简单粗暴 TensorFlow 2 | A Concise Handbook of TensorFlow 2¶
基于Keras和即时执行模式 | Based on Keras and Eager Execution
简体中文版 | 繁體中文版 | English Version |
简体中文版¶
这是一本简明的 TensorFlow 2 入门指导手册,基于 Keras 和即时执行模式(Eager Execution),力图让具备一定机器学习及 Python 基础的开发者们快速上手 TensorFlow 2。同时也是纸质版技术手册 《简明的 TensorFlow 2》 的部分草稿。
本手册的所有代码基于 TensorFlow 2.2 正式版。文中的所有示例代码可至 这里 获得。
本手册正于TensorFlow官方微信公众号(TensorFlow_official)连载,可点此查看 连载文章目录 。本手册的原始语言为简体中文,并有 繁体中文版 和 英文版 。本手册是 Google Summer of Code 2019 项目之一,并获得 谷歌开源贡献奖(Google Open Source Peer Bonus) 。
自2020年4月起,在每章文末加入了留言区,欢迎有需要的读者在文末讨论交流。
GitHub: https://github.com/snowkylin/tensorflow-handbook
教程答疑区: https://discuss.tf.wiki
纸质完整版:《简明的 TensorFlow 2》
本书纸质版《简明的 TensorFlow 2》由人民邮电出版社(图灵社区)出版,在本在线手册的基础上进行了细致的编排校对,并增加了若干 TensorFlow 高级专题,全彩印刷,为读者带来更好的阅读体验。 豆瓣评分:https://book.douban.com/subject/35217981/ 纸质版购买链接: |
- TensorFlow安装与环境配置
- TensorFlow基础
- TensorFlow 模型建立与训练
- TensorFlow常用模块
繁体中文版¶
- TensorFlow 安裝與環境配置
- TensorFlow 基礎
- TensorFlow 模型建立與訓練
- TensorFlow常用模組
English Version (in progress)¶
This is a concise handbook of TensorFlow 2.0 based on Keras and Eager Execution mode, aiming to help developers with some basic machine learning and Python knowledge to get started with TensorFlow 2.0 quickly.
The code of this handbook is based on TensorFlow 2.0 stable version and beta1 version. All sample code in this handbook can be viewed here .
The English version of this handbook is still in progress (section title with a ✔️ means that the translation of this section is finished). Please refer to https://v1.tf.wiki for the eariler version. This handbook is a project of Google Summer of Code 2019 .
GitHub: https://github.com/snowkylin/tensorflow-handbook
- Installation and Environment Configuration
- TensorFlow Basic
- Model Construction and Training
- Common Modules in TensorFlow
- Variable saving and restore:
tf.train.Checkpoint
- Visualization of training process: TensorBoard
- Dataset construction and preprocessing:
tf.data
- TFRecord: Dataset format of TensorFlow
- Graph execution mode:
@tf.function
* - TensorFlow dynamic array:
tf.TensorArray
* - Setting and allocating GPUs:
tf.config
*
- Variable saving and restore: