# tensorflow-practice **Repository Path**: vencol/tensorflow-practice ## Basic Information - **Project Name**: tensorflow-practice - **Description**: No description available - **Primary Language**: Unknown - **License**: MIT - **Default Branch**: master - **Homepage**: None - **GVP Project**: No ## Statistics - **Stars**: 0 - **Forks**: 0 - **Created**: 2020-05-11 - **Last Updated**: 2020-12-19 ## Categories & Tags **Categories**: Uncategorized **Tags**: None ## README # Overview This repository provides data source, Jupyter notebooks for machine learning projects. Each folder corresponds to one project or data sets. General notes about machine learning and TensorFlow are collected in the folder "0_Notes_for_Tensorflow". You can click [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)]()to open the notebook in Colab and exclude the code there directly. Quick links of the projects are (with constant updates): [1_Linear_Regression](https://github.com/zht007/tensorflow-practice/tree/master/1_Linear_Regression) [2_Classification_Pima_Indians_Diabetes](https://github.com/zht007/tensorflow-practice/tree/master/2_Classification_Pima_Indians_Diabetes) [3_Classification_Census_Data](https://github.com/zht007/tensorflow-practice/tree/master/3_Classification_Census_Data) [4_Clasification_DigitRecognizer](https://github.com/zht007/tensorflow-practice/tree/master/4_Clasification_DigitRecognizer) [5_Prediction_MilkProdction](https://github.com/zht007/tensorflow-practice/tree/master/5_Prediction_MilkProdction) [6_Renforcement_Learning_Gridword](https://github.com/zht007/tensorflow-practice/tree/master/6_Renforcement_Learning_Gridword) [7_Renforcement_Learning_blackjack](https://github.com/zht007/tensorflow-practice/tree/master/7_Renforcement_Learning_blackjack) [8_Renforcement_Learning_Clif_Env](https://github.com/zht007/tensorflow-practice/tree/master/8_Renforcement_Learning_Clif_Env) [9_Renforcement_Learning_CartPole](https://github.com/zht007/tensorflow-practice/tree/master/9_Renforcement_Learning_CartPole) [10_Renforcement_Learning_Moutain_Car](https://github.com/zht007/tensorflow-practice/tree/master/10_Renforcement_Learning_Moutain_Car) [11_Transfer_Learing](https://github.com/zht007/tensorflow-practice/tree/master/11_Transfer_Learning) [12_Classification_CIFAR](https://github.com/zht007/tensorflow-practice/tree/master/12_Classification_CIFAR) [13_Classification_Reuters](https://github.com/zht007/tensorflow-practice/tree/master/13_Classification_Reuters) All codes are written in Python 3 on Jupyter Notebooks, with detailed notes and comments in English. Tensorflow tutorials for Chinease readers are provided. If you like this repository please follow me on my [Steemit](https://steemit.com/@hongtao) or [Jianshu](https://www.jianshu.com/). ---- For Chinese Readers: 本项目旨在通过项目实战的方式向读者介绍如何使用Tensorfow进行机器学习，每一个目录对应着一个项目或者一个训练数据集。一般性的学习笔记放在了"0_Notes_for_Tensorflow".目录。 所有的代码都是在Jupyter Notebook上用Python 3写成，详细的英文笔记和注释也都附在了Jupyter Notebook中。对于代码的解释以及Tensorflow的入门，我写成了中文教程。如果喜欢我的教程，欢迎关注我的 [Steemit](https://steemit.com/@hongtao) 或者 [简书](https://www.jianshu.com/) 也欢迎关注我的微信公众号**tensorflow机器学习**，共同学习，一起进步。 ![](https://ws2.sinaimg.cn/large/006tKfTcgy1g1oq6xu1iaj307607674q.jpg) --- ## Table of Contents ### [0_Notes_for_Tensorflow](https://github.com/zht007/tensorflow-practice/tree/master/0_Notes_for_Tensorflow) [AI学习笔记——Tensorflow入门](https://github.com/zht007/tensorflow-practice/blob/master/0_Notes_for_Tensorflow/AI%E5%AD%A6%E4%B9%A0%E7%AC%94%E8%AE%B0%E2%80%94%E2%80%94Tensorflow%E5%85%A5%E9%97%A8.md) [AI学习笔记——机器学习中易混淆术语解析](https://github.com/zht007/tensorflow-practice/blob/master/0_Notes_for_Tensorflow/AI%E5%AD%A6%E4%B9%A0%E7%AC%94%E8%AE%B0%E2%80%94%E2%80%94%E6%9C%BA%E5%99%A8%E5%AD%A6%E4%B9%A0%E4%B8%AD%E6%98%93%E6%B7%B7%E6%B7%86%E6%9C%AF%E8%AF%AD%E8%A7%A3%E6%9E%90.md) [AI学习笔记——神经网络和深度学习](https://github.com/zht007/tensorflow-practice/blob/master/0_Notes_for_Tensorflow/AI学习笔记——神经网络和深度学习.md) [AI学习笔记——精准识别You Only Look Once(YOLO)](https://github.com/zht007/tensorflow-practice/blob/master/0_Notes_for_Tensorflow/AI学习笔记——精准识别You_Only_Look_Once(YOLO).md) [Tensorflow入门——处理overfitting的问题](https://github.com/zht007/tensorflow-practice/blob/master/0_Notes_for_Tensorflow/Tensorflow%E5%85%A5%E9%97%A8%E2%80%94%E2%80%94%E5%A4%84%E7%90%86overfitting%E7%9A%84%E9%97%AE%E9%A2%98.md) [免费使用Google的GPU和TPU来训练你的模型](https://github.com/zht007/tensorflow-practice/blob/master/0_Notes_for_Tensorflow/%E5%85%8D%E8%B4%B9%E4%BD%BF%E7%94%A8Google%E7%9A%84GPU%E5%92%8CTPU%E6%9D%A5%E8%AE%AD%E7%BB%83%E4%BD%A0%E7%9A%84%E6%A8%A1%E5%9E%8B.md) [深入理解Numpy和Tensorflow中的Axis操作](https://github.com/zht007/tensorflow-practice/blob/master/0_Notes_for_Tensorflow/深入理解Numpy和Tensorflow中的Axis操作.md) [Tensorflow2.0——与Keras 的深度融合](https://github.com/zht007/tensorflow-practice/blob/master/0_Notes_for_Tensorflow/Tensorflow2.0——与Keras的深度融合.md) [Tensorflow_2_0_Tutorial_data_loading.ipynb](https://github.com/zht007/tensorflow-practice/blob/master/0_Notes_for_Tensorflow/Tensorflow_2_0_Tutorial_data_loading.ipynb)[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/zht007/tensorflow-practice/blob/master/0_Notes_for_Tensorflow/Tensorflow_2_0_Tutorial_data_loading.ipynb) [Tensorflow2.0-数据加载和预处理.md](https://github.com/zht007/tensorflow-practice/blob/master/0_Notes_for_Tensorflow/Tensorflow2.0-数据加载和预处理.md) ---- ### [1_Linear_Regression](https://github.com/zht007/tensorflow-practice/tree/master/1_Linear_Regression) [1-LinearRegression.ipynb](https://github.com/zht007/tensorflow-practice/blob/master/1_Linear_Regression/01-LinearRegression.ipynb) [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/zht007/tensorflow-practice/blob/master/1_Linear_Regression/01-LinearRegression.ipynb) [Tensorflow入门——线性回归](https://github.com/zht007/tensorflow-practice/blob/master/1_Linear_Regression/Tensorflow%E5%85%A5%E9%97%A8%E2%80%94%E2%80%94%E7%BA%BF%E6%80%A7%E5%9B%9E%E5%BD%92.md) [2-RegressionBatchKeras.ipynb](https://github.com/zht007/tensorflow-practice/blob/master/1_Linear_Regression/02-RegressionBatchKeras.ipynb)[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/zht007/tensorflow-practice/blob/master/1_Linear_Regression/02-RegressionBatchKeras.ipynb) [Tensorflow入门——Keras简介和上手](https://github.com/zht007/tensorflow-practice/blob/master/1_Linear_Regression/Tensorflow%E5%85%A5%E9%97%A8%E2%80%94%E2%80%94Keras%E7%AE%80%E4%BB%8B%E5%92%8C%E4%B8%8A%E6%89%8B.md) [3-Regression_TF_eager_api.ipynb](https://github.com/zht007/tensorflow-practice/blob/master/1_Linear_Regression/03-Regression_TF_eager_api.ipynb)[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/zht007/tensorflow-practice/blob/master/1_Linear_Regression/03-Regression_TF_eager_api.ipynb) [Tensorflow入门——Eager模式像原生python一样训练模型.md](https://github.com/zht007/tensorflow-practice/blob/master/1_Linear_Regression/Tensorflow入门——Eager模式像原生python一样训练模型.md) [4_Regression_TF_2_0.ipynb](https://github.com/zht007/tensorflow-practice/blob/master/1_Linear_Regression/04_Regression_TF_2_0.ipynb)[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/zht007/tensorflow-practice/blob/master/1_Linear_Regression/04_Regression_TF_2_0.ipynb) [Tensorflow 2.0 快速入门 —— 自动求导与线性回归](https://github.com/zht007/tensorflow-practice/blob/master/1_Linear_Regression/Tensorflow2.0快速入门——自动求导与线性回归.md) ### [2_Classification_Pima_Indians_Diabetes](https://github.com/zht007/tensorflow-practice/tree/master/2_Classification_Pima_Indians_Diabetes) [1-KerasClassification.ipynb](https://github.com/zht007/tensorflow-practice/blob/master/2_Classification_Pima_Indians_Diabetes/1-KerasClassification.ipynb)[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/zht007/tensorflow-practice/blob/master/2_Classification_Pima_Indians_Diabetes/1-KerasClassification.ipynb) [Tensorflow入门——Keras处理分类问题](https://github.com/zht007/tensorflow-practice/blob/master/2_Classification_Pima_Indians_Diabetes/Tensorflow%E5%85%A5%E9%97%A8%E2%80%94%E2%80%94Keras%E5%A4%84%E7%90%86%E5%88%86%E7%B1%BB%E9%97%AE%E9%A2%98.md) [2-TensorflowClassification.ipynb](https://github.com/zht007/tensorflow-practice/blob/master/2_Classification_Pima_Indians_Diabetes/2-TensorflowClassification.ipynb)[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/zht007/tensorflow-practice/blob/master/2_Classification_Pima_Indians_Diabetes/2-TensorflowClassification.ipynb) [Tensorflow入门——Tensorflow处理分类问题](https://github.com/zht007/tensorflow-practice/blob/master/2_Classification_Pima_Indians_Diabetes/Tensorflow%E5%85%A5%E9%97%A8%E2%80%94%E2%80%94Tensorflow%E5%A4%84%E7%90%86%E5%88%86%E7%B1%BB%E9%97%AE%E9%A2%98.md) [3-KerasClassification-with-Regularization-dropout](https://github.com/zht007/tensorflow-practice/blob/master/2_Classification_Pima_Indians_Diabetes/3-KerasClassification-with-Regularization-dropout.ipynb)[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/zht007/tensorflow-practice/blob/master/2_Classification_Pima_Indians_Diabetes/3-KerasClassification-with-Regularization-dropout.ipynb) ### [3_Classification_Census_Data](https://github.com/zht007/tensorflow-practice/tree/master/3_Classification_Census_Data) [1-Classification-keras-census.ipynb](https://github.com/zht007/tensorflow-practice/blob/master/3_Classification_Census_Data/1-Classification-keras-census.ipynb)[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/zht007/tensorflow-practice/blob/master/3_Classification_Census_Data/1-Classification-keras-census.ipynb) ### [4_Clasification_DigitRecognizer](https://github.com/zht007/tensorflow-practice/tree/master/4_Clasification_DigitRecognizer) [1_DL_One_Layer_NN_for_DigitRecognizer.ipynb](https://github.com/zht007/tensorflow-practice/blob/master/4_Clasification_DigitRecognizer/1_DL_One_Layer_NN_for_DigitRecognizer.ipynb)[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/zht007/tensorflow-practice/blob/master/4_Clasification_DigitRecognizer/1_DL_One_Layer_NN_for_DigitRecognizer.ipynb) [Tensorflow入门——单层神经网络MNIST手写数子识别](https://github.com/zht007/tensorflow-practice/blob/master/4_Clasification_DigitRecognizer/Tensorflow%E5%85%A5%E9%97%A8%E2%80%94%E2%80%94%E5%8D%95%E5%B1%82%E7%A5%9E%E7%BB%8F%E7%BD%91%E7%BB%9CMNIST%E6%89%8B%E5%86%99%E6%95%B0%E5%AD%97%E8%AF%86%E5%88%AB.md) [2_DL_Multi_Layer_NN_for_DigitRecognizer.ipynb](https://github.com/zht007/tensorflow-practice/blob/master/4_Clasification_DigitRecognizer/2_DL_Multi_Layer_NN_for_DigitRecognizer.ipynb)[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/zht007/tensorflow-practice/blob/master/4_Clasification_DigitRecognizer/2_DL_Multi_Layer_NN_for_DigitRecognizer.ipynb) [Tensorflow入门——多层神经网络MNIST手写数子识别](https://github.com/zht007/tensorflow-practice/blob/master/4_Clasification_DigitRecognizer/Tensorflow%E5%85%A5%E9%97%A8%E2%80%94%E2%80%94%E5%A4%9A%E5%B1%82%E7%A5%9E%E7%BB%8F%E7%BD%91%E7%BB%9CMNIST%E6%89%8B%E5%86%99%E6%95%B0%E5%AD%97%E8%AF%86%E5%88%AB.md) [3_DL_Multi_Layer_CNN_for_DigitRecognizer.ipnb](https://github.com/zht007/tensorflow-practice/blob/master/4_Clasification_DigitRecognizer/3_DL_Multi_Layer_CNN_for_DigitRecognizer.ipynb)[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/zht007/tensorflow-practice/blob/master/4_Clasification_DigitRecognizer/3_DL_Multi_Layer_CNN_for_DigitRecognizer.ipynb) [Tensorflow入门——卷积神经网络MNIST手写数子识别](https://github.com/zht007/tensorflow-practice/blob/master/4_Clasification_DigitRecognizer/Tensorflow%E5%85%A5%E9%97%A8%E2%80%94%E2%80%94%E5%8D%B7%E7%A7%AF%E7%A5%9E%E7%BB%8F%E7%BD%91%E7%BB%9CMNIST%E6%89%8B%E5%86%99%E6%95%B0%E5%AD%97%E8%AF%86%E5%88%AB.md) [4_DL_Multi_Layer_CNN_for_DigitRecognizer_with_tensorboard.ipynb](https://github.com/zht007/tensorflow-practice/blob/master/4_Clasification_DigitRecognizer/4_DL_Multi_Layer_CNN_for_DigitRecognizer_with_tensorboard.ipynb)[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/zht007/tensorflow-practice/blob/master/4_Clasification_DigitRecognizer/4_DL_Multi_Layer_CNN_for_DigitRecognizer_with_tensorboard.ipynb) [两步轻松实现在Keras中使用Tensorboard.](https://github.com/zht007/tensorflow-practice/blob/master/4_Clasification_DigitRecognizer/两步轻松实现在Keras中使用Tensorboard.md) [5_DL_Multi_Layer_CNN_for_DigitRecognizer_with_various_parameters](https://github.com/zht007/tensorflow-practice/blob/master/4_Clasification_DigitRecognizer/5_DL_Multi_Layer_CNN_for_DigitRecognizer_with_various_parameters.ipynb)[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/zht007/tensorflow-practice/blob/master/4_Clasification_DigitRecognizer/5_DL_Multi_Layer_CNN_for_DigitRecognizer_with_various_parameters.ipynb) [利用Tensorboard辅助模型调参](https://github.com/zht007/tensorflow-practice/blob/master/4_Clasification_DigitRecognizer/利用Tensorboard辅助模型调参.md) [6_DL_Multi_Layer_CNN_for_DigitRecognizer_TF_2.0](https://github.com/zht007/tensorflow-practice/blob/master/4_Clasification_DigitRecognizer/6_DL_Multi_Layer_CNN_for_DigitRecognizer_TF2_0.ipynb)[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/zht007/tensorflow-practice/blob/master/4_Clasification_DigitRecognizer/6_DL_Multi_Layer_CNN_for_DigitRecognizer_TF2_0.ipynb) [Tensorflow_2.0_快速入门——引入Keras自定义模型](https://github.com/zht007/tensorflow-practice/blob/master/4_Clasification_DigitRecognizer/Tensorflow_2.0_快速入门——引入Keras自定义模型.md) [7_DL_Multi_Layer_CNN_for_DigitRecognizer_TF2_0_with_Tensorboard.ipynb](https://github.com/zht007/tensorflow-practice/blob/master/4_Clasification_DigitRecognizer/7_DL_Multi_Layer_CNN_for_DigitRecognizer_TF2_0_with_Tensorboard.ipynb)[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/zht007/tensorflow-practice/blob/master/4_Clasification_DigitRecognizer/7_DL_Multi_Layer_CNN_for_DigitRecognizer_TF2_0_with_Tensorboard.ipynb) [Tensorflow2.0——可视化工具Tensorboard](https://github.com/zht007/tensorflow-practice/blob/master/4_Clasification_DigitRecognizer/Tensorflow2.0——可视化工具Tensorboard.md) ### [5_Prediction_MilkProdction](https://github.com/zht007/tensorflow-practice/tree/master/5_Prediction_MilkProdction) [1_RNN_Many_to_One_Keras.ipynb](https://github.com/zht007/tensorflow-practice/blob/master/5_Prediction_MilkProdction/1_RNN_Many_to_One_Keras.ipynb)[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/zht007/tensorflow-practice/blob/master/5_Prediction_MilkProdction/1_RNN_Many_to_One_Keras.ipynb) [Tensorflow入门——RNN预测牛奶产量](https://github.com/zht007/tensorflow-practice/blob/master/5_Prediction_MilkProdction/Tensorflow%E5%85%A5%E9%97%A8%E2%80%94%E2%80%94RNN%E9%A2%84%E6%B5%8B%E7%89%9B%E5%A5%B6%E4%BA%A7%E9%87%8F.md) [2_RNN_Many_to_Many_Keras.ipynb](https://github.com/zht007/tensorflow-practice/blob/master/5_Prediction_MilkProdction/2_RNN_Many_to_Many_Keras.ipynb)[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/zht007/tensorflow-practice/blob/master/5_Prediction_MilkProdction/2_RNN_Many_to_Many_Keras.ipynb) [3_RNN_Many_to_Many_Stateful_Keras.ipynb](https://github.com/zht007/tensorflow-practice/blob/master/5_Prediction_MilkProdction/3_RNN_Many_to_Many_Stateful_Keras.ipynb)[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/zht007/tensorflow-practice/blob/master/5_Prediction_MilkProdction/3_RNN_Many_to_Many_Stateful_Keras.ipynb) [Tensorflow入门——改进RNN预测牛奶产量](https://github.com/zht007/tensorflow-practice/blob/master/5_Prediction_MilkProdction/Tensorflow入门——改进RNN预测牛奶产量.md) [4_RNN_Many_to_One_TF2_0.ipynb](https://github.com/zht007/tensorflow-practice/blob/master/5_Prediction_MilkProdction/4_RNN_Many_to_One_TF2_0.ipynb) [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/zht007/tensorflow-practice/blob/master/5_Prediction_MilkProdction/4_RNN_Many_to_One_TF2_0.ipynb) [Tensorflow 2.0 快速入门 —— RNN 预测牛奶产量](https://github.com/zht007/tensorflow-practice/blob/master/5_Prediction_MilkProdction/Tensorflow2.0快速入门——RNN预测牛奶产量.md) ### [6_Renforcement_Learning_Gridword](https://github.com/zht007/tensorflow-practice/tree/master/6_Renforcement_Learning_Gridword) [1_Policy_Evaluation.ipynb](https://github.com/zht007/tensorflow-practice/blob/master/6_Renforcement_Learning_Gridword/1_Policy_Evaluation.ipynb)[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/zht007/tensorflow-practice/blob/master/6_Renforcement_Learning_Gridword/1_Policy_Evaluation.ipynb) [2_Policy_Iteration.ipynb](https://github.com/zht007/tensorflow-practice/blob/master/6_Renforcement_Learning_Gridword/2_Policy_Iteration.ipynb)[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/zht007/tensorflow-practice/blob/master/6_Renforcement_Learning_Gridword/2_Policy_Iteration.ipynb) [3_Value_Iteration.ipynb](https://github.com/zht007/tensorflow-practice/blob/master/6_Renforcement_Learning_Gridword/3_Value_Iteration.ipynb)[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/zht007/tensorflow-practice/blob/master/6_Renforcement_Learning_Gridword/3_Value_Iteration.ipynb) [强化学习实战——动态规划(DP)求最优MDP](https://github.com/zht007/tensorflow-practice/blob/master/6_Renforcement_Learning_Gridword/强化学习实战——动态规划(DP)求最优MDP.md) ### [7_Renforcement_Learning_blackjack](https://github.com/zht007/tensorflow-practice/tree/master/7_Renforcement_Learning_blackjack) [1_MC_Prediction .ipynb](https://github.com/zht007/tensorflow-practice/blob/master/7_Renforcement_Learning_blackjack/1_MC_Prediction%20.ipynb)[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/zht007/tensorflow-practice/blob/master/7_Renforcement_Learning_blackjack/1_MC_Prediction%20.ipynb) [2_MC_Control_with Epsilon_Greedy Policies.ipynb](https://github.com/zht007/tensorflow-practice/blob/master/7_Renforcement_Learning_blackjack/2_MC_Control_with%20Epsilon_Greedy%20Policies.ipynb)[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/zht007/tensorflow-practice/blob/master/7_Renforcement_Learning_blackjack/2_MC_Control_with%20Epsilon_Greedy%20Policies.ipynb) [3_Off_Policy_MC Control_with_Weighted Importance_Sampling.ipynb](https://github.com/zht007/tensorflow-practice/blob/master/7_Renforcement_Learning_blackjack/3_Off_Policy_MC%20Control_with_Weighted%20Importance_Sampling.ipynb)[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/zht007/tensorflow-practice/blob/master/7_Renforcement_Learning_blackjack/3_Off_Policy_MC%20Control_with_Weighted%20Importance_Sampling.ipynb) [强化学习——MC(蒙特卡洛)玩21点扑克游戏](https://github.com/zht007/tensorflow-practice/blob/master/7_Renforcement_Learning_blackjack/强化学习——MC(蒙特卡洛)玩21点扑克游戏.md) ### [8_Renforcement_Learning_Clif_Env](https://github.com/zht007/tensorflow-practice/tree/master/8_Renforcement_Learning_Clif_Env) [1_SARSA_Q-Learning_compare_Clif_Env.ipynb](https://github.com/zht007/tensorflow-practice/blob/master/8_Renforcement_Learning_Clif_Env/1_SARSA_Q-Learning_compare_Clif_Env.ipynb)[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/zht007/tensorflow-practice/blob/master/8_Renforcement_Learning_Clif_Env/1_SARSA_Q-Learning_compare_Clif_Env.ipynb) [强化学习实战——Q-Learing和SASAR悬崖探宝](https://github.com/zht007/tensorflow-practice/blob/master/8_Renforcement_Learning_Clif_Env/强化学习实战——Q-Learing和SASAR悬崖探宝.md) ### [9_Renforcement_Learning_CartPole](https://github.com/zht007/tensorflow-practice/tree/master/9_Renforcement_Learning_CartPole) [1_dqn_keras_rl_cartpole.ipynb](https://github.com/zht007/tensorflow-practice/blob/master/9_Renforcement_Learning_CartPole/1_dqn_keras_rl_cartpole.ipynb)[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/zht007/tensorflow-practice/blob/master/9_Renforcement_Learning_CartPole/1_dqn_keras_rl_cartpole.ipynb) [DQN深度Q-Learning轻松上手](https://github.com/zht007/tensorflow-practice/blob/master/9_Renforcement_Learning_CartPole/DQN深度Q-Learning轻松上手.md) [2_q_learning_python_carpole.ipynb](https://github.com/zht007/tensorflow-practice/blob/master/9_Renforcement_Learning_CartPole/2_q_learning_python_carpole.ipynb)[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/zht007/tensorflow-practice/blob/master/9_Renforcement_Learning_CartPole/2_q_learning_python_carpole.ipynb) [3_SARSA_python_carpole.ipynb](https://github.com/zht007/tensorflow-practice/blob/master/9_Renforcement_Learning_CartPole/3_SARSA_python_carpole.ipynb)[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/zht007/tensorflow-practice/blob/master/9_Renforcement_Learning_CartPole/3_SARSA_python_carpole.ipynb) [4_SARSA_lambda_python_carpole.ipynb](https://github.com/zht007/tensorflow-practice/blob/master/9_Renforcement_Learning_CartPole/4_SARSA_lambda_python_carpole.ipynb)[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/zht007/tensorflow-practice/blob/master/9_Renforcement_Learning_CartPole/4_SARSA_lambda_python_carpole.ipynb) [强化学习_Q-Learning_SARSA玩Carpole经典游戏](https://github.com/zht007/tensorflow-practice/blob/master/9_Renforcement_Learning_CartPole/强化学习_Q-Learning_SARSA玩Carpole经典游戏.md) [5_DQN_keras_cartpole.ipynb](https://github.com/zht007/tensorflow-practice/blob/master/9_Renforcement_Learning_CartPole/5_DQN_keras_cartpole.ipynb)[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/zht007/tensorflow-practice/blob/master/9_Renforcement_Learning_CartPole/5_DQN_keras_cartpole.ipynb) [6_double_dqn_kearas_cartpole.ipynb](https://github.com/zht007/tensorflow-practice/blob/master/9_Renforcement_Learning_CartPole/6_double_dqn_kearas_cartpole.ipynb)[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/zht007/tensorflow-practice/blob/master/9_Renforcement_Learning_CartPole/6_double_dqn_kearas_cartpole.ipynb) [用Keras搭建Double DQN模型](https://github.com/zht007/tensorflow-practice/blob/master/9_Renforcement_Learning_CartPole/用Keras搭建Double_DQN模型.md) [7_policy_gradient_cartpole_tensorflow.ipynb](https://github.com/zht007/tensorflow-practice/blob/master/9_Renforcement_Learning_CartPole/7_policy_gradient_cartpole_tensorflow.ipynb)[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/zht007/tensorflow-practice/blob/master/9_Renforcement_Learning_CartPole/7_policy_gradient_cartpole_tensorflow.ipynb) [深度强化学习_Policy_Gradient_玩转_CartPole 游戏](https://github.com/zht007/tensorflow-practice/blob/master/9_Renforcement_Learning_CartPole/深度强化学习_Policy_Gradient_玩转_CartPole游戏.md) [8_policy_gradient_TF2_cartpole.ipynb](https://github.com/zht007/tensorflow-practice/blob/master/9_Renforcement_Learning_CartPole/8_policy_gradient_TF2_cartpole.ipynb)[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github//zht007/tensorflow-practice/blob/master/9_Renforcement_Learning_CartPole/8_policy_gradient_TF2_cartpole.ipynb) [Tensorflow2.0_深度强化学习——Policy_Gradient](https://github.com/zht007/tensorflow-practice/blob/master/9_Renforcement_Learning_CartPole/Tensorflow2.0_深度强化学习——Policy_Gradient) ### [10_Renforcement_Learning_Moutain_Car](https://github.com/zht007/tensorflow-practice/tree/master/10_Renforcement_Learning_Moutain_Car) [1_q_learning_python_mountain_car.ipynb](https://github.com/zht007/tensorflow-practice/blob/master/10_Renforcement_Learning_Moutain_Car/1_q_learning_python_mountain_car.ipynb)[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/zht007/tensorflow-practice/blob/master/10_Renforcement_Learning_Moutain_Car/1_q_learning_python_mountain_car.ipynb) [强化学习_Q-Learning玩MountainCar爬坡上山](https://github.com/zht007/tensorflow-practice/blob/master/10_Renforcement_Learning_Moutain_Car/强化学习_Q-Learning玩MountainCar爬坡上山.md) [2_SARSA_python_mountain_car.ipynb](https://github.com/zht007/tensorflow-practice/blob/master/10_Renforcement_Learning_Moutain_Car/2_SARSA_python_mountain_car.ipynb)[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/zht007/tensorflow-practice/blob/master/10_Renforcement_Learning_Moutain_Car/2_SARSA_python_mountain_car.ipynb) [3_SARSA_lambda_python_mountain_car.ipynb](https://github.com/zht007/tensorflow-practice/blob/master/10_Renforcement_Learning_Moutain_Car/3_SARSA_lambda_python_mountain_car.ipynb)[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/zht007/tensorflow-practice/blob/master/10_Renforcement_Learning_Moutain_Car/3_SARSA_lambda_python_mountain_car.ipynb) [强化学习_SARSA和SARSA