Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.
Awesome Lists | Featured Topics | Projects
https://github.com/princewen/tensorflow_practice

tensorflow实战练习，包括强化学习、推荐系统、nlp等
https://github.com/princewen/tensorflow_practice
Last synced: 22 days ago
JSON representation
tensorflow实战练习，包括强化学习、推荐系统、nlp等
Host: GitHub
URL: https://github.com/princewen/tensorflow_practice
Owner: princewen
Created: 2018-02-23T06:31:20.000Z (over 6 years ago)
Default Branch: master
Last Pushed: 2023-09-24T19:46:36.000Z (about 1 year ago)
Last Synced: 2024-10-01T11:23:56.199Z (about 1 month ago)
Language: Python
Homepage:
Size: 110 MB
Stars: 6,689
Watchers: 223
Forks: 3,276
Open Issues: 47
Metadata Files:
- Readme: README.md
Awesome Lists containing this project

awesome-ai-list-guide - tensorflow_practice
my-awesome - princewen/tensorflow_practice - 09 star:6.7k fork:3.3k tensorflow实战练习，包括强化学习、推荐系统、nlp等 (Python)
README

        Tensroflow练习

======

相关数据集下载地址：链接:https://pan.baidu.com/s/1GMv7_3qruoVZBJMvN-afGA  密码:ako7

基于tf1.4

目录

1、基础


[基本语法
](https://github.com/princewen/tensorflow_practice/blob/master/basic/basic.py)

[tensorBoard使用
](https://github.com/princewen/tensorflow_practice/blob/master/basic/tensorBoard.py)

[dropout
](https://github.com/princewen/tensorflow_practice/blob/master/basic/dropout.py)

[模型保存与重载
](https://github.com/princewen/tensorflow_practice/blob/master/basic/save2file.py)

[基本神经网络
](https://github.com/princewen/tensorflow_practice/blob/master/basic/first_nerual_network.py)

[卷积神经网络
](https://github.com/princewen/tensorflow_practice/blob/master/basic/CNN.py)




2、自然语言相关


[static_RNN
](https://github.com/princewen/tensorflow_practice/blob/master/nlp/RNN_static_cell.py)

[dynamic_RNN
](https://github.com/princewen/tensorflow_practice/blob/master/nlp/RNN_dynamic_cell.py)

[LSTM
](https://github.com/princewen/tensorflow_practice/blob/master/nlp/LSTM.py)

[LSTM_regression
](https://github.com/princewen/tensorflow_practice/blob/master/nlp/LSTM_Regression.py)

[seq2seq
](https://github.com/princewen/tensorflow_practice/blob/master/nlp/basic_seq2seq.py)

[seq2seq_attention
](https://github.com/princewen/tensorflow_practice/tree/master/nlp/chat_bot_seq2seq_attention)




3、强化学习相关


[Q-learning
](https://github.com/princewen/tensorflow_practice/tree/master/RL/my_q_learning_new)

[SARSA
](https://github.com/princewen/tensorflow_practice/tree/master/RL/SARSA)

[SARSA-lambda
](https://github.com/princewen/tensorflow_practice/tree/master/RL/sarsa_lambda)

[DQN
](https://github.com/princewen/tensorflow_practice/tree/master/RL/DQN-demo)

[Double DQN
](https://github.com/princewen/tensorflow_practice/tree/master/RL/Double-DQN-demo)

[Dueling DQN
](https://github.com/princewen/tensorflow_practice/tree/master/RL/Dueling%20DQN%20Demo)

[Prioritized Replay DQN
](https://github.com/princewen/tensorflow_practice/tree/master/RL/Prioritized_Replay_DQN_demo)

[Policy Gradient
](https://github.com/princewen/tensorflow_practice/tree/master/RL/Basic-Policy-Network)

[Actor-Critic
](https://github.com/princewen/tensorflow_practice/tree/master/RL/Basic-Actor-Critic)

[DDPG
](https://github.com/princewen/tensorflow_practice/tree/master/RL/Basic-DDPG)

[Pointer-Network
](https://github.com/princewen/tensorflow_practice/tree/master/RL/myPtrNetwork)

