernelSVMipython_>`_                    |                                              |\n+----+----------------------------+----------------------------------------------------------------------------------------+----------------------------------------------+\n\n==========================\n\n~~~~~~~~~~~~~~~~\nNeural Networks\n~~~~~~~~~~~~~~~~\n\n.. image:: _img\u002Fmainpage\u002FCNNs.png\n   :height: 100px\n   :width: 200 px\n   :scale: 50 %\n   :alt: alternate text\n   :align: right\n\n+----+-----------------------------------+-----------------------------------------------------------------------------------------------+----------------------------------------------+\n| #  |       topic                       |   Source Code                                                                                 |                                              |\n+====+===================================+===============================================================================================+==============================================+\n| 8  | *Multi Layer Perceptron*          |`Simple Multi Layer Perceptron`_   \u002F `IPython \u003CMultiLayerPerceptronipython_>`_                 |                                              |\n+----+-----------------------------------+-----------------------------------------------------------------------------------------------+----------------------------------------------+\n| 9  | *Convolutional Neural Network*    | `Simple Convolutional Neural Networks`_                                                       |       `Documentation \u003CDocumentationcnn_>`_   |\n+----+-----------------------------------+-----------------------------------------------------------------------------------------------+----------------------------------------------+\n| 10 | *Autoencoder*                     | `Undercomplete Autoencoder \u003Cudercompleteautoencodercode_>`_                                   |       `Documentation \u003CDocumentationauto_>`_  |\n+----+-----------------------------------+-----------------------------------------------------------------------------------------------+----------------------------------------------+\n| 11 | *Recurrent Neural Network*        | `RNN`_  \u002F `IPython \u003CRNNIpython_>`_                                                            |                                              |\n+----+-----------------------------------+-----------------------------------------------------------------------------------------------+----------------------------------------------+\n\n\n.. ~~~~~~~~~~~~\n.. **Welcome**\n.. ~~~~~~~~~~~~\n\n.. The tutorial in this section is just a simple entrance to TensorFlow world.\n\n.. _welcomesourcecode: https:\u002F\u002Fgithub.com\u002Fastorfi\u002FTensorFlow-World\u002Ftree\u002Fmaster\u002Fcodes\u002F0-welcome\n.. _Documentationcnnwelcome: https:\u002F\u002Fgithub.com\u002Fastorfi\u002FTensorFlow-World\u002Fblob\u002Fmaster\u002Fdocs\u002Ftutorials\u002F0-welcome\n.. _ipythonwelcome: https:\u002F\u002Fgithub.com\u002Fastorfi\u002FTensorFlow-World\u002Fblob\u002Fmaster\u002Fcodes\u002F0-welcome\u002Fcode\u002F0-welcome.ipynb\n\n\n\n.. +---+---------------------------------------------+-------------------------------------------------+\n.. | # |          Source Code                        |                                                 |\n.. +===+=============================================+=================================================+\n.. | 1 |    `Welcome \u003Cwelcomesourcecode_>`_          |  `Documentation \u003CDocumentationcnnwelcome_>`_    |\n.. +---+---------------------------------------------+-------------------------------------------------+\n\n.. ~~~~~~~~~~\n.. **Basics**\n.. ~~~~~~~~~~\n.. These tutorials are related to basics of TensorFlow.\n\n.. _basicmathsourcecode: https:\u002F\u002Fgithub.com\u002Fastorfi\u002FTensorFlow-World\u002Ftree\u002Fmaster\u002Fcodes\u002F1-basics\u002Fbasic_math_operations\n.. _Documentationbasicmath: https:\u002F\u002Fgithub.com\u002Fastorfi\u002FTensorFlow-World\u002Fblob\u002Fmaster\u002Fdocs\u002Ftutorials\u002F1-basics\u002Fbasic_math_operations\n.. _ipythonbasicmath: https:\u002F\u002Fgithub.com\u002Fastorfi\u002FTensorFlow-World\u002Fblob\u002Fmaster\u002Fcodes\u002F1-basics\u002Fbasic_math_operations\u002Fcode\u002Fbasic_math_operation.ipynb\n\n.. _ipythonvariabls: https:\u002F\u002Fgithub.com\u002Fastorfi\u002FTensorFlow-World\u002Fblob\u002Fmaster\u002Fcodes\u002F1-basics\u002Fvariables\u002Fcode\u002Fvariables.ipynb\n.. _variablssourcecode: https:\u002F\u002Fgithub.com\u002Fastorfi\u002FTensorFlow-World\u002Fblob\u002Fmaster\u002Fcodes\u002F1-basics\u002Fvariables\u002FREADME.rst\n.. _Documentationvariabls: https:\u002F\u002Fgithub.com\u002Fastorfi\u002FTensorFlow-World\u002Fblob\u002Fmaster\u002Fdocs\u002Ftutorials\u002F1-basics\u002Fvariables\n\n\n.. +---+-----------------------------------------------------+-------------------------------------------------+\n.. | # |          Source Code                                |                                                 |\n.. +===+=====================================================+=================================================+\n.. | 1 |    `Basic Math Operations \u003Cbasicmathsourcecode_>`_  |  `Documentation \u003CDocumentationbasicmath_>`_     |\n.. +---+-----------------------------------------------------+-------------------------------------------------+\n.. | 2 |    `TensorFlow Variables \u003Cvariablssourcecode_>`_    |  `Documentation \u003CDocumentationvariabls_>`_      |\n.. +---+-----------------------------------------------------+-------------------------------------------------+\n\n.. ~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n.. **Machine Learning Basics**\n.. ~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n.. We are going to present concepts of basic machine learning models and methods and show how to implement them in Tensorflow.