MatConvNet Convolutional Neural Networks for MATLAB

被引：1674

作者：

Vedaldi, Andrea ^{[1
]}

Lenc, Karel ^{[1
]}

机构：

[1] Univ Oxford, Oxford OX1 2JD, England

来源：

MM'15: PROCEEDINGS OF THE 2015 ACM MULTIMEDIA CONFERENCE | 2015年

基金：

英国工程与自然科学研究理事会;

关键词：

Computer vision; image understanding; machine learning; deep learning; convolutional neural networks;

D O I：

10.1145/2733373.2807412

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

MATCONVNET is an open source implementation of Convolutional Neural Networks (CNNs) with a deep integration in the MATLAB environment. The toolbox is designed with an emphasis on simplicity and flexibility. It exposes the building blocks of CNNs as easy-to-use MAT LAB functions, providing routines for computing convolutions with filter banks, feature pooling, normalisation, and much more. MATCONVNET can be easily extended, often using only MATLAB code, allowing 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 containing millions of training examples.

引用

页码：689 / 692

页数：4