[MADDPG
](https://github.com/princewen/tensorflow_practice/tree/master/RL/Basic-MADDPG-Demo)




4、推荐系统


[FM
](https://github.com/princewen/tensorflow_practice/tree/master/recommendation/recommendation-FM-demo)

[FFM
](https://github.com/princewen/tensorflow_practice/tree/master/recommendation/recommendation-FFM-Demo)

[DeepFM
](https://github.com/princewen/tensorflow_practice/tree/master/recommendation/Basic-DeepFM-model)

[Deep Cross Network
](https://github.com/princewen/tensorflow_practice/tree/master/recommendation/Basic-DCN-Demo)

[P NN
](https://github.com/princewen/tensorflow_practice/tree/master/recommendation/Basic-PNN-Demo)

[NFM
](https://github.com/princewen/tensorflow_practice/tree/master/recommendation/Basic-NFM-Demo)

[AFM
](https://github.com/princewen/tensorflow_practice/tree/master/recommendation/Basic-AFM-Demo)

[MLR
](https://github.com/princewen/tensorflow_practice/tree/master/recommendation/Basic-MLR-Demo)

[DIN
](https://github.com/princewen/tensorflow_practice/tree/master/recommendation/Basic-DIN-Demo)

[Bandit
](https://github.com/princewen/tensorflow_practice/tree/master/recommendation/Basic-Bandit-Demo)

[GBDT+LR
](https://github.com/princewen/tensorflow_practice/tree/master/recommendation/GBDT%2BLR-Demo)

[evaluation-metrics
](https://github.com/princewen/tensorflow_practice/tree/master/recommendation/Basic-Evaluation-metrics)

[NCF
](https://github.com/princewen/tensorflow_practice/tree/master/recommendation/Basic-NCF-Demo)




5、GAN


[Basic GAN
](https://github.com/princewen/tensorflow_practice/blob/master/GAN/GAN.py)

[SeqGAN
](https://github.com/princewen/tensorflow_practice/tree/master/GAN/seqgan)










推荐阅读

==============

1、基础


[TensorFlow基础知识点总结
](https://www.jianshu.com/p/ce213e6b2dc0)

[用tensorboard来看看我们的网络流吧
](https://www.jianshu.com/p/41466470b347)

[使用dropout来避免过拟合吧
](https://www.jianshu.com/p/4f1b525ddf86)

[使用Tensorflow实现第一个神经网络吧！
](https://www.jianshu.com/p/596a30d46f34y)

[实现CNN对mnist手写数字分类
](https://www.jianshu.com/p/49ab6568e472)




2、自然语言相关


[使用简单的RNN观测数字中的规律
](https://www.jianshu.com/p/3ccc1eb5fda2)

[更进一步，使用LSTM实现对手写数字识别
](https://www.jianshu.com/p/d25baccde6bc)

[简单的Seq2Seq实现作对联
](https://www.jianshu.com/p/83443b2baf27)

[使用Seq2Seq+attention model实现简单的Chatbot
](https://www.jianshu.com/p/aab40f439012)




3、强化学习相关


[实战深度强化学习DQN-理论和实践
](https://www.jianshu.com/p/10930c371cac)

[DQN三大改进(一)-Double DQN
](https://www.jianshu.com/p/fae51b5fe000)

[DQN三大改进(二)-Prioritised replay
](https://www.jianshu.com/p/db14fdc67d2c)

[DQN三大改进(三)-Dueling Network
](https://www.jianshu.com/p/b421c85796a2)

[深度强化学习-Policy Gradient基本实现
](https://www.jianshu.com/p/2ccbab48414b)

[深度强化学习-Actor-Critic算法原理和实现
](https://www.jianshu.com/p/6fe18d0d8822)

[深度强化学习-DDPG算法原理和实现
](https://www.jianshu.com/p/6fe18d0d8822)

[Pointer-network理论及tensorflow实战
](https://www.jianshu.com/p/2ad389e91467)

[探秘多智能体强化学习-MADDPG算法原理及简单实现
](https://www.jianshu.com/p/4e4e35d80137)




4、推荐系统


[推荐系统遇上深度学习(一)--FM模型理论和实践
](https://www.jianshu.com/p/152ae633fb00)