\n\n.. _Linear Regression: https:\u002F\u002Fgithub.com\u002Fastorfi\u002FTensorFlow-World\u002Ftree\u002Fmaster\u002Fcodes\u002F2-basics_in_machine_learning\u002Flinear_regression\n.. _LinearRegressionipython: https:\u002F\u002Fgithub.com\u002Fastorfi\u002FTensorFlow-World\u002Ftree\u002Fmaster\u002Fcodes\u002F2-basics_in_machine_learning\u002Flinear_regression\u002Fcode\u002Flinear_regression.ipynb\n.. _Documentationlr: https:\u002F\u002Fwww.machinelearningmindset.com\u002Flinear-regression-with-tensorflow\u002F\n\n.. _Logistic Regression: https:\u002F\u002Fgithub.com\u002Fastorfi\u002FTensorFlow-World\u002Ftree\u002Fmaster\u002Fcodes\u002F2-basics_in_machine_learning\u002Flogistic_regression\n.. _LogisticRegressionipython: https:\u002F\u002Fgithub.com\u002Fastorfi\u002FTensorFlow-World\u002Ftree\u002Fmaster\u002Fcodes\u002F2-basics_in_machine_learning\u002Flogistic_regression\u002Fcode\u002Flogistic_regression.ipynb\n.. _LogisticRegDOC: https:\u002F\u002Fgithub.com\u002Fastorfi\u002FTensorFlow-World\u002Ftree\u002Fmaster\u002Fdocs\u002Ftutorials\u002F2-basics_in_machine_learning\u002Flogistic_regression\n\n.. _Linear SVM: https:\u002F\u002Fgithub.com\u002Fastorfi\u002FTensorFlow-World\u002Ftree\u002Fmaster\u002Fcodes\u002F2-basics_in_machine_learning\u002Flinear_svm\n.. _LinearSVMipython: https:\u002F\u002Fgithub.com\u002Fastorfi\u002FTensorFlow-World\u002Ftree\u002Fmaster\u002Fcodes\u002F2-basics_in_machine_learning\u002Flinear_svm\u002Fcode\u002Flinear_svm.ipynb\n\n\n.. _MultiClass Kernel SVM: https:\u002F\u002Fgithub.com\u002Fastorfi\u002FTensorFlow-World\u002Fblob\u002Fmaster\u002Fcodes\u002F2-basics_in_machine_learning\u002Fmulticlass_svm\n.. _MultiClassKernelSVMipython: https:\u002F\u002Fgithub.com\u002Fastorfi\u002FTensorFlow-World\u002Fblob\u002Fmaster\u002Fcodes\u002F2-basics_in_machine_learning\u002Fmulticlass_svm\u002Fcode\u002Fmulticlass_svm.ipynb\n\n\n.. +---+---------------------------------------------+----------------------------------------+\n.. | # |          Source Code                        |                                        |\n.. +===+=============================================+========================================+\n.. | 1 |    `Linear Regression`_                     |  `Documentation \u003CDocumentationlr_>`_   |\n.. +---+---------------------------------------------+----------------------------------------+\n.. | 2 |    `Logistic Regression`_                   |  `Documentation \u003CLogisticRegDOC_>`_    |\n.. +---+---------------------------------------------+----------------------------------------+\n.. | 3 |    `Linear SVM`_                            |                                        |\n.. +---+---------------------------------------------+----------------------------------------+\n.. | 4 |    `MultiClass Kernel SVM`_                 |                                        |\n\n.. ~~~~~~~~~~~~~~~~~~~\n.. **Neural Networks**\n.. ~~~~~~~~~~~~~~~~~~~\n.. The tutorials in this section are related to neural network architectures.\n\n.. _Simple Convolutional Neural Networks: https:\u002F\u002Fgithub.com\u002Fastorfi\u002FTensorFlow-World\u002Ftree\u002Fmaster\u002Fcodes\u002F3-neural_networks\u002Fconvolutional-neural-network\n.. _Documentationcnn: https:\u002F\u002Fgithub.com\u002Fastorfi\u002FTensorFlow-World\u002Fblob\u002Fmaster\u002Fdocs\u002Ftutorials\u002F3-neural_network\u002Fconvolutiona_neural_network\n\n.. _Simple Multi Layer Perceptron: https:\u002F\u002Fgithub.com\u002Fastorfi\u002FTensorFlow-World\u002Fblob\u002Fmaster\u002Fcodes\u002F3-neural_networks\u002Fmulti-layer-perceptron\n.. _MultiLayerPerceptronipython: https:\u002F\u002Fgithub.com\u002Fastorfi\u002FTensorFlow-World\u002Fblob\u002Fmaster\u002Fcodes\u002F3-neural_networks\u002Fmulti-layer-perceptron\u002Fcode\u002Ftrain_mlp.ipynb\n\n\n.. _udercompleteautoencodercode: https:\u002F\u002Fgithub.com\u002Fastorfi\u002FTensorFlow-World\u002Ftree\u002Fmaster\u002Fcodes\u002F3-neural_networks\u002Fundercomplete-autoencoder\n.. _Documentationauto: https:\u002F\u002Fgithub.com\u002Fastorfi\u002FTensorFlow-World\u002Ftree\u002Fmaster\u002Fdocs\u002Ftutorials\u002F3-neural_network\u002Fautoencoder\n\n.. _RNN: codes\u002F3-neural_networks\u002Frecurrent-neural-networks\u002Fcode\u002Frnn.py\n.. _RNNIpython: codes\u002F3-neural_networks\u002Frecurrent-neural-networks\u002Fcode\u002Frnn.py\n\n\n.. +---+---------------------------------------------+----------------------------------------+\n.. | # |          Source Code                        |                                        |\n.. +===+=============================================+========================================+\n.. | 1 |    `Multi Layer Perceptron`_                |                                        |\n.. +---+---------------------------------------------+----------------------------------------+\n.. | 2 |    `Convolutional Neural Networks`_         |  `Documentation \u003CDocumentationcnn_>`_  |\n.. +---+---------------------------------------------+----------------------------------------+\n\n\n=====================\nSome Useful Tutorials\n=====================\n\n  * `TensorFlow Examples \u003Chttps:\u002F\u002Fgithub.com\u002Faymericdamien\u002FTensorFlow-Examples>`_ - TensorFlow tutorials and code examples for beginners\n  * `Sungjoon's TensorFlow-101 \u003Chttps:\u002F\u002Fgithub.com\u002Fsjchoi86\u002FTensorflow-101>`_ - TensorFlow tutorials written in Python with Jupyter Notebook\n  * `Terry Um’s TensorFlow Exercises \u003Chttps:\u002F\u002Fgithub.com\u002Fterryum\u002FTensorFlow_Exercises>`_ - Re-create the codes from other TensorFlow examples\n  * `Classification on time series \u003Chttps:\u002F\u002Fgithub.com\u002Fguillaume-chevalier\u002FLSTM-Human-Activity-Recognition>`_ - Recurrent Neural Network classification in TensorFlow with LSTM on cellphone sensor data\n\n=============\nContributing\n=============\n\nWhen contributing to this repository, please first discuss the change you wish to make via issue,\nemail, or any other method with the owners of this repository before making a change. *For typos, please\ndo not create a pull request. Instead, declare them in issues or email the repository owner*.\n\nPlease note we have a code of conduct, please follow it in all your interactions with the project.\n\n~~~~~~~~~~~~~~~~~~~~\nPull Request Process\n~~~~~~~~~~~~~~~~~~~~\n\nPlease consider the following criterions in order to help us in a better way:\n\n  * The pull request is mainly expected to be a code script suggestion or improvement.\n  * A pull request related to non-code-script sections is expected to make a significant difference in the documentation. Otherwise, it is expected to be announced in the issues section.\n  * Ensure any install or build dependencies are removed before the end of the layer when doing a build and creating a pull request.\n  * Add comments with details of changes to the interface, this includes new environment variables, exposed ports, useful file locations and container parameters.\n  * You may merge the Pull Request in once you have the sign-off of at least one other developer, or if you do not have permission to do that, you may request the owner to merge it for you if you believe all checks are passed.\n\n\n~~~~~~~~~~~\nFinal Note\n~~~~~~~~~~~\n\nWe are looking forward to your kind feedback. Please help us to improve this open source project and make our work better.\nFor contribution, please create a pull request and we will investigate it promptly. Once again, we appreciate\nyour kind feedback and elaborate code inspections.\n\n================\nAcknowledgement\n================\n\nI have taken huge efforts in this project for hopefully being a small part of TensorFlow world. However, it would not have been plausible without the kind support and help of my friend and colleague `Domenick Poster \u003Chttps:\u002F\u002Fgithub.com\u002Fvonclites\u002F>`_ for his valuable advices. He helped me for having a better understanding of TensorFlow and my special appreciation goes to him.\n","********************\n`TensorFlow世界`_\n********************\n.. image:: https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcontributions-welcome-brightgreen.svg?style=flat\n    :target: https:\u002F\u002Fgithub.com\u002Fastorfi\u002FTensorFlow-World\u002Fissues\n.. image:: https:\u002F\u002Fbadges.frapsoft.com\u002Fos\u002Fv2\u002Fopen-source.svg?v=102\n    :target: https:\u002F\u002Fgithub.com\u002Fellerbrock\u002Fopen-source-badge\u002F\n.. image:: https:\u002F\u002Fcoveralls.io\u002Frepos\u002Fgithub\u002Fastorfi\u002FTensorFlow-World\u002Fbadge.svg?branch=master\n    :target: https:\u002F\u002Fcoveralls.io\u002Fgithub\u002Fastorfi\u002FTensorFlow-World?branch=master\n.. image:: https:\u002F\u002Fzenodo.org\u002Fbadge\u002F86115145.svg\n   :target: https:\u002F\u002Fzenodo.org\u002Fbadge\u002Flatestdoi\u002F86115145\n.. image:: https:\u002F\u002Fimg.shields.io\u002Ftwitter\u002Ffollow\u002Famirsinatorfi.svg?label=Follow&style=social\n      :target: https:\u002F\u002Ftwitter.com\u002Famirsinatorfi\n\n.. _TensorFlow世界: http:\u002F\u002Ftensorflow-world.readthedocs.io\u002Fen\u002Flatest\u002F\n\n为了支持本项目的维护与升级，请您考虑`赞助项目开发者 \u003Chttps:\u002F\u002Fgithub.com\u002Fsponsors\u002Fastorfi\u002Fdashboard>`_。\n\n无论何种程度的支持，都是对本项目的巨大贡献 :heart:\n\n.. raw:: html\n\n   \u003Cdiv align=\"center\">\n\n.. raw:: html\n\n \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fsponsors\u002Fastorfi\u002Fdashboard\" target=\"_blank\">\n  \u003Cimg width=\"600\" height=\"500\" align=\"center\" src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fastorfi_TensorFlow-World_readme_f47972565d7a.jpg\"\u002F>\n \u003C\u002Fa>\n\n.. raw:: html\n\n   \u003C\u002Fdiv>  \n\n本仓库旨在为 TensorFlow 提供简单易用的教程。相关说明均在本仓库附带的维基中。\n\n每个教程都包含``源代码``和相应的``文档``。\n\n.. 链接。\n.. _wiki: https:\u002F\u002Fgithub.com\u002Fastorfi\u002FTensorFlow-World\u002Fwiki\n.. _TensorFlow: https:\u002F\u002Fwww.tensorflow.org\u002Finstall\u002F\n\n\n.. raw:: html\n\n   \u003Cdiv align=\"center\">\n\n.. raw:: html\n\n \u003Ca href=\"http:\u002F\u002Fwww.machinelearningmindset.com\u002Ftensorflow-roadmap-ebook\u002F\" target=\"_blank\">\n  \u003Cimg width=\"850\" height=\"600\" align=\"center\" src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fastorfi_TensorFlow-World_readme_1bb1678f6fbd.png\"\u002F>\n \u003C\u002Fa>\n\n.. raw:: html\n\n   \u003C\u002Fdiv>\n   \n###################################################\nSlack 群组\n###################################################\n\n.. raw:: html\n\n   \u003Cdiv align=\"center\">\n\n.. raw:: html\n\n \u003Ca href=\"https:\u002F\u002Fwww.machinelearningmindset.com\u002Fslack-group\u002F\" target=\"_blank\">\n  \u003Cimg width=\"1033\" height=\"350\" align=\"center\" src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fastorfi_TensorFlow-World_readme_2f07fac72f26.png\"\u002F>\n \u003C\u002Fa>\n\n.. raw:: html\n\n   \u003C\u002Fdiv}\n\n#################\n目录\n#################\n.. contents::\n  :local:\n  :depth: 3\n\n============\n动机\n============\n\n这个开源项目有多种动机。TensorFlow（截至本文撰写时）是目前最好的深度学习框架之一。那么问题来了：既然网络上已有大量关于 TensorFlow 的教程，为什么还要创建这个仓库呢？\n\n~~~~~~~~~~~~~~~~~~~~~\n为什么要使用 TensorFlow？\n~~~~~~~~~~~~~~~~~~~~~\n\n如今，深度学习备受关注——人们迫切需要快速且优化的算法与架构实现。而 TensorFlow 正是为了满足这一需求而设计的。\n\nTensorFlow 的一大优势在于其灵活性，能够构建高度模块化的模型；但这也可能成为初学者的劣势，因为搭建模型时需要综合考虑许多细节。\n\n不过，通过开发诸如 `Keras \u003Chttps:\u002F\u002Fkeras.io\u002F>`_ 和 `Slim \u003Chttps:\u002F\u002Fgithub.com\u002Ftensorflow\u002Fmodels\u002Fblob\u002Fmaster\u002Finception\u002Finception\u002Fslim\u002FREADME.md\u002F\u002F>`_ 等高层 API，已经大大简化了这一过程，这些 API 抽象掉了机器学习算法设计中的许多复杂部分。\n\n有趣的是，**TensorFlow 如今几乎无处不在**。众多研究人员和开发者都在使用它，而且它的社区正以惊人的速度增长！由于参与 TensorFlow 社区的人数众多，许多常见问题都能轻松得到解决。\n\n~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n这个仓库的意义何在？\n~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n\n**仅仅为了开发而开发开源项目，并不是我们开展这项工作的初衷**。\n尽管有大量的教程不断涌入这个庞大的社区，但我们创建这个仓库的目的，正是为了打破大多数开源项目常见的“启动后很快停滞”的现象，**那么为什么以及如何做到这一点呢？**\n\n首先，如果大多数人不会驻足浏览，那投入精力又有何意义呢？如果所创建的内容无法帮助开发者和研究人员群体，又有什么价值呢？为何要花费时间去做一件很容易被遗忘的事情呢？然而，**我们究竟该如何实现呢？** 即便到目前为止，关于 TensorFlow 的教程依然数不胜数，涵盖模型设计和 TensorFlow 工作流等多个方面。\n\n但其中大部分要么过于复杂，要么缺乏足够的文档说明。真正简洁明了、结构清晰，并能深入讲解特定实现模型的教程却寥寥无几。\n\n本项目的目标就是通过结构化、简洁且优化的代码实现，为社区提供更好的指导，帮助大家*快速有效地*掌握 TensorFlow 的使用方法。\n\n值得注意的是，**本项目的核心目标是提供文档完善、代码简化的教程**！\n\n=================================================\nTensorFlow 安装与环境配置\n=================================================\n\n.. image:: _img\u002Fmainpage\u002Finstallation-logo.gif\n   :height: 100px\n   :width: 200 px\n   :scale: 50 %\n   :alt: 替代文本\n   :align: 右侧\n   :target: https:\u002F\u002Fgithub.com\u002Fastorfi\u002FTensorFlow-World\u002Ftree\u002Fmaster\u002Fdocs\u002Ftutorials\u002Finstallation\n\n.. _TensorFlow安装: https:\u002F\u002Fgithub.com\u002Fastorfi\u002FTensorFlow-World\u002Ftree\u002Fmaster\u002Fdocs\u002Ftutorials\u002Finstallation\n\n要安装 TensorFlow，请参考以下链接：\n\n  * `TensorFlow安装`_\n\n\n.. image:: _img\u002Fmainpage\u002Finstallation.gif\n    :target: https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=_3JFEPk4qQY&t=2s\n\n建议使用虚拟环境进行安装，以避免软件包冲突，并便于自定义工作环境。\n\n====================\nTensorFlow教程\n====================\n\n本仓库中的教程按相关主题分类。\n\n==========================\n\n~~~~~~~~\n热身\n~~~~~~~~\n\n.. image:: _img\u002Fmainpage\u002Fwelcome.gif\n   :height: 100px\n   :width: 200 px\n   :scale: 50 %\n   :alt: 替代文本\n   :align: 右侧\n\n+----+---------------------+----------------------------------------------------------------------------------------+----------------------------------------------+\n| #  |       topic         |   Source Code                                                                          |                                              |\n+====+=====================+========================================================================================+==============================================+\n| 1  | 启动                | `欢迎 \u003Cwelcomesourcecode_>`_  \u002F `IPython \u003Cipythonwelcome_>`_                        |  `文档 \u003CDocumentationcnnwelcome_>`_          |\n+----+---------------------+----------------------------------------------------------------------------------------+----------------------------------------------+\n\n==========================\n\n~~~~~~\n基础\n~~~~~~\n\n.. image:: _img\u002Fmainpage\u002Fbasics.gif\n   :height: 100px\n   :width: 200 px\n   :scale: 50 %\n   :alt: 替代文本\n   :align: right\n\n+----+---------------------+----------------------------------------------------------------------------------------+----------------------------------------------+\n| #  |       topic         |   Source Code                                                                          |                                              |\n+====+=====================+========================================================================================+==============================================+\n| 2  | *TensorFlow 基础*   | `基本数学运算 \u003Cbasicmathsourcecode_>`_   \u002F `IPython \u003Cipythonbasicmath_>`_     |  `文档 \u003CDocumentationbasicmath_>`_          |\n+----+---------------------+----------------------------------------------------------------------------------------+----------------------------------------------+\n| 3  | *TensorFlow 基础*   | `TensorFlow 变量 \u003Cvariablssourcecode_>`_   \u002F `IPython \u003Cipythonvariabls_>`_        |  `文档 \u003CDocumentationvariabls_>`_           |\n+----+---------------------+----------------------------------------------------------------------------------------+----------------------------------------------+\n\n==========================\n\n~~~~~~~~~~~~~~~~~~~~~~\n基础机器学习\n~~~~~~~~~~~~~~~~~~~~~~\n\n.. image:: _img\u002Fmainpage\u002Fbasicmodels.gif\n   :height: 100px\n   :width: 200 px\n   :scale: 50 %\n   :alt: 替代文本\n   :align: right\n\n+----+----------------------------+----------------------------------------------------------------------------------------+----------------------------------------------+\n| #  |       topic                |   Source Code                                                                          |                                              |\n+====+============================+========================================================================================+==============================================+\n| 4  | *线性模型*            |`线性回归`_  \u002F `IPython \u003CLinearRegressionipython_>`_                           | `文档 \u003CDocumentationlr_>`_                  |\n+----+----------------------------+----------------------------------------------------------------------------------------+----------------------------------------------+\n| 5  | *预测模型*        | `逻辑回归`_  \u002F `IPython \u003CLogisticRegressionipython_>`_                      | `文档 \u003CLogisticRegDOC_>`_                   |\n+----+----------------------------+----------------------------------------------------------------------------------------+----------------------------------------------+\n| 6  | *支持向量机*  | `线性 SVM`_  \u002F `IPython \u003CLinearSVMipython_>`_                                        |                                              |\n+----+----------------------------+----------------------------------------------------------------------------------------+----------------------------------------------+\n| 7  | *支持向量机*  |`多分类核 SVM`_  \u002F `IPython \u003CMultiClassKernelSVMipython_>`_                    |                                              |\n+----+----------------------------+----------------------------------------------------------------------------------------+----------------------------------------------+\n\n==========================\n\n~~~~~~~~~~~~~~~~\n神经网络\n~~~~~~~~~~~~~~~~\n\n.. image:: _img\u002Fmainpage\u002FCNNs.png\n   :height: 100px\n   :width: 200 px\n   :scale: 50 %\n   :alt: 替代文本\n   :align: right\n\n+----+-----------------------------------+-----------------------------------------------------------------------------------------------+----------------------------------------------+\n| #  |       topic                       |   Source Code                                                                                 |                                              |\n+====+===================================+===============================================================================================+==============================================+\n| 8  | *多层感知器*          |`简单多层感知器`_   \u002F `IPython \u003CMultiLayerPerceptronipython_>`_                 |                                              |\n+----+-----------------------------------+-----------------------------------------------------------------------------------------------+----------------------------------------------+\n| 9  | *卷积神经网络*    | `简单卷积神经网络`_                                                       |       `文档 \u003CDocumentationcnn_>`_           |\n+----+-----------------------------------+-----------------------------------------------------------------------------------------------+----------------------------------------------+\n| 10 | *自编码器*                     | `欠完备自编码器 \u003Cudercompleteautoencodercode_>`_                                   |       `文档 \u003CDocumentationauto_>`_  |\n+----+-----------------------------------+-----------------------------------------------------------------------------------------------+----------------------------------------------+\n| 11 | *循环神经网络*        | `RNN`_  \u002F `IPython \u003CRNNIpython_>`_                                                            |                                              |\n+----+-----------------------------------+-----------------------------------------------------------------------------------------------+----------------------------------------------+\n\n\n.. ~~~~~~~~~~~~\n.. **欢迎**\n.. ~~~~~~~~~~~~\n\n.. 本节教程只是进入 TensorFlow 世界的一个简单入口。\n\n.. _welcomesourcecode: https:\u002F\u002Fgithub.com\u002Fastorfi\u002FTensorFlow-World\u002Ftree\u002Fmaster\u002Fcodes\u002F0-welcome\n.. _Documentationcnnwelcome: https:\u002F\u002Fgithub.com\u002Fastorfi\u002FTensorFlow-World\u002Fblob\u002Fmaster\u002Fdocs\u002Ftutorials\u002F0-welcome\n.. _ipythonwelcome: https:\u002F\u002Fgithub.com\u002Fastorfi\u002FTensorFlow-World\u002Fblob\u002Fmaster\u002Fcodes\u002F0-welcome\u002Fcode\u002F0-welcome.ipynb\n\n.. +---+---------------------------------------------+-------------------------------------------------+\n.. | # |          源代码                        |                                                 |\n.. +===+=============================================+=================================================+\n.. | 1 |    `欢迎 \u003Cwelcomesourcecode_>`_          |  `文档 \u003CDocumentationcnnwelcome_>`_    |\n.. +---+---------------------------------------------+-------------------------------------------------+\n\n.. ~~~~~~~~~~\n.. **基础**\n.. ~~~~~~~~~~\n.. 这些教程与 TensorFlow 的基础知识相关。\n\n.. _basicmathsourcecode: https:\u002F\u002Fgithub.com\u002Fastorfi\u002FTensorFlow-World\u002Ftree\u002Fmaster\u002Fcodes\u002F1-basics\u002Fbasic_math_operations\n.. _Documentationbasicmath: https:\u002F\u002Fgithub.com\u002Fastorfi\u002FTensorFlow-World\u002Fblob\u002Fmaster\u002Fdocs\u002Ftutorials\u002F1-basics\u002Fbasic_math_operations\n.. _ipythonbasicmath: https:\u002F\u002Fgithub.com\u002Fastorfi\u002FTensorFlow-World\u002Fblob\u002Fmaster\u002Fcodes\u002F1-basics\u002Fbasic_math_operations\u002Fcode\u002Fbasic_math_operation.ipynb\n\n.. _ipythonvariabls: https:\u002F\u002Fgithub.com\u002Fastorfi\u002FTensorFlow-World\u002Fblob\u002Fmaster\u002Fcodes\u002F1-basics\u002Fvariables\u002Fcode\u002Fvariables.ipynb\n.. _variablssourcecode: https:\u002F\u002Fgithub.com\u002Fastorfi\u002FTensorFlow-World\u002Fblob\u002Fmaster\u002Fcodes\u002F1-basics\u002Fvariables\u002FREADME.rst\n.. _Documentationvariabls: https:\u002F\u002Fgithub.com\u002Fastorfi\u002FTensorFlow-World\u002Fblob\u002Fmaster\u002Fdocs\u002Ftutorials\u002F1-basics\u002Fvariables\n\n\n.. +---+-----------------------------------------------------+-------------------------------------------------+\n.. | # |          源代码                                |                                                 |\n.. +===+=====================================================+=================================================+\n.. | 1 |    `基础数学运算 \u003Cbasicmathsourcecode_>`_  |  `文档 \u003CDocumentationbasicmath_>`_     |\n.. +---+-----------------------------------------------------+-------------------------------------------------+\n.. | 2 |    `TensorFlow 变量 \u003Cvariablssourcecode_>`_    |  `文档 \u003CDocumentationvariabls_>`_      |\n.. +---+-----------------------------------------------------+-------------------------------------------------+\n\n.. ~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n.. **机器学习基础**\n.. ~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n.. 