RecNN：围绕pytorch 1.7构建的增强推荐工具包
这是我的学校项目。 它侧重于强化学习以进行个性化新闻推荐。 主要区别在于，它试图通过动态生成的项目嵌入来解决在线非政策学习。 我想使用SOTA算法创建一个库，以加强学习建议，并提供您喜欢的抽象级别。
:bar_chart: 这些功能可以总结为
根据您的决定进行抽象：您可以导入整个算法（例如DDPG）并将其告诉ddpg.learn（batch），可以分别导入网络和学习功能，为任务创建自定义加载程序，也可以自己定义所有内容。
示例不包含任何垃圾代码或变通办法：纯模型定义和算法本身在一个文件中。 我写了几篇文章解释其功能。
学习围绕支持ML20M等的顺序或框架环境构建。 Seq和Frame确定顺序数据的长度类型，seq是完全顺序动态大小（WIP），而帧只是静态帧。
状态表示模块具有多种方法。 对于顺序状态表示，可以使用LSTM / RNN / GRU（WIP）
使用Modin（Dask / Ray）并行数据加载和缓存
Pytorch 1.7支持Tensorboard可视化。
将来会添加新的数据集。
:books: 中篇文章
回购协议由两部分组成：库（./recnn）和游乐场（.
文件下载
资源详情
[{"title":"（ 72 个子文件 2.04MB ） RecNN：围绕pytorch 1.7构建的增强推荐工具包","children":[{"title":"RecNN-master","children":[{"title":"setup.py <span style='color:#111;'> 1.01KB </span>","children":null,"spread":false},{"title":".gitignore <span style='color:#111;'> 1.32KB </span>","children":null,"spread":false},{"title":"recnn","children":[{"title":"data","children":[{"title":"env.py <span style='color:#111;'> 13.27KB </span>","children":null,"spread":false},{"title":"dataset_functions.py <span style='color:#111;'> 5.74KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 129B </span>","children":null,"spread":false},{"title":"utils.py <span style='color:#111;'> 8.22KB </span>","children":null,"spread":false},{"title":"pandas_backend.py <span style='color:#111;'> 948B </span>","children":null,"spread":false},{"title":"db_con.py <span style='color:#111;'> 2.02KB </span>","children":null,"spread":false}],"spread":true},{"title":"__init__.py <span style='color:#111;'> 51B </span>","children":null,"spread":false},{"title":"utils","children":[{"title":"plot.py <span style='color:#111;'> 3.54KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 65B </span>","children":null,"spread":false},{"title":"misc.py <span style='color:#111;'> 879B </span>","children":null,"spread":false}],"spread":true},{"title":"nn","children":[{"title":"algo.py <span style='color:#111;'> 6.58KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 99B </span>","children":null,"spread":false},{"title":"update","children":[{"title":"td3.py <span style='color:#111;'> 4.64KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 195B </span>","children":null,"spread":false},{"title":"reinforce.py <span style='color:#111;'> 3.70KB </span>","children":null,"spread":false},{"title":"misc.py <span style='color:#111;'> 1.52KB </span>","children":null,"spread":false},{"title":"ddpg.py <span style='color:#111;'> 2.99KB </span>","children":null,"spread":false},{"title":"bcq.py <span style='color:#111;'> 6.11KB </span>","children":null,"spread":false}],"spread":true},{"title":"models.py <span style='color:#111;'> 9.28KB </span>","children":null,"spread":false}],"spread":true}],"spread":true},{"title":"res","children":[{"title":"article_1.png <span style='color:#111;'> 216.70KB </span>","children":null,"spread":false},{"title":"logo big.png <span style='color:#111;'> 28.17KB </span>","children":null,"spread":false},{"title":"article_2.png <span style='color:#111;'> 153.21KB </span>","children":null,"spread":false}],"spread":true},{"title":"requirements.txt <span style='color:#111;'> 208B </span>","children":null,"spread":false},{"title":"LICENSE <span style='color:#111;'> 11.09KB </span>","children":null,"spread":false},{"title":"setup.cfg <span style='color:#111;'> 75B </span>","children":null,"spread":false},{"title":"examples","children":[{"title":"1. Vanilla RL","children":[{"title":"2. DDPG.ipynb <span style='color:#111;'> 139.34KB </span>","children":null,"spread":false},{"title":"1. Anomaly Detection.ipynb <span style='color:#111;'> 93.00KB </span>","children":null,"spread":false},{"title":"4. SAC.ipynb <span style='color:#111;'> 117.25KB </span>","children":null,"spread":false},{"title":"5. LSTM State Encoder.ipynb <span style='color:#111;'> 18.46KB </span>","children":null,"spread":false},{"title":"3. TD3.ipynb <span style='color:#111;'> 378.81KB </span>","children":null,"spread":false}],"spread":true},{"title":"0. Embeddings Generation","children":[{"title":"1. (proof of concept) DQN.ipynb <span style='color:#111;'> 30.62KB </span>","children":null,"spread":false},{"title":"Pipelines","children":[{"title":"ML20M","children":[{"title":"3. Feature Engineering .ipynb <span style='color:#111;'> 521.84KB </span>","children":null,"spread":false},{"title":"2. NLP.ipynb <span style='color:#111;'> 12.04KB </span>","children":null,"spread":false},{"title":"1. Async Parsing.ipynb <span style='color:#111;'> 11.53KB </span>","children":null,"spread":false},{"title":"4. Graph Embeddings.ipynb <span style='color:#111;'> 22.74KB </span>","children":null,"spread":false},{"title":"5. The Big Merge.ipynb <span style='color:#111;'> 11.51KB </span>","children":null,"spread":false}],"spread":true}],"spread":true}],"spread":true},{"title":"99.To be released, but working","children":[{"title":"4. SearchNet","children":[{"title":"1. DDPG_SN.ipynb <span style='color:#111;'> 14.12KB </span>","children":null,"spread":false}],"spread":true},{"title":"2. BCQ","children":[{"title":"2. BCQ Pyro.ipynb <span style='color:#111;'> 19.59KB </span>","children":null,"spread":false},{"title":"1. BCQ PyTorch .ipynb <span style='color:#111;'> 220.65KB </span>","children":null,"spread":false}],"spread":true},{"title":"3. Decentralized Recommendation with PySyft","children":[{"title":"1. PySyft with RecNN Environment .ipynb <span style='color:#111;'> 16.33KB </span>","children":null,"spread":false}],"spread":false}],"spread":true},{"title":"[Library Basics]","children":[{"title":"1. Getting Started.ipynb <span style='color:#111;'> 141.11KB </span>","children":null,"spread":false},{"title":"algorithms how to","children":[{"title":"ddpg.ipynb <span style='color:#111;'> 141.46KB </span>","children":null,"spread":false},{"title":"reinforce.ipynb <span style='color:#111;'> 110.21KB </span>","children":null,"spread":false},{"title":"td3.ipynb <span style='color:#111;'> 59.15KB </span>","children":null,"spread":false}],"spread":false},{"title":"2. Different Pandas Backends.ipynb <span style='color:#111;'> 6.41KB </span>","children":null,"spread":false}],"spread":true},{"title":"[Results]","children":[{"title":"2. Diversity Test (Indexes).ipynb <span style='color:#111;'> 215.05KB </span>","children":null,"spread":false},{"title":"4. BCQ Stochastic Diversity .ipynb <span style='color:#111;'> 203.12KB </span>","children":null,"spread":false},{"title":"1. Ranking.ipynb <span style='color:#111;'> 135.66KB </span>","children":null,"spread":false},{"title":"3. Distances Test.ipynb <span style='color:#111;'> 46.33KB </span>","children":null,"spread":false}],"spread":true},{"title":"readme.md <span style='color:#111;'> 1.36KB </span>","children":null,"spread":false},{"title":"2. REINFORCE TopK Off Policy Correction","children":[{"title":"1. Basic Reinforce with RecNN.ipynb <span style='color:#111;'> 91.68KB </span>","children":null,"spread":false},{"title":"2. Reinforce Off