Awesome Torch

This blog from:

A curated list of awesome Torch tutorials, projects and communities.

Table of Contents

Tutorials

Model Zoo

Codes and related articles. (#) means authors of code and paper are different.

Recurrent Networks

Convolutional Networks

Reinforcement Learning

  • Deep Q-networkDeepMind-Atari-Deep-Q-Learner

    • Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Andrei A. Rusu, Joel Veness, Marc G. Bellemare, Alex Graves, Martin Riedmiller, Andreas K. Fidjeland, Georg Ostrovski, Stig Petersen, Charles Beattie, Amir Sadik, Ioannis Antonoglou, Helen King, Dharshan Kumaran, Daan Wierstra, Shane Legg, Demis Hassabis, Human-Level Control through Deep Reinforcement Learning, Nature, [Paper]
  • Deep Attention Recurrent Q-Network
    • (#) Ivan Sorokin, Alexey Seleznev, Mikhail Pavlov, Aleksandr Fedorov, Anastasiia Ignateva, Deep Attention Recurrent Q-Network, NIPS 2015, [Paper]
  • Grid World DQN using torch7
    • (#) Marc G. Bellemare, Georg Ostrovski, Arthur Guez, Philip S. Thomas, Rémi Munos, Increasing the Action Gap: New Operators for Reinforcement Learning, arXiv:1512.04860, [Paper]
  • Deep Q-Networks for Accelerating the Training of Deep Neural Networks
    • Jie Fu, Zichuan Lin, Miao Liu, Nicholas Leonard, Jiashi Feng, Tat-Seng Chua, Deep Q-Networks for Accelerating the Training of Deep Neural Networks, arXiv:1606.01467, [Paper]
  • ActorMimic
    • Emilio Parisotto, Jimmy Lei Ba, Ruslan Salakhutdinov, Actor-Mimic: Deep Multitask and Transfer Reinforcement Learning, ICLR 2016, [Paper]
  • MazeBase: a sandbox for learning from games
    • Sainbayar Sukhbaatar, Arthur Szlam, Gabriel Synnaeve, Soumith Chintala, Rob Fergus, MazeBase: A Sandbox for Learning from Games, arXiv:1511.07401, [Paper]
  • mario-ai
    • This project contains code to train a model that automatically plays the first level of Super Mario World using only raw pixels as the input (no hand-engineered features).The used technique is deep Q-learning, as described in the Atari paper (Summary), combined with a Spatial Transformer.
  • Deep Successor Reinforcement Learning (DSR)
    • Tejas D. Kulkarni, Ardavan Saeedi, Simanta Gautam, Samuel J. Gershman, Deep Successor Reinforcement Learning, arXiv:1606.02396, [Paper]
  • ViZDoom
    • ViZDoom allows developing AI bots that play Doom using only the visual information (the screen buffer). It is primarily intended for research in machine visual learning, and deep reinforcement learning, in particular.
  • MIXER - Sequence Level Training with Recurrent Neural Networks
    • Marc'Aurelio Ranzato, Sumit Chopra, Michael Auli, Wojciech Zaremba, Sequence Level Training with Recurrent Neural Networks, ICLR 2016, [Paper]
  • TorchQLearning
    • Implementation of a simple example of Q learning in Torch.
  • rltorch
    • This package is a Reinforcement Learning package written in LUA for Torch.
  • Opponent Modeling in Deep Reinforcement Learning
    • He He, Jordan Boyd-Graber, Kevin Kwok, Hal Daumé III, Opponent Modeling in Deep Reinforcement Learning, ICML 2016, [Paper]

### ETC

Libraries

Model related

  • nn : an easy and modular way to build and train simple or complex neural networks [Code] [Documentation]
  • dpnn : extensions to the nn lib, more modules [Code]
  • nnx : extension to the nn lib, experimental neural network modules and criterions [Code]
  • nninit : weight initialisation schemes [Code]
  • rnn : Recurrent Neural Network library [Code]
  • optim : A numeric optimization package for Torch [Code]
  • dp : a deep learning library designed for streamlining research and development [Code] [Documentation]
  • nngraph : provides graphical computation for nn library [Code] [Oxford Introduction]
  • nnlr : Add layer-wise learning rate schemes to Torch [Code]
  • optnet: Memory optimizations for torch neural networks. [Code]
  • autograd : Autograd automatically differentiates native Torch code. [Code]
  • torchnet: framework for torch which provides a set of abstractions aiming at encouraging code re-use as well as encouraging modular programming [Code] [Paper]

GPU related

  • distro-cl: An OpenCL distribution for Torch [Code]
  • cutorch : A CUDA backend for Torch [Code]
  • cudnn : Torch FFI bindings for NVIDIA CuDNN [Code]
  • fbcunn : Facebook's extensions to torch/cunn [Code] [Documentation]

IDE related

  • iTorch : IPython kernel for Torch with visualization and plotting [Code]
  • Lua Development Tools (LDT) : based on Eclipse [Code]
  • zbs-torch : A lightweight Lua-based IDE for Lua with code completion, syntax highlighting, live coding, remote debugger, and code analyzer [Code]

ETC

  • fblualib : Facebook libraries and utilities for Lua [Code]
  • loadcaffe : Load Caffe networks in Torch [Code]
  • Purdue e-lab lib : A collection of snippets and libraries [Code]
  • torch-android : Torch for Android [Code]
  • torch-models : Implementation of state-of-art models in Torch. [Code]
  • lutorpy : Lutorpy is a libray built for deep learning with torch in python. [Code]
  • CoreNLP.lua : Lua client for Stanford CoreNLP. [Code]
  • Torchlib: Data structures and libraries for Torch. [Code]
  • THFFmpeg: Torch bindings for FFmpeg (reading videos only) [Code]
  • tunnel: Data Driven Framework for Distributed Computing in Torch 7, [Code]
  • pytorch: Python wrappers for torch and lua, [Code]
  • lutorpy: Use torch in python for deep learning., [Code]
  • torch-pcl: Point Cloud Library (PCL) bindings for Torch, [Code]
  • Moses: A Lua utility-belt library for functional programming. It complements the built-in Lua table library, making easier operations on arrays, lists, collections. [Cpde]

Links

Awesome Torch的更多相关文章

  1. Torch Problems: require some packages doesn't work

    I've recently got a problem. require 'cutorch' doesn't work. But it was ok yesterday, although I hav ...

  2. Torch学习笔记1--Torch简介

    Torch是什么 Torch是一个由Lua语言开发的深度学习框架,目前支持Mac OS X 和Ubuntu 12及以上,官网 ,github地址. 具有如下特点: 交互式开发工具 可视化式的工具 第三 ...

  3. 深度学习框架 Torch 7 问题笔记

    深度学习框架 Torch 7 问题笔记 1. 尝试第一个 CNN 的 torch版本, 代码如下: -- We now have 5 steps left to do in training our ...

  4. Torch 网络层 参数的初始化问题

    Torch 网络层 参数的初始化问题 参考链接: https://github.com/Kaixhin/nninit 从 Torch 中自带的包,可以看到:https://github.com/tor ...

  5. Torch 7 load saved model failed, 加载保存的模型失败

    Torch 7 load saved model failed, 加载保存的模型失败: 可以尝试下面的解决方案:  

  6. Torch 日志文件的保存 logroll

    Torch 日志文件的保存 logroll 怎样将 Torch 在终端显示的信息,保存到 log 文件中 ?   现在介绍一种方法:利用 logroll 的方式.  参考 https://github ...

  7. torch 入门

    torch 入门1.安装环境我的环境mac book pro 集成显卡 Intel Iris不能用 cunn 模块,因为显卡不支持 CUDA2.安装步骤: 官方文档 (1).git clone htt ...

  8. 对torch的一点感想

    torch是一个基于LuaJIT的科学计算框架,知乎上有个人回答说torch比较适合科研用途, torch与matlab的很多函数很相似

  9. torch基本操作

    1.在terminal中th进入troch,th+文件名.lua运行文件.进入torch之后,dofile+"文件名.lua"运行文件

  10. torch基本命令

    命令行输入th进入torch框架 命令行输入th + lua文件表示用torch执行lua文件

随机推荐

  1. B树,B+树,B*树以及R树的介绍

    https://blog.csdn.net/peterchan88/article/details/52248714 作者:July.weedge.Frankie.编程艺术室出品. 说明:本文从B树开 ...

  2. Keras 如何利用训练好的神经网络进行预测

    分成两种情况,一种是公开的训练好的模型,下载后可以使用的,一类是自己训练的模型,需要保存下来,以备今后使用. 如果是第一种情况,则参考    http://keras-cn.readthedocs.i ...

  3. Echo团队团队展示

    班级:软件工程1916|W 作业:团队作业第一次-团队展示 团队名称:Echo 课程目标:展示团队 成员信息 队员学号 队员姓名 个人博客地址 备注 221600418 黄少勇 http://www. ...

  4. uva 1322 Minimizing Maximizer

    题意: 有n个数,m个排序器,每个排序器可以把区间ai到bi的数从小到大排序.这m个排序器的输出就是m个排序之后的第n个数. 现在发现有些排序器是多余的.问至少需要多少个排序器可以使得输出不变.排序器 ...

  5. 20165305 苏振龙《Java程序设计》第四周课上测试补做

    第一次测试 第二次测试 第三次测试 上传代码 第四次测试 总结 之前我一直在git bash进行程序设计,但是对于我来说操作起来有点困难,所以我改用了虚拟机,之后之前一直困扰我的问题在虚拟机下就没有了 ...

  6. Linux基础命令---调整程序优先级renice

    renice renice指令可以重新调整程序运行的优先级,可以通过进程id.用户id.组id来修改优先级.修改组的等级,影响组内所有用户的所有进程优先级:修改用户等级,影响该用户的所有进程优先级.除 ...

  7. Linux基础命令---显示登录用户logname

    logname 显示当前登录的用户名称.此命令的适用范围:RedHat.RHEL.Ubuntu.CentOS.SUSE.openSUSE.Fedora. 1.语法        logname   2 ...

  8. 算法提高 c++_ch02_01 (强制类型转换)

    编写一个程序,利用强制类型转换打印元音字母大小写10种形式的ASCII码. 输出的顺序为:大写的字母A,E,I,O,U的ASCII码,小写的字母a,e,i,o,u的ASCII码.所有的ASCII码都用 ...

  9. Oracle执行计划 explain plan

    Rowid的概念:rowid是一个伪列,既然是伪列,那么这个列就不是用户定义,而是系统自己给加上的. 对每个表都有一个rowid的伪列,但是表中并不物理存储ROWID列的值.不过你可以像使用其它列那样 ...

  10. 全球最大的3D数据集公开了!标记好的10800张全景图

    Middlebury数据集 http://vision.middlebury.edu/stereo/data/ KITTI数据集简介与使用 https://blog.csdn.net/solomon1 ...