码迷,mamicode.com
首页 > 其他好文 > 详细

Rethinking the Inception Architecture for Computer Vision

时间:2017-11-05 17:25:11      阅读:114      评论:0      收藏:0      [点我收藏+]

标签:regular   sed   zed   core   alt   http   class   ons   res   

 

https://arxiv.org/abs/1512.00567

 

Convolutional networks are at the core of most state-of-the-art computer vision solutions for a wide variety of tasks. Since 2014 very deep convolutional networks started to become mainstream, yielding substantial gains in various benchmarks. Although increased model size and computational cost tend to translate to immediate quality gains for most tasks (as long as enough labeled data is provided for training), computational efficiency and low parameter count are still enabling factors for various use cases such as mobile vision and big-data scenarios. Here we explore ways to scale up networks in ways that aim at utilizing the added computation as efficiently as possible by suitably factorized convolutions and aggressive regularization. We benchmark our methods on the ILSVRC 2012 classification challenge validation set demonstrate substantial gains over the state of the art: 21.2% top-1 and 5.6% top-5 error for single frame evaluation using a network with a computational cost of 5 billion multiply-adds per inference and with using less than 25 million parameters. With an ensemble of 4 models and multi-crop evaluation, we report 3.5% top-5 error on the validation set (3.6% error on the test set) and 17.3% top-1 error on the validation set.

 

Rethinking the Inception Architecture for Computer Vision

标签:regular   sed   zed   core   alt   http   class   ons   res   

原文地址:http://www.cnblogs.com/yuanjiangw/p/7787775.html

(0)
(0)
   
举报
评论 一句话评论(0
登录后才能评论!
© 2014 mamicode.com 版权所有  联系我们:gaon5@hotmail.com
迷上了代码!