Policy Correction.ipynb <span style='color:#111;'> 47.74KB </span>","children":null,"spread":false},{"title":"0. Inner workings of REINFORCE inside recnn (optional).ipynb <span style='color:#111;'> 20.69KB </span>","children":null,"spread":false},{"title":"3. TopK Reinforce Off Policy Correction.ipynb <span style='color:#111;'> 86.88KB </span>","children":null,"spread":false}],"spread":false},{"title":"streamlit_demo.py <span style='color:#111;'> 18.01KB </span>","children":null,"spread":false}],"spread":true},{"title":"readme.md <span style='color:#111;'> 7.28KB </span>","children":null,"spread":false},{"title":".circleci","children":[{"title":"tests","children":[{"title":"main.py <span style='color:#111;'> 144B </span>","children":null,"spread":false},{"title":"learning.py <span style='color:#111;'> 2.34KB </span>","children":null,"spread":false}],"spread":true},{"title":"config.yml <span style='color:#111;'> 1.11KB </span>","children":null,"spread":false}],"spread":true},{"title":"docs","children":[{"title":"Makefile <span style='color:#111;'> 638B </span>","children":null,"spread":false},{"title":"make.bat <span style='color:#111;'> 799B </span>","children":null,"spread":false},{"title":"source","children":[{"title":"index.rst <span style='color:#111;'> 1.76KB </span>","children":null,"spread":false},{"title":"conf.py <span style='color:#111;'> 1.99KB </span>","children":null,"spread":false},{"title":"data.rst <span style='color:#111;'> 2.38KB </span>","children":null,"spread":false},{"title":"examples","children":[{"title":"examples.rst <span style='color:#111;'> 360B </span>","children":null,"spread":false},{"title":"your_data.rst <span style='color:#111;'> 6.82KB </span>","children":null,"spread":false},{"title":"getting_started.rst <span style='color:#111;'> 5.41KB </span>","children":null,"spread":false},{"title":"pandas_backend.rst <span style='color:#111;'> 2.06KB </span>","children":null,"spread":false},{"title":"cloning_from_github.rst <span style='color:#111;'> 1.24KB </span>","children":null,"spread":false}],"spread":false},{"title":"nn.rst <span style='color:#111;'> 468B </span>","children":null,"spread":false}],"spread":false}],"spread":true}],"spread":false}],"spread":true}]
评论信息
其他资源
- KOB KT F360说明书.docx
- An Introduction to Multivariate Statistical Analysis (3ed)
- PSO-LSSVM的MATLAB代码.rar
- Linux环境下的文件安全传输(C/C++)
- 反激式开关电源原理图及PCB
- opencv-4.0.0-windows版本
- 【课设报告 | 附代码】基于STM32的4层电梯控制系统 课程设计.docx
- 基于fpga产生正弦波的Verilog程序
- MFC自定义界面HUI，高效简单，含详细注释和示例
- The_design_of_the_unix_operating_system.pdf(文字版）
- CRC Handbook of Chemistry and Physics (Internet Version 2016)(96th)
- 逻辑思维训练500题(附答案)
- 基于mfc中opengl鼠标控制视图旋转缩放
- 用贪心算法实现会场安排问题
- 吉林省echarts地图js附赠echarts-min-js和china-js和china-json和其他各省市json文件.rar
- vslayout.part2.rar
- php的最简单的调查问卷功能
- 33.深度解密三十三：微信搜一搜中各频道的信息来源及相关规则讲解.pdf
- R in a Nutshell, 2nd Edition
- jsp ssh mvc java web j2ee学生信息管理系统+论文+源码 毕业设计
- DICOM文件信息修改程序
- 佳能相机快门检查工具
- pycharm2018.2汉化 解决设置打不开问题
免责申明
【只为小站】的资源来自网友分享，仅供学习研究，请务必在下载后24小时内给予删除，不得用于其他任何用途，否则后果自负。基于互联网的特殊性，【只为小站】 无法对用户传输的作品、信息、内容的权属或合法性、合规性、真实性、科学性、完整权、有效性等进行实质审查；无论 【只为小站】 经营者是否已进行审查，用户均应自行承担因其传输的作品、信息、内容而可能或已经产生的侵权或权属纠纷等法律责任。
本站所有资源不代表本站的观点或立场，基于网友分享，根据中国法律《信息网络传播权保护条例》第二十二条之规定，若资源存在侵权或相关问题请联系本站客服人员，zhiweidada#qq.com，请把#换成@，本站将给予最大的支持与配合，做到及时反馈和处理。关于更多版权及免责申明参见 版权及免责申明
本站所有资源不代表本站的观点或立场，基于网友分享，根据中国法律《信息网络传播权保护条例》第二十二条之规定，若资源存在侵权或相关问题请联系本站客服人员，zhiweidada#qq.com，请把#换成@，本站将给予最大的支持与配合，做到及时反馈和处理。关于更多版权及免责申明参见 版权及免责申明