{"id":14959047,"url":"https://github.com/solidglue/deep_learning_tensorflow2_examples","last_synced_at":"2025-05-02T12:31:02.152Z","repository":{"id":224689376,"uuid":"763905290","full_name":"solidglue/Deep_Learning_TensorFlow2_Examples","owner":"solidglue","description":"深度学习TensorFlow2入门指南。Deep Learning TensorFlow2  API and Examples with Python3 and Jupyter Notebook.","archived":false,"fork":false,"pushed_at":"2024-05-20T09:16:43.000Z","size":3300,"stargazers_count":104,"open_issues_count":1,"forks_count":3,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-04-07T01:43:43.254Z","etag":null,"topics":["jupyter-notebook","keras","tensorflow-api","tensorflow-examples","tensorflow2"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/solidglue.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-02-27T05:57:44.000Z","updated_at":"2025-04-06T07:29:08.000Z","dependencies_parsed_at":"2024-03-29T07:23:11.638Z","dependency_job_id":"f7b1ae44-becb-4f60-9a2d-24138298a7a9","html_url":"https://github.com/solidglue/Deep_Learning_TensorFlow2_Examples","commit_stats":{"total_commits":43,"total_committers":2,"mean_commits":21.5,"dds":"0.32558139534883723","last_synced_commit":"c7c8c47badef3816bcff61d2915b4b26050f3b01"},"previous_names":["solidglue/tensorflow2_keras_api_jupyter_demo","solidglue/tensorflow2_keras_guide_api_jupyter_demo","solidglue/deep_learning_tensorflow2_examples"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/solidglue%2FDeep_Learning_TensorFlow2_Examples","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/solidglue%2FDeep_Learning_TensorFlow2_Examples/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/solidglue%2FDeep_Learning_TensorFlow2_Examples/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/solidglue%2FDeep_Learning_TensorFlow2_Examples/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/solidglue","download_url":"https://codeload.github.com/solidglue/Deep_Learning_TensorFlow2_Examples/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":252038108,"owners_count":21684626,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["jupyter-notebook","keras","tensorflow-api","tensorflow-examples","tensorflow2"],"created_at":"2024-09-24T13:18:45.727Z","updated_at":"2025-05-02T12:31:01.746Z","avatar_url":"https://github.com/solidglue.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# 深度学习入门指南\n基于TensorFlow2 + Keras讲解深度学习入门指南。  \n\n## 注意\n如果通过Github站内超链接打开Jupyter Notebook文件发生错误，可以点击根据 https://nbviewer.org 生成的“备用链接”间接访问对应文件。  \n或者通过以下链接访问整个项目的站外备用链接，注意点击站外备用链接里的非Jupyter Notebook格式文件会跳转回到Github仓库内：  \n●  [**Deep_Learning_TensorFlow2_Examples**](https://nbviewer.org/github/solidglue/Deep_Learning_TensorFlow2_Examples/tree/master/)  \n\n\n## 张量 \n●  [**张量**](https://github.com/solidglue/TensorFlow2_Keras_Guide_API_Jupyter_Demo/blob/master/01_TensorFlow_basics/01_01_Tensors.ipynb)       [~~*(备用链接)*~~](https://nbviewer.org/github/solidglue/Deep_Learning_TensorFlow2_Examples/blob/master/01_TensorFlow_basics/01_01_Tensors.ipynb)]  \n●  [**变量**](https://github.com/solidglue/TensorFlow2_Keras_Guide_API_Jupyter_Demo/blob/master/01_TensorFlow_basics/01_02_Variables.ipynb)       [~~*(备用链接)*~~](https://nbviewer.org/github/solidglue/Deep_Learning_TensorFlow2_Examples/blob/master/01_TensorFlow_basics/01_02_Variables.ipynb)]     \n●  [**自动微分**](https://github.com/solidglue/TensorFlow2_Keras_Guide_API_Jupyter_Demo/blob/master/01_TensorFlow_basics/01_03_Automatic_differentiation.ipynb)       [~~*(备用链接)*~~](https://nbviewer.org/github/solidglue/Deep_Learning_TensorFlow2_Examples/blob/master/01_TensorFlow_basics/01_03_Automatic_differentiation.ipynb)]    \n●  图和函数简介  \n●  [**模块、层和模型简介**](https://github.com/solidglue/TensorFlow2_Keras_Guide_API_Jupyter_Demo/blob/master/01_TensorFlow_basics/01_05_Modules_layers_and_models.ipynb)       [~~*(备用链接)*~~](https://nbviewer.org/github/solidglue/Deep_Learning_TensorFlow2_Examples/blob/master/01_TensorFlow_basics/01_05_Modules_layers_and_models.ipynb)]    \n●  [**训练循环**](https://github.com/solidglue/TensorFlow2_Keras_Guide_API_Jupyter_Demo/blob/master/01_TensorFlow_basics/01_06_Training_loops.ipynb)       [~~*(备用链接)*~~](https://nbviewer.org/github/solidglue/Deep_Learning_TensorFlow2_Examples/blob/master/01_TensorFlow_basics/01_06_Training_loops.ipynb)]    \n●  高级自动微分  \n●  不规则张量  \n●  [**稀疏张量**](https://github.com/solidglue/TensorFlow2_Keras_Guide_API_Jupyter_Demo/blob/master/04_TensorFlow_in_depth/04_04_Sparse_tensor.ipynb)       [~~*(备用链接)*~~](https://nbviewer.org/github/solidglue/Deep_Learning_TensorFlow2_Examples/blob/master/04_TensorFlow_in_depth/04_04_Sparse_tensor.ipynb)]    \n●  Numpy API  \n●  Tensor切片  \n\n## Keras\n●  [**Sequential模型**](https://github.com/solidglue/TensorFlow2_Keras_Guide_API_Jupyter_Demo/blob/master/02_Keras/02_01_The_sequential_model.ipynb)       [~~*(备用链接)*~~](https://nbviewer.org/github/solidglue/Deep_Learning_TensorFlow2_Examples/blob/master/02_Keras/02_01_The_sequential_model.ipynb)]    \n●  [**Functional API**](https://github.com/solidglue/TensorFlow2_Keras_Guide_API_Jupyter_Demo/blob/master/02_Keras/02_02_The_functional_API.ipynb)       [~~*(备用链接)*~~](https://nbviewer.org/github/solidglue/Deep_Learning_TensorFlow2_Examples/blob/master/02_Keras/02_02_The_functional_API.ipynb)]    \n●  [**使用内置方法进行训练和评估**](https://github.com/solidglue/TensorFlow2_Keras_Guide_API_Jupyter_Demo/blob/master/02_Keras/02_03_Training_evaluation_with_the_built_in_methods.ipynb)       [~~*(备用链接)*~~](https://nbviewer.org/github/solidglue/Deep_Learning_TensorFlow2_Examples/blob/master/02_Keras/02_03_Training_evaluation_with_the_built_in_methods.ipynb)]    \n●  通过子类化构建新层和模型  \n●  [**保存并加载Keras模型**](https://github.com/solidglue/TensorFlow2_Keras_Guide_API_Jupyter_Demo/blob/master/02_Keras/02_05_Serialization_and_saving.ipynb)       [~~*(备用链接)*~~](https://nbviewer.org/github/solidglue/Deep_Learning_TensorFlow2_Examples/blob/master/02_Keras/02_05_Serialization_and_saving.ipynb)]    \n●  [**使用预处理层**](https://github.com/solidglue/TensorFlow2_Keras_Guide_API_Jupyter_Demo/blob/master/02_Keras/02_07_Working_with_preprocessing_layers.ipynb)       [~~*(备用链接)*~~](https://nbviewer.org/github/solidglue/Deep_Learning_TensorFlow2_Examples/blob/master/02_Keras/02_07_Working_with_preprocessing_layers.ipynb)]    \n●  [**自定义Model.fit的操作流程**](https://github.com/solidglue/TensorFlow2_Keras_Guide_API_Jupyter_Demo/blob/master/02_Keras/02_08_Customizing_what_happens_in_fit.ipynb)       [~~*(备用链接)*~~](https://nbviewer.org/github/solidglue/Deep_Learning_TensorFlow2_Examples/blob/master/02_Keras/02_08_Customizing_what_happens_in_fit.ipynb)]    \n●  [**从头开始编写训练循环**](https://github.com/solidglue/TensorFlow2_Keras_Guide_API_Jupyter_Demo/blob/master/02_Keras/02_09_Writing_a_training_loop_from_scratch.ipynb)       [~~*(备用链接)*~~](https://nbviewer.org/github/solidglue/Deep_Learning_TensorFlow2_Examples/blob/master/02_Keras/02_09_Writing_a_training_loop_from_scratch.ipynb)]    \n●  采用Keras的循环神经网络（RNN）  \n●  [**采用Keras进行遮盖和填充**](https://github.com/solidglue/TensorFlow2_Keras_Guide_API_Jupyter_Demo/blob/master/02_Keras/02_11_Understading_masking_and_padding.ipynb)       [~~*(备用链接)*~~](https://nbviewer.org/github/solidglue/Deep_Learning_TensorFlow2_Examples/blob/master/02_Keras/02_11_Understading_masking_and_padding.ipynb)]    \n●  自动编写回调  \n●  迁移学习和微调  \n●  使用TensorFlow Cloud训练Keras模型  \n\n## TensorFlow Core\n●  [**TensorFlow Core API 快速入门**](https://github.com/solidglue/TensorFlow2_Keras_Guide_API_Jupyter_Demo/blob/master/03_Build_with_Core/03_01_Quickstart_for_core.ipynb)       [~~*(备用链接)*~~](https://nbviewer.org/github/solidglue/Deep_Learning_TensorFlow2_Examples/blob/master/03_Build_with_Core/03_01_Quickstart_for_core.ipynb)]    \n●  [**使用 Core API 进行二元分类的逻辑回归**](https://github.com/solidglue/TensorFlow2_Keras_Guide_API_Jupyter_Demo/blob/master/03_Build_with_Core/03_02_Logistic_regression.ipynb)       [~~*(备用链接)*~~](https://nbviewer.org/github/solidglue/Deep_Learning_TensorFlow2_Examples/blob/master/03_Build_with_Core/03_02_Logistic_regression.ipynb)]    \n\n## 自定义\n●  创建操作  \n●  生成随机数字  \n\n## 数据输入流水线\n●  [**tf.data**](https://github.com/solidglue/TensorFlow2_Keras_Guide_API_Jupyter_Demo/blob/master/06_Data_input_pipelines/06_01_tfdata.ipynb)       [~~*(备用链接)*~~](https://nbviewer.org/github/solidglue/Deep_Learning_TensorFlow2_Examples/blob/master/06_Data_input_pipelines/06_01_tfdata.ipynb)]    \n●  优化流水线性能  \n●  分析流水线性能  \n\n## 保存模型\n●  [**Checkpoint**](https://github.com/solidglue/TensorFlow2_Keras_Guide_API_Jupyter_Demo/blob/master/07_Import_and_export/07_01_Checkpoint.ipynb)       [~~*(备用链接)*~~](https://nbviewer.org/github/solidglue/Deep_Learning_TensorFlow2_Examples/blob/master/07_Import_and_export/07_01_Checkpoint.ipynb)]    \n●  [**SavedModel**](https://github.com/solidglue/Deep_Learning_TensorFlow2_Examples/blob/master/07_Import_and_export/07_02_SaveModel.ipynb)       [~~*(备用链接)*~~](https://nbviewer.org/github/solidglue/Deep_Learning_TensorFlow2_Examples/blob/master/07_Import_and_export/07_02_SaveModel.ipynb)]   \n\n## 加速器\n●  分布式训练  \n●  GPU  \n●  TPU  \n\n## 性能\n●  使用tf.function提升性能  \n●  分析TensorFlow的性能  \n●  优化GPU性能  \n●  图优化  \n●  混合精度  \n\n## TensorFlow Serving（服务）\n●  TensorFlow Serving和Docker  \n●  安装  \n●  提供TensorFlow模型  \n●  高级模型服务器配置  \n\n\n## *扩展\n\n1.**推荐系统**  \n王树森推荐系统公开课 - 基于小红书的场景讲解工业界真实的推荐系统。  \n●  [**Recommender_System**](https://github.com/solidglue/Recommender_System) \n\n2.**YouTuBe推荐系统排序模型**  \n以\"DNN_for_YouTube_Recommendations\"模型和电影评分数据集（ml-1m）为基础，详尽的展示了如何基于TensorFlow2实现推荐系统排序模型。  \n●  [**YouTube深度排序模型(多值embedding、多目标学习)**](https://github.com/solidglue/DNN_for_YouTube_Recommendations) \n\n3.**推荐系统推理服务**  \n基于Goalng、Docker和微服务思想实现了高并发、高性能和高可用的推荐系统推理微服务，包括多种召回/排序服务，并提供多种接口访问方式（REST、gRPC和Dubbo）等，每日可处理上千万次推理请求。   \n● [**推荐系统推理微服务Golang**](https://github.com/solidglue/Recommender_System_Inference_Services)  \n\n4.**机器学习 Sklearn入门教程**  \n●  [**机器学习Sklearn入门教程**](https://github.com/solidglue/Machine_Learning_Sklearn_Examples)  \n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsolidglue%2Fdeep_learning_tensorflow2_examples","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsolidglue%2Fdeep_learning_tensorflow2_examples","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsolidglue%2Fdeep_learning_tensorflow2_examples/lists"}