Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/solidglue/deep_learning_tensorflow2_examples

深度学习TensorFlow2入门指南。Deep Learning TensorFlow2 API and Examples with Python3 and Jupyter Notebook.
https://github.com/solidglue/deep_learning_tensorflow2_examples

jupyter-notebook keras tensorflow-api tensorflow-examples tensorflow2

Last synced: 27 days ago
JSON representation

深度学习TensorFlow2入门指南。Deep Learning TensorFlow2 API and Examples with Python3 and Jupyter Notebook.

Host: GitHub
URL: https://github.com/solidglue/deep_learning_tensorflow2_examples
Owner: solidglue
License: apache-2.0
Created: 2024-02-27T05:57:44.000Z (8 months ago)
Default Branch: master
Last Pushed: 2024-05-20T09:16:43.000Z (6 months ago)
Last Synced: 2024-10-10T08:43:47.745Z (27 days ago)
Topics: jupyter-notebook, keras, tensorflow-api, tensorflow-examples, tensorflow2
Language: Jupyter Notebook
Homepage:
Size: 3.15 MB
Stars: 98
Watchers: 1
Forks: 2
Open Issues: 1
Metadata Files:
- Readme: README.md
- License: LICENSE

Awesome Lists containing this project

README

        # 深度学习入门指南

基于TensorFlow2 + Keras讲解深度学习入门指南。  

## 注意

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。  

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：  

●  [**Deep_Learning_TensorFlow2_Examples**](https://nbviewer.org/github/solidglue/Deep_Learning_TensorFlow2_Examples/tree/master/)  

## 张量 

●  [**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)]  

●  [**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)]     

●  [**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)]    

●  图和函数简介  

●  [**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)]    

●  [**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)]    

●  高级自动微分  

●  不规则张量  

●  [**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)]    

●  Numpy API  

●  Tensor切片  

## Keras

●  [**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)]    

●  [**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)]    

●  [**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)]    

●  通过子类化构建新层和模型  

●  [**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)]    

●  [**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)]    

●  [**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)]    

●  [**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)]    

●  采用Keras的循环神经网络（RNN）  

●  [**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)]    

●  自动编写回调  

●  迁移学习和微调  

●  使用TensorFlow Cloud训练Keras模型  

## TensorFlow Core

●  [**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)]    

●  [**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)]    

## 自定义

●  创建操作  

●  生成随机数字  

## 数据输入流水线

●  [**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)]    

●  优化流水线性能  

●  分析流水线性能  

## 保存模型

●  [**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)]    

●  [**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)]   

## 加速器

●  分布式训练  

●  GPU  

●  TPU  

## 性能

●  使用tf.function提升性能  

●  分析TensorFlow的性能  

●  优化GPU性能  

●  图优化  

●  混合精度  

## TensorFlow Serving（服务）

●  TensorFlow Serving和Docker  

●  安装  

●  提供TensorFlow模型  

●  高级模型服务器配置  

## *扩展

1.**推荐系统**  

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。  

●  [**Recommender_System**](https://github.com/solidglue/Recommender_System) 

2.**YouTuBe推荐系统排序模型**  

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。  

●  [**YouTube深度排序模型(多值embedding、多目标学习)**](https://github.com/solidglue/DNN_for_YouTube_Recommendations) 

3.**推荐系统推理服务**  

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。   

● [**推荐系统推理微服务Golang**](https://github.com/solidglue/Recommender_System_Inference_Services)  

4.**机器学习 Sklearn入门教程**  

●  [**机器学习Sklearn入门教程**](https://github.com/solidglue/Machine_Learning_Sklearn_Examples)