[推荐系统遇上深度学习(二)--FFM模型理论和实践
](https://www.jianshu.com/p/781cde3d5f3d)

[推荐系统遇上深度学习(三)--DeepFM模型理论和实践
](https://www.jianshu.com/p/6f1c2643d31b)

[推荐系统遇上深度学习(四)--多值离散特征的embedding解决方案
](https://www.jianshu.com/p/4a7525c018b2)

[推荐系统遇上深度学习(五)--Deep&Cross Network模型理论和实践
](https://www.jianshu.com/p/77719fc252fa)

[推荐系统遇上深度学习(六)--PNN模型理论和实践
](https://www.jianshu.com/p/be784ab4abc2)

[推荐系统遇上深度学习(七)--NFM模型理论和实践
](https://www.jianshu.com/p/4e65723ee632)

[推荐系统遇上深度学习(八)--AFM模型理论和实践
](https://www.jianshu.com/p/83d3b2a1e55d)

[推荐系统遇上深度学习(九)--评价指标AUC原理及实践
](https://www.jianshu.com/p/4dde15a56d44)

[推荐系统遇上深度学习(十)--GBDT+LR融合方案实战
](https://www.jianshu.com/p/96173f2c2fb4)

[推荐系统遇上深度学习(十一)--神经协同过滤NCF原理及实战
](https://www.jianshu.com/p/6173dbde4f53)

[推荐系统遇上深度学习(十二)--推荐系统中的EE问题及基本Bandit算法
](https://www.jianshu.com/p/95b2de50ce44)

[推荐系统遇上深度学习(十三)--linUCB方法浅析及实现
](https://www.jianshu.com/p/e0e843d78e3c)

[推荐系统遇上深度学习(十四)--《DRN:A Deep Reinforcement Learning Framework for News Recommendation》
](https://www.jianshu.com/p/c0384b213320)

[推荐系统遇上深度学习(十五)--强化学习在京东推荐中的探索
](https://www.jianshu.com/p/b9113332e33e)

[推荐系统遇上深度学习(十六)--详解推荐系统中的常用评测指标
](https://www.jianshu.com/p/665f9f168eff)

[推荐系统遇上深度学习(十七)--探秘阿里之MLR算法浅析及实现
](https://www.jianshu.com/p/627fc0d755b2)

[推荐系统遇上深度学习(十八)--探秘阿里之深度兴趣网络(DIN)浅析及实现
](https://www.jianshu.com/p/73b6f5d00f46)

[推荐系统遇上深度学习(十九)--探秘阿里之完整空间多任务模型ESSM
](https://www.jianshu.com/p/35f00299c059)

[推荐系统遇上深度学习(二十)--贝叶斯个性化排序(BPR)算法原理及实战
](https://www.jianshu.com/p/ba1936ee0b69)

[推荐系统遇上深度学习(二十一)--阶段性回顾
](https://www.jianshu.com/p/99e8f24ec7df)

[推荐系统遇上深度学习(二十二)--DeepFM升级版XDeepFM模型强势来袭！
](https://www.jianshu.com/p/b4128bc79df0)

[推荐系统遇上深度学习(二十三)--大一统信息检索模型IRGAN在推荐领域的应用
](https://www.jianshu.com/p/d151b52e57f9)

[推荐系统遇上深度学习(二十四)--深度兴趣进化网络DIEN原理及实战！
](https://www.jianshu.com/p/6742d10b89a8)

[推荐系统遇上深度学习(二十五)--当知识图谱遇上个性化推荐
](https://www.jianshu.com/p/6a5e796499e8)

[推荐系统遇上深度学习(二十六)--知识图谱与推荐系统结合之DKN模型原理及实现
](https://www.jianshu.com/p/2e3cade31098)

[推荐系统遇上深度学习(二十七)--知识图谱与推荐系统结合之RippleNet模型原理及实现
](https://www.jianshu.com/p/c5ffaf7ed449)




5、GAN


[听说GAN很高大上，其实就这么简单
](https://www.jianshu.com/p/5f638f493b7a)

[对抗思想与强化学习的碰撞-SeqGAN模型原理和代码解析
](https://www.jianshu.com/p/de4e913e0580)