Ecosyste.ms: Awesome

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

Awesome Lists | Featured Topics | Projects

https://github.com/geektutu/tensorflow-tutorial-samples

TensorFlow2教程 TensorFlow 2.0 Tutorial 入门教程实战案例
https://github.com/geektutu/tensorflow-tutorial-samples

mnist openai-gym tensorflow tensorflow-mnist

Last synced: 13 days ago
JSON representation

TensorFlow2教程 TensorFlow 2.0 Tutorial 入门教程实战案例

Host: GitHub
URL: https://github.com/geektutu/tensorflow-tutorial-samples
Owner: geektutu
Created: 2017-11-19T12:41:17.000Z (almost 7 years ago)
Default Branch: master
Last Pushed: 2020-11-22T17:30:57.000Z (almost 4 years ago)
Last Synced: 2024-10-16T00:36:23.274Z (28 days ago)
Topics: mnist, openai-gym, tensorflow, tensorflow-mnist
Language: Python
Homepage: https://geektutu.com/post/tensorflow2-mnist-cnn.html
Size: 21.6 MB
Stars: 534
Watchers: 17
Forks: 201
Open Issues: 1
Metadata Files:
- Readme: README.md

Awesome Lists containing this project

README

        # TensorFlow 2.0 Tutorial 入门教程实战案例

> 用最白话的语言，讲解机器学习、神经网络与深度学习

> 示例基于 TensorFlow 1.4 和 TensorFlow 2.0 实现

## 相关链接

- [Python 简明教程](https://geektutu.com/post/quick-python.html)

- [机器学习笔试面试题](https://geektutu.com/post/qa-ml-1.html)，[Github](https://github.com/geektutu/interview-questions)

- [TensorFlow 2.0 中文文档](https://geektutu.com/post/tf2doc.html)，[Github](https://github.com/geektutu/tensorflow2-docs-zh)

- [TensorFlow 2.0 图像识别&强化学习实战](https://geektutu.com/post/tensorflow2-mnist-cnn.html)，[Github](https://github.com/geektutu/tensorflow-tutorial-samples)

## OpenAI gym

- [TensorFlow 2.0 (九) - 强化学习70行代码实战 Policy Gradient](https://geektutu.com/post/tensorflow2-gym-pg.html)

    - [Github - gym/CartPole-v0-policy-gradient](https://github.com/geektutu/tensorflow-tutorial-samples/tree/master/gym/CartPole-v0-policy-gradient)

    - 介绍了策略梯度算法(Policy Gradient)来玩 CartPole-v0

- [TensorFlow 2.0 (八) - 强化学习 DQN 玩转 gym Mountain Car](https://geektutu.com/post/tensorflow2-gym-dqn.html)

    - [Github - gym/MountainCar-v0-dqn](https://github.com/geektutu/tensorflow-tutorial-samples/tree/master/gym/MountainCar-v0-dqn)

    - 介绍了DQN(Deep Q-Learning)来玩MountainCar-v0游戏

    - Q-Table用神经网络来代替。

- [TensorFlow 2.0 (七) - 强化学习 Q-Learning 玩转 OpenAI gym](https://geektutu.com/post/tensorflow2-gym-q-learning.html)

    - [Github - gym/MountainCar-v0-q-learning](https://github.com/geektutu/tensorflow-tutorial-samples/tree/master/gym/MountainCar-v0-q-learning)

    - 介绍了使用Q-Learning(创建Q-Table)来玩MountainCar-v0游戏

    - 将连续的状态离散化。

- [TensorFlow 2.0 (六) - 监督学习玩转 OpenAI gym game ](https://geektutu.com/post/tensorflow2-gym-nn.html)

    - [Github - gym/CartPole-v0-nn](https://github.com/geektutu/tensorflow-tutorial-samples/tree/master/gym/CartPole-v0-nn)

    - 介绍了使用纯监督学习(神经网络)来玩CartPole-v0游戏

    - 使用TensorFlow 2.0

## mnist

- [TensorFlow 2.0 (五) - mnist手写数字识别(CNN卷积神经网络)](https://geektutu.com/post/tensorflow2-mnist-cnn.html)

    - [Github - v4_cnn](https://github.com/geektutu/tensorflow-tutorial-samples/tree/master/mnist/v4_cnn)

    - 介绍了如何搭建CNN网络，准确率达到0.99

    - 使用TensorFlow 2.0

- [TensorFlow入门(四) - mnist手写数字识别(制作h5py训练集)](https://geektutu.com/post/tensorflow-make-npy-hdf5-data-set.html)

    - [Github - make_data_set](https://github.com/geektutu/tensorflow-tutorial-samples/tree/master/make_data_set)

    - 介绍了如何使用 numpy 制作 npy 格式的数据集

    - 介绍了如何使用 h5py 制作 HDF5 格式的数据集

- [TensorFlow入门(三) - mnist手写数字识别(可视化训练)](https://geektutu.com/post/tensorflow-mnist-tensorboard-training.html)

    - [Github - mnist/v3](https://github.com/geektutu/tensorflow-tutorial-samples/tree/master/mnist/v3)

    - 介绍了tensorboard的简单用法，包括标量图、直方图以及网络结构图

- [TensorFlow入门(二) - mnist手写数字识别(模型保存加载)](https://geektutu.com/post/tensorflow-mnist-save-ckpt.html)

    - [Github - mnist/v2](https://github.com/geektutu/tensorflow-tutorial-samples/tree/master/mnist/v2)

    - 介绍了 TensorFlow 中如何保存训练好的模型

    - 介绍了如何从某一个模型为起点继续训练

    - 介绍了模型如何加载使用，传入真实的图片如何识别

- [TensorFlow入门(一) - mnist手写数字识别(网络搭建)](https://geektutu.com/post/tensorflow-mnist-simplest.html)

    - [Github - mnist/v1](https://github.com/geektutu/tensorflow-tutorial-samples/tree/master/mnist/v1)

    - 这篇博客介绍了使用 TensorFlow 搭建最简单的神经网络。

    - 包括输入输出、独热编码与损失函数，以及正确率的验证。