我们将介绍基本的机器学习模型和方法，并展示如何在 TensorFlow 中实现它们。\n\n.. _线性回归: https:\u002F\u002Fgithub.com\u002Fastorfi\u002FTensorFlow-World\u002Ftree\u002Fmaster\u002Fcodes\u002F2-basics_in_machine_learning\u002Flinear_regression\n.. _线性回归IPython: https:\u002F\u002Fgithub.com\u002Fastorfi\u002FTensorFlow-World\u002Ftree\u002Fmaster\u002Fcodes\u002F2-basics_in_machine_learning\u002Flinear_regression\u002Fcode\u002Flinear_regression.ipynb\n.. _线性回归文档: https:\u002F\u002Fwww.machinelearningmindset.com\u002Flinear-regression-with-tensorflow\u002F\n\n.. _逻辑回归: https:\u002F\u002Fgithub.com\u002Fastorfi\u002FTensorFlow-World\u002Ftree\u002Fmaster\u002Fcodes\u002F2-basics_in_machine_learning\u002Flogistic_regression\n.. _逻辑回归IPython: https:\u002F\u002Fgithub.com\u002Fastorfi\u002FTensorFlow-World\u002Ftree\u002Fmaster\u002Fcodes\u002F2-basics_in_machine_learning\u002Flogistic_regression\u002Fcode\u002Flogistic_regression.ipynb\n.. _逻辑回归文档: https:\u002F\u002Fgithub.com\u002Fastorfi\u002FTensorFlow-World\u002Ftree\u002Fmaster\u002Fdocs\u002Ftutorials\u002F2-basics_in_machine_learning\u002Flogistic_regression\n\n.. _线性支持向量机: https:\u002F\u002Fgithub.com\u002Fastorfi\u002FTensorFlow-World\u002Ftree\u002Fmaster\u002Fcodes\u002F2-basics_in_machine_learning\u002Flinear_svm\n.. _线性支持向量机IPython: https:\u002F\u002Fgithub.com\u002Fastorfi\u002FTensorFlow-World\u002Ftree\u002Fmaster\u002Fcodes\u002F2-basics_in_machine_learning\u002Flinear_svm\u002Fcode\u002Flinear_svm.ipynb\n\n\n.. _多分类核支持向量机: https:\u002F\u002Fgithub.com\u002Fastorfi\u002FTensorFlow-World\u002Fblob\u002Fmaster\u002Fcodes\u002F2-basics_in_machine_learning\u002Fmulticlass_svm\n.. _多分类核支持向量机IPython: https:\u002F\u002Fgithub.com\u002Fastorfi\u002FTensorFlow-World\u002Fblob\u002Fmaster\u002Fcodes\u002F2-basics_in_machine_learning\u002Fmulticlass_svm\u002Fcode\u002Fmulticlass_svm.ipynb\n\n\n.. +---+---------------------------------------------+----------------------------------------+\n.. | # |          源代码                        |                                        |\n.. +===+=============================================+========================================+\n.. | 1 |    `线性回归`_                     |  `文档 \u003CDocumentationlr_>`_   |\n.. +---+---------------------------------------------+----------------------------------------+\n.. | 2 |    `逻辑回归`_                   |  `文档 \u003CLogisticRegDOC_>`_    |\n.. +---+---------------------------------------------+----------------------------------------+\n.. | 3 |    `线性支持向量机`_                            |                                        |\n.. +---+---------------------------------------------+----------------------------------------+\n.. | 4 |    `多分类核支持向量机`_                 |                                        |\n\n.. ~~~~~~~~~~~~~~~~~~~\n.. **神经网络**\n.. ~~~~~~~~~~~~~~~~~~~\n.. 本节的教程与神经网络架构相关。\n\n.. _简单卷积神经网络: https:\u002F\u002Fgithub.com\u002Fastorfi\u002FTensorFlow-World\u002Ftree\u002Fmaster\u002Fcodes\u002F3-neural_networks\u002Fconvolutional-neural-network\n.. _卷积神经网络文档: https:\u002F\u002Fgithub.com\u002Fastorfi\u002FTensorFlow-World\u002Fblob\u002Fmaster\u002Fdocs\u002Ftutorials\u002F3-neural_network\u002Fconvolutiona_neural_network\n\n.. _简单多层感知器: https:\u002F\u002Fgithub.com\u002Fastorfi\u002FTensorFlow-World\u002Fblob\u002Fmaster\u002Fcodes\u002F3-neural_networks\u002Fmulti-layer-perceptron\n.. _多层感知器IPython: https:\u002F\u002Fgithub.com\u002Fastorfi\u002FTensorFlow-World\u002Fblob\u002Fmaster\u002Fcodes\u002F3-neural_networks\u002Fmulti-layer-perceptron\u002Fcode\u002Ftrain_mlp.ipynb\n\n\n.. _欠完备自编码器代码: https:\u002F\u002Fgithub.com\u002Fastorfi\u002FTensorFlow-World\u002Ftree\u002Fmaster\u002Fcodes\u002F3-neural_networks\u002Fundercomplete-autoencoder\n.. _自编码器文档: https:\u002F\u002Fgithub.com\u002Fastorfi\u002FTensorFlow-World\u002Ftree\u002Fmaster\u002Fdocs\u002Ftutorials\u002F3-neural_network\u002Fautoencoder\n\n.. _循环神经网络: codes\u002F3-neural_networks\u002Frecurrent-neural-networks\u002Fcode\u002Frnn.py\n.. _循环神经网络IPython: codes\u002F3-neural_networks\u002Frecurrent-neural-networks\u002Fcode\u002Frnn.py\n\n\n.. +---+---------------------------------------------+----------------------------------------+\n.. | # |          源代码                        |                                        |\n.. +===+=============================================+========================================+\n.. | 1 |    `多层感知器`_                |                                        |\n.. +---+---------------------------------------------+----------------------------------------+\n.. | 2 |    `卷积神经网络`_         |  `文档 \u003CDocumentationcnn_>`_  |\n.. +---+---------------------------------------------+----------------------------------------+\n\n\n=====================\n一些有用的教程\n=====================\n\n* `TensorFlow 示例 \u003Chttps:\u002F\u002Fgithub.com\u002Faymericdamien\u002FTensorFlow-Examples>`_ - 面向初学者的 TensorFlow 教程和代码示例\n  * `Sungjoon 的 TensorFlow-101 \u003Chttps:\u002F\u002Fgithub.com\u002Fsjchoi86\u002FTensorflow-101>`_ - 使用 Jupyter Notebook 编写的 Python 版 TensorFlow 教程\n  * `Terry Um 的 TensorFlow 练习 \u003Chttps:\u002F\u002Fgithub.com\u002Fterryum\u002FTensorFlow_Exercises>`_ - 重新实现其他 TensorFlow 示例中的代码\n  * `时间序列分类 \u003Chttps:\u002F\u002Fgithub.com\u002Fguillaume-chevalier\u002FLSTM-Human-Activity-Recognition>`_ - 在手机传感器数据上使用 LSTM 的循环神经网络分类\n\n=============\n贡献说明\n=============\n\n在向本仓库提交贡献时，请先通过 Issue、邮件或其他方式与仓库维护者沟通您计划进行的更改，再实施具体修改。