Installation and configuration of Torch7 under Ubuntu

The main purpose of this series of tutorials in Torch7 is to introduce the introduction of torch. First share the installation of Torch7 today. (Install Torch7 in Ubuntu14.04)

Why Choose Torch

The goal of torch is to have the most flexibility and speed while building a scientific algorithm, which is a very simple process. Torch has a large community-driven ecosystem of machine learning, computer vision, signal processing, parallel processing, image, video, audio, and networking, built on the LUA community base.

At the heart of the torch are popular neural networks and optimized libraries, which are easy to use and offer maximum flexibility when implementing complex neural network topologies. You can create arbitrary neural network diagrams and parallelize them effectively on CPUs and GPUs.

Before installing, first identify your Ubuntu to install Git tool, open terminal via Ctrl+alt+t, enter git under terminal, add terminal output

It means that your system does not have Git installed. Under Terminal, enter sudo apt install git to install, as shown in.

After you've decided to install the Git tool successfully, you can start installing TORCH7!

The first step:

Gets the dependency packages necessary to install Luajit (the C language-written LUA interpreter) and torch. The code is as follows: Git clone https://github.com/torch/distro.git ~/torch--recursive as shown.

Step Two:

Because the default is to download the dependent package under the current path under the torch file, go to the Torch folder, open and execute the command in install-deps (the command execution time may be a bit long, don't worry ha). The code is as follows:

Step Three:

Execute the install.sh file as shown in.

Terminal tip:

Do your want to automatically prepend the Torch install location to PATH and Ld_library_path in Your/home/guodongwei/.bash Rc? (yes/no)

Input: Yes as shown.

Fourth Step:

Manually add the path to the PATH variable:

Then

Fifth Step:

Detects if the installation was successful. Enter the TH command at the terminal, if present, to indicate that the installation was successful.

At this point, Torch7 even if the installation is successful, then you can use it to carry out your own machine learning tasks. The next step is to get a more detailed anatomy torch7de Getting started.

Past US-click to view

Read the convolution Neural Network (CNN)

EM algorithm

A detailed description of convolutional neural networks

Gradient enhancement of model combinations (Gradient boosting)

Initial understanding of support vector Machine (SVM)-1

Support Vector Machine (SVM) (2)

The usage statistics of distance and similarity measure in machine learning

Convolution neural network of feature learning

Support Vector Machine (SVM)--3

Support Vector Machine (SVM)--(4)

The Mercer theorem and loss function of support vector machine (SVM)----5

SMO-------of support vector Machines 7

Classic machine learning Books recommended

Python Scientific Computing (book recommendation)

Python: Common machine learning Framework

Installation and configuration of Torch7 under Ubuntu