MatConvNet - Convolutional Neural Networks for MATLAB

TL;DR

MatConvNet is a MATLAB toolbox that simplifies the development and training of convolutional neural networks, supporting fast prototyping and efficient computation on CPU and GPU for large datasets.

Contribution

It provides an easy-to-use, flexible MATLAB framework for CNN implementation, enabling rapid development and efficient training of complex models.

Findings

Supports large-scale datasets like ImageNet ILSVRC

Enables fast prototyping of new CNN architectures

Offers efficient CPU and GPU computation

Abstract

MatConvNet is an implementation of Convolutional Neural Networks (CNNs) for MATLAB. The toolbox is designed with an emphasis on simplicity and flexibility. It exposes the building blocks of CNNs as easy-to-use MATLAB functions, providing routines for computing linear convolutions with filter banks, feature pooling, and many more. In this manner, MatConvNet allows fast prototyping of new CNN architectures; at the same time, it supports efficient computation on CPU and GPU allowing to train complex models on large datasets such as ImageNet ILSVRC. This document provides an overview of CNNs and how they are implemented in MatConvNet and gives the technical details of each computational block in the toolbox.