*对于拼写错误等小问题，请勿直接创建 Pull Request，而应在 Issue 中提出或直接联系仓库维护者*。\n\n请注意，我们有一份行为准则，请在与本项目的所有互动中严格遵守。\n\n~~~~~~~~~~~~~~~~~~~~\nPull Request 流程\n~~~~~~~~~~~~~~~~~~~~\n\n为便于我们更好地处理您的请求，请遵循以下原则：\n\n  * Pull Request 主要应用于代码脚本的建议或改进。\n  * 若涉及非代码部分的修改，则应显著提升文档质量；否则，建议优先在 Issue 中讨论。\n  * 在构建并提交 Pull Request 之前，请确保已移除所有安装或构建依赖项。\n  * 请添加详细注释，说明接口变更内容，包括新增环境变量、开放端口、重要文件路径及容器参数等。\n  * 当至少有一位其他开发者确认并通过审核后，您可以自行合并 Pull Request；若您无权限执行此操作，也可请求仓库维护者代为合并，前提是您认为所有检查均已通过。\n\n\n~~~~~~~~~~~\n结语\n~~~~~~~~~~~\n\n我们期待您的宝贵反馈！请帮助我们不断完善这个开源项目，共同提升工作质量。如需贡献代码，请创建 Pull Request，我们将尽快评估。再次感谢您的支持与细致的代码审查！\n\n================\n致谢\n================\n\n我为本项目付出了大量努力，希望能为 TensorFlow 社区贡献一份微薄之力。然而，这一切离不开我的朋友兼同事 `Domenick Poster \u003Chttps:\u002F\u002Fgithub.com\u002Fvonclites\u002F>`_ 的鼎力支持与宝贵建议。他帮助我更深入地理解了 TensorFlow，对此我深表感激。","# TensorFlow-World 快速上手指南\n\nTensorFlow-World 是一个旨在提供简单、即用型 TensorFlow 教程的开源项目。每个教程均包含源代码和配套文档，帮助开发者快速掌握从基础数学运算到复杂神经网络模型的实现。\n\n## 1. 环境准备\n\n在开始之前，请确保您的开发环境满足以下要求：\n\n*   **操作系统**：Linux, macOS, 或 Windows (推荐使用 Linux 或 macOS 以获得最佳兼容性)\n*   **Python 版本**：Python 3.6 - 3.9 (具体版本取决于您安装的 TensorFlow 版本)\n*   **前置依赖**：\n    *   `pip` (Python 包管理工具)\n    *   `virtualenv` 或 `conda` (强烈建议使用虚拟环境以避免包冲突)\n    *   `git` (用于克隆代码仓库)\n\n> **注意**：本项目主要基于原生 TensorFlow 构建。虽然支持 Keras 等高层 API，但核心示例侧重于理解 TensorFlow 底层机制。\n\n## 2. 安装步骤\n\n### 第一步：创建并激活虚拟环境\n为了防止依赖冲突，建议先创建一个独立的虚拟环境。\n\n**使用 venv:**\n```bash\npython3 -m venv tf-world-env\nsource tf-world-env\u002Fbin\u002Factivate  # Windows 用户请使用: tf-world-env\\Scripts\\activate\n```\n\n**或使用 conda:**\n```bash\nconda create -n tf-world-env python=3.8\nconda activate tf-world-env\n```\n\n### 第二步：安装 TensorFlow\n根据您的硬件情况选择安装 CPU 或 GPU 版本。国内用户推荐使用清华源或阿里源加速下载。\n\n**使用 pip 安装 (推荐):**\n```bash\n# 设置国内镜像源 (可选，加速下载)\npip config set global.index-url https:\u002F\u002Fpypi.tuna.tsinghua.edu.cn\u002Fsimple\n\n# 安装 TensorFlow (CPU 版本)\npip install tensorflow\n\n# 如果需要 GPU 支持 (需确保已安装对应的 CUDA 和 cuDNN)\n# pip install tensorflow-gpu\n```\n\n### 第三步：获取教程源码\n克隆 TensorFlow-World 仓库到本地：\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Fastorfi\u002FTensorFlow-World.git\ncd TensorFlow-World\n```\n\n## 3. 基本使用\n\n本项目的教程按难度分类（热身、基础、机器学习、神经网络等）。以下是运行第一个\"热身\"教程的示例。\n\n### 示例：运行欢迎教程 (Welcome Tutorial)\n\n1.  **定位代码**：\n    进入项目目录后，找到 `docs\u002Ftutorials` 或直接查看根目录下的教程结构。根据 README 指引，\"Warm-up\" 部分的第一个教程是 \"Start-up\"。\n\n2.  **执行代码**：\n    您可以直接运行提供的 Python 脚本或在 Jupyter\u002FIPython 环境中交互运行。\n\n    **方式 A：直接运行 Python 脚本**\n    ```bash\n    # 假设教程脚本位于 docs\u002Ftutorials\u002Fwarmup 目录下 (具体路径请以实际克隆后的文件结构为准)\n    # 这里以典型的入口文件为例\n    python docs\u002Ftutorials\u002F01_welcome\u002Fwelcome.py\n    ```\n\n    **方式 B：使用 IPython\u002FJupyter (推荐)**\n    项目中提供了 `.ipynb` 文件，适合逐步学习。\n    ```bash\n    # 启动 Jupyter Notebook\n    jupyter notebook\n    \n    # 在浏览器中导航至对应的 .ipynb 文件并运行单元格\n    # 例如：docs\u002Ftutorials\u002F01_welcome\u002Fwelcome.ipynb\n    ```\n\n### 探索更多教程\n项目内容涵盖以下模块，您可以依次深入：\n\n*   **Basics (基础)**: 包含基本数学运算 (`basic_math_operations`) 和变量管理 (`tensorflow_variables`)。\n*   **Basic Machine Learning (基础机器学习)**: 线性回归、逻辑回归、支持向量机 (SVM)。\n*   **Neural Networks (神经网络)**: 多层感知机 (MLP)、卷积神经网络 (CNN) 等。\n\n**查看文档**：\n详细的理论解释和代码说明请参阅项目关联的 Wiki 页面：\nhttps:\u002F\u002Fgithub.com\u002Fastorfi\u002FTensorFlow-World\u002Fwiki\n\n---\n*提示：为了获得最佳学习体验，建议按照目录顺序，从 \"Warm-up\" 开始，逐步过渡到复杂的神经网络模型。*","某高校人工智能实验室的研究生李明，正试图在两周内复现一篇关于图像分类的顶会论文，以完成他的学期项目。\n\n### 没有 TensorFlow-World 时\n- **文档碎片化严重**：需要在官方文档、StackOverflow 和各类博客间反复跳转搜索基础代码片段，耗费大量时间甄别信息真伪。\n- **环境配置与架构搭建困难**：面对 TensorFlow 高度模块化的特性，不知如何组合各个组件构建模型，常因缺少标准模板而陷入“从零造轮子”的困境。\n- **缺乏系统性指引**：网上的教程质量参差不齐，往往只展示代码却缺失原理解析，导致知其然而不知其所以然，调试报错时无从下手。\n- **学习曲线陡峭**：作为初学者，被复杂的 API 细节劝退，难以快速验证想法，项目进度严重滞后。\n\n### 使用 TensorFlow-World 后\n- **一站式获取就绪代码**：直接查阅 TensorFlow-World 中分类清晰的教程库，瞬间找到包含完整源码和对应文档的图像分类示例，无需四处拼凑。\n- **模块化模型快速构建**：参考仓库中现成的最佳实践模板，迅速理解如何将数据输入、网络层和损失函数模块化组装，大幅降低架构设计门槛。\n- **源码与文档深度对照**：每个教程都提供代码与详细解释的完美结合，李明能边跑通代码边理解背后的数学原理，遇到报错也能依据文档快速定位。\n- **高效验证与创新**：基于成熟的基础教程进行微调，几天内就完成了基线模型复现，将节省下的时间投入到核心算法改进中。\n\nTensorFlow-World 通过将碎片化的知识整合为简单可用的实战教程，极大地缩短了开发者从理论认知到工程落地的路径。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fastorfi_TensorFlow-World_5008074b.png","astorfi","Sina Torfi","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002Fastorfi_af2bf404.png","PhD & Developer\r\nworking on Deep Learning, Computer Vision & NLP\r\n","Meta","San Jose","amirsina.torfi@gmail.com",null,"https:\u002F\u002Fastorfi.github.io\u002F","https:\u002F\u002Fgithub.com\u002Fastorfi",[25,29,33],{"name":26,"color":27,"percentage":28},"Python","#3572A5",50.3,{"name":30,"color":31,"percentage":32},"Jupyter Notebook","#DA5B0B",48.8,{"name":34,"color":35,"percentage":36},"Shell","#89e051",0.9,4501,406,"2026-04-12T19:31:58","MIT",2,"","未说明",{"notes":45,"python":43,"dependencies":46},"该项目是 TensorFlow 的教程集合，旨在提供简单且优化的代码实现。README 中未列出具体的系统配置要求，但建议使用虚拟环境（virtual environment）进行安装以防止包冲突并自定义工作环境。