lambda玩 MountainCa 爬坡上山](https://github.com/zht007/tensorflow-practice/blob/master/10_Renforcement_Learning_Moutain_Car/强化学习_SARSA和SARSA_lambda玩MountainCar爬坡上山.md) [4_q_learning_python_mountain_car_continuos.](https://github.com/zht007/tensorflow-practice/blob/master/10_Renforcement_Learning_Moutain_Car/4_q_learning_python_mountain_car_continuos.ipynb)[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/zht007/tensorflow-practice/blob/master/10_Renforcement_Learning_Moutain_Car/4_q_learning_python_mountain_car_continuos.ipynb) [Q-Learning--可操控动作大小的小车爬山游戏](https://github.com/zht007/tensorflow-practice/blob/master/10_Renforcement_Learning_Moutain_Car/Q-Learning--可操控动作大小的小车爬山游戏.md) [5_DQN_keras_mountain_car.ipynb](https://github.com/zht007/tensorflow-practice/blob/master/10_Renforcement_Learning_Moutain_Car/5_DQN_keras_mountain_car.ipynb)[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/zht007/tensorflow-practice/blob/master/10_Renforcement_Learning_Moutain_Car/5_DQN_keras_mountain_car.ipynb) ### [11_Transfer_Learing](https://github.com/zht007/tensorflow-practice/tree/master/11_Transfer_Learning) [1_flowers_with_transfer_learning.ipynb](https://github.com/zht007/tensorflow-practice/blob/master/11_Transfer_Learning/1_flowers_with_transfer_learning.ipynb)[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/zht007/tensorflow-practice/blob/master/11_Transfer_Learning/1_flowers_with_transfer_learning.ipynb) [Tensorflow 2.0 轻松实现迁移学习](https://github.com/zht007/tensorflow-practice/blob/master/11_Transfer_Learning/Tensorflow_2.0_轻松实现迁移学习.md) ### [12_Classification_CIFAR](https://github.com/zht007/tensorflow-practice/tree/master/12_Classification_CIFAR) [1_ResNet_for_CIFAR100_TF2_0](https://github.com/zht007/tensorflow-practice/blob/master/12_Classification_CIFAR/1_ResNet_for_CIFAR100_TF2_0.ipynb)[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/zht007/tensorflow-practice/blob/master/12_Classification_CIFAR/1_ResNet_for_CIFAR100_TF2_0.ipynb) [Tensorflow_2_0__ResNet实战CIFAR100数据集](https://github.com/zht007/tensorflow-practice/blob/master/12_Classification_CIFAR/Tensorflow_2_0__ResNet实战CIFAR100数据集.md) ### [13_Classification_Reuters](https://github.com/zht007/tensorflow-practice/tree/master/13_Classification_Reuters) [1_RNN_LSTM_GRU_for_Reuters_TF2_0.ipynb](https://github.com/zht007/tensorflow-practice/blob/master/13_Classification_Reuters/1_RNN_LSTM_GRU_for_Reuters_TF2_0.ipynb)[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/zht007/tensorflow-practice/blob/master/13_Classification_Reuters/1_RNN_LSTM_GRU_for_Reuters_TF2_0.ipynb) [2_RNN_LSTM_GRU_cell_for_Reuters_TF2_0.ipynb](https://github.com/zht007/tensorflow-practice/blob/master/13_Classification_Reuters/2_RNN_LSTM_GRU_cell_for_Reuters_TF2_0.ipynb)[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/zht007/tensorflow-practice/blob/master/13_Classification_Reuters/2_RNN_LSTM_GRU_cell_for_Reuters_TF2_0.ipynb) [Tensorflow2_0---RNN实战路透社新闻分类](https://github.com/zht007/tensorflow-practice/blob/master/13_Classification_Reuters/Tensorflow2_0---RNN实战路透社新闻分类.md)