MatConvNet - Convolutional Neural Networks for MATLAB
This provides a flexible and simple tool for researchers and practitioners in MATLAB environments to work with CNNs, but it is incremental as it adapts existing CNN methods to a specific software platform.
The authors introduced MatConvNet, a MATLAB toolbox for implementing Convolutional Neural Networks (CNNs) that enables fast prototyping of new architectures and supports efficient training on large datasets like ImageNet ILSVRC.
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.