具体安装步骤需参考项目提供的 'TensorFlow Installation' 链接。",[47,48,49],"TensorFlow","Keras (可选)","Slim (可选)",[51,52],"开发框架","图像",[54,55,56,57,58,59],"deep-learning","neural-network","tensorflow","machine-learning","python","computer-vision","ready","2026-03-27T02:49:30.150509","2026-04-16T01:51:42.827113",[64,69,74,79,84,89,94],{"id":65,"question_zh":66,"answer_zh":67,"source_url":68},34841,"克隆仓库时出现 'remote: Not Found' 错误怎么办？","不需要使用终端命令克隆。您可以直接在 GitHub 仓库页面顶部点击 'Code' 按钮，然后选择 'Download ZIP' 下载压缩包，或者先 Fork 该仓库到您的账户后再下载。","https:\u002F\u002Fgithub.com\u002Fastorfi\u002FTensorFlow-World\u002Fissues\u002F16",{"id":70,"question_zh":71,"answer_zh":72,"source_url":73},34842,"发现代码或文档中有拼写错误，应该如何贡献修复？","根据当前的贡献政策，对于拼写错误请不要直接创建 Pull Request。您应该在 Issues 中声明该错误，或者直接通过邮件联系仓库所有者，由维护者来进行修复。","https:\u002F\u002Fgithub.com\u002Fastorfi\u002FTensorFlow-World\u002Fissues\u002F25",{"id":75,"question_zh":76,"answer_zh":77,"source_url":78},34843,"运行 TensorBoard 时提示参数错误，如何解决？","这可能与 TensorFlow 版本差异有关。如果文档中的命令 `tensorboard --logdir=\"path\"`（带等号）报错，请尝试移除等号，改为 `tensorboard --logdir \"path\"`（不带等号，中间用空格分隔）即可正常运行。","https:\u002F\u002Fgithub.com\u002Fastorfi\u002FTensorFlow-World\u002Fissues\u002F26",{"id":80,"question_zh":81,"answer_zh":82,"source_url":83},34844,"在 TensorFlow 代码中定义 'train_op' 的作用是什么？为什么不能省略？","'train_op' 是执行训练步骤（如更新权重）所必需的关键图张量，而不仅仅是损失函数。它是优化器对象，必须由 TensorFlow 会话（session.run）运行才能实际执行训练。如果省略，模型将无法进行参数更新和学习。","https:\u002F\u002Fgithub.com\u002Fastorfi\u002FTensorFlow-World\u002Fissues\u002F12",{"id":85,"question_zh":86,"answer_zh":87,"source_url":88},34845,"代码中出现 'undefined name' (未定义名称) 错误导致 NameError 怎么办？","这通常是由于变量命名不一致造成的。例如在多层感知机代码中，如果上下文未定义 'logits'，应检查是否应该使用 'logits_last' 或其他已定义的变量名。维护者通常会确认并修复此类命名错误。","https:\u002F\u002Fgithub.com\u002Fastorfi\u002FTensorFlow-World\u002Fissues\u002F19",{"id":90,"question_zh":91,"answer_zh":92,"source_url":93},34846,"在 Linux 上安装 NVIDIA 驱动时提示 'Unable to locate package' 怎么办？","如果遇到 `sudo apt-get install nvidia-current-updates` 找不到包的问题，可能是因为软件源名称在不同 Linux 发行版或版本中有所不同。建议检查您的系统版本对应的正确 NVIDIA 包名称，或访问 NVIDIA 官网下载对应的驱动程序。此外，安装 CuDNN 后需将其路径添加到系统环境变量中：`export LD_LIBRARY_PATH=\u003Cinstallpath>:$LD_LIBRARY_PATH`，其中 `\u003Cinstallpath>` 应替换为 CuDNN 库的实际安装目录路径。","https:\u002F\u002Fgithub.com\u002Fastorfi\u002FTensorFlow-World\u002Fissues\u002F28",{"id":95,"question_zh":96,"answer_zh":97,"source_url":98},34847,"线性回归教程中每个 epoch 只报告最后一个数据点的损失值，这是正常的吗？","这不是预期的行为。如果代码在循环中逐个处理数据点并打印损失，确实只会显示最后一个点的损失。为了获得整个数据集的平均损失，损失函数应包含对所有样本的求和或平均操作（例如使用 `tf.reduce_sum` 除以样本数量），并且在训练循环外或针对整个批次计算损失，而不是在单个数据点迭代中覆盖损失值。","https:\u002F\u002Fgithub.com\u002Fastorfi\u002FTensorFlow-World\u002Fissues\u002F21",[100],{"id":101,"version":102,"summary_zh":103,"released_at":104},272163,"v1.0","该开源项目的第一个正式版本。","2017-06-17T21:37:58",[106,117,125,134,142,151],{"id":107,"name":108,"github_repo":109,"description_zh":110,"stars":111,"difficulty_score":112,"last_commit_at":113,"category_tags":114,"status":60},4358,"openclaw","openclaw\u002Fopenclaw","OpenClaw 是一款专为个人打造的本地化 AI 助手，旨在让你在自己的设备上拥有完全可控的智能伙伴。它打破了传统 AI 助手局限于特定网页或应用的束缚，能够直接接入你日常使用的各类通讯渠道，包括微信、WhatsApp、Telegram、Discord、iMessage 等数十种平台。无论你在哪个聊天软件中发送消息，OpenClaw 都能即时响应，甚至支持在 macOS、iOS 和 Android 设备上进行语音交互，并提供实时的画布渲染功能供你操控。\n\n这款工具主要解决了用户对数据隐私、响应速度以及“始终在线”体验的需求。通过将 AI 部署在本地，用户无需依赖云端服务即可享受快速、私密的智能辅助，真正实现了“你的数据，你做主”。其独特的技术亮点在于强大的网关架构，将控制平面与核心助手分离，确保跨平台通信的流畅性与扩展性。\n\nOpenClaw 非常适合希望构建个性化工作流的技术爱好者、开发者，以及注重隐私保护且不愿被单一生态绑定的普通用户。只要具备基础的终端操作能力（支持 macOS、Linux 及 Windows WSL2），即可通过简单的命令行引导完成部署。如果你渴望拥有一个懂你",349277,3,"2026-04-06T06:32:30",[115,51,52,116],"Agent","数据工具",{"id":118,"name":119,"github_repo":120,"description_zh":121,"stars":122,"difficulty_score":112,"last_commit_at":123,"category_tags":124,"status":60},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,"2026-04-05T11:01:52",[51,52,115],{"id":126,"name":127,"github_repo":128,"description_zh":129,"stars":130,"difficulty_score":41,"last_commit_at":131,"category_tags":132,"status":60},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",156804,"2026-04-15T11:34:33",[51,115,133],"语言模型",{"id":135,"name":136,"github_repo":137,"description_zh":138,"stars":139,"difficulty_score":41,"last_commit_at":140,"category_tags":141,"status":60},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。",108322,"2026-04-10T11:39:34",[51,52,115],{"id":143,"name":144,"github_repo":145,"description_zh":146,"stars":147,"difficulty_score":41,"last_commit_at":148,"category_tags":149,"status":60},6121,"gemini-cli","google-gemini\u002Fgemini-cli","gemini-cli 是一款由谷歌推出的开源 AI 命令行工具，它将强大的 Gemini 大模型能力直接集成到用户的终端环境中。对于习惯在命令行工作的开发者而言，它提供了一条从输入提示词到获取模型响应的最短路径，无需切换窗口即可享受智能辅助。\n\n这款工具主要解决了开发过程中频繁上下文切换的痛点，让用户能在熟悉的终端界面内直接完成代码理解、生成、调试以及自动化运维任务。无论是查询大型代码库、根据草图生成应用，还是执行复杂的 Git 操作，gemini-cli 都能通过自然语言指令高效处理。\n\n它特别适合广大软件工程师、DevOps 人员及技术研究人员使用。其核心亮点包括支持高达 100 万 token 的超长上下文窗口，具备出色的逻辑推理能力；内置 Google 搜索、文件操作及 Shell 命令执行等实用工具；更独特的是，它支持 MCP（模型上下文协议），允许用户灵活扩展自定义集成，连接如图像生成等外部能力。此外，个人谷歌账号即可享受免费的额度支持，且项目基于 Apache 2.0 协议完全开源，是提升终端工作效率的理想助手。",100752,"2026-04-10T01:20:03",[150,115,52,51],"插件",{"id":152,"name":153,"github_repo":154,"description_zh":155,"stars":156,"difficulty_score":41,"last_commit_at":157,"category_tags":158,"status":60},4721,"markitdown","microsoft\u002Fmarkitdown","MarkItDown 是一款由微软 AutoGen 团队打造的轻量级 Python 工具，专为将各类文件高效转换为 Markdown 格式而设计。它支持 PDF、Word、Excel、PPT、图片（含 OCR）、音频（含语音转录）、HTML 乃至 YouTube 链接等多种格式的解析，能够精准提取文档中的标题、列表、表格和链接等关键结构信息。\n\n在人工智能应用日益普及的今天，大语言模型（LLM）虽擅长处理文本，却难以直接读取复杂的二进制办公文档。MarkItDown 恰好解决了这一痛点，它将非结构化或半结构化的文件转化为模型“原生理解”且 Token 效率极高的 Markdown 格式，成为连接本地文件与 AI 分析 pipeline 的理想桥梁。此外，它还提供了 MCP（模型上下文协议）服务器，可无缝集成到 Claude Desktop 等 LLM 应用中。\n\n这款工具特别适合开发者、数据科学家及 AI 研究人员使用，尤其是那些需要构建文档检索增强生成（RAG）系统、进行批量文本分析或希望让 AI 助手直接“阅读”本地文件的用户。虽然生成的内容也具备一定可读性，但其核心优势在于为机器",93400,"2026-04-06T19:52:38",[150,51]]