cvpr'14 BING objectness
Posted zherlock
tags:
篇首语:本文由小常识网(cha138.com)小编为大家整理,主要介绍了cvpr'14 BING objectness相关的知识,希望对你有一定的参考价值。
参考代码
https://github.com/torrvision/Objectness
调试到能运行,花了不少时间,中间读数据集报错这些都能出现的,可怕。
编译成功后,直接运行bing_linux,得到输出
Dataset:`/home/zherlock/Dataset/CV/VOC2007/‘ with 2501 training and 4952 testing
WinRecall.m Base = 2, W = 8, NSS = 2, perSz = 130
Learning stage I takes 5.27422 seconds...
Learning stage II takes 113.173 seconds...
Start predicting
Average time for predicting an image (MAXBGR) is 0.0426362s
1:0.249,0.304 10:0.478,0.448 100:0.795,0.607 1000:0.96,0.669 2000:0.97,0.673 3000:0.97,0.673 4000:0.97,0.673 5000:0.97,0.673
objectness的原文,我是没有通读过的,大概也是一个训练模型的思想,好像是两级的SVM。
emmmmmmmmmmmmm
接下来,
以上是关于cvpr'14 BING objectness的主要内容,如果未能解决你的问题,请参考以下文章
window.history.go 返回上一页bing'shua'xin
window.history.go 返回上一页bing'shua'xin
requests.exceptions.SSLError: HTTPSConnectionPool(host='cn.bing.com', port=443)报错解决方案
requests.exceptions.SSLError: HTTPSConnectionPool(host='cn.bing.com', port=443)报错解决方案