py-faster-rcnn代码
注意第18~20行是拿一个数(x1)和array(x1[ [0,2,3] ])去比:
aaarticlea/png;base64,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" alt="" />
2. box_inside_weights和box-outside_weights:
在smoothl1losslayer.cu里:
计算loss时乘的系数
3. tools/train_net.py:
对于git上默认的配置,这段代码实现:
- roidb = get_roidb( voc_2007_trainval )
- imdb = get_imdb( voc_2007_trainval )
generate_anchors.py:
注意原始py-faster-rcnn会设置batch_inds为0
proposal_layer.py:
bottom[0].shape=(1,18,7,7),最后得到all_scores.shpae=(1,9,7,7),根据注释,前面9层是背景,后面的9层才是前景,这里取bottom[0]里后面的9层。
proposal_target_layer.py:
bbox_overlaps函数在utils/bbox.pyx里,参考
偶见train.py:所以prototxt里不能随意改最后输出层的名字
涉及知识点:
- from IPython import embed;embed() #程序运行到这里会转成ipython环境
py-faster-rcnn代码的更多相关文章
- py faster rcnn+ 1080Ti+cudnn5.0
看了py-faster-rcnn上的issue,原来大家都遇到各种问题. 我要好好琢磨一下,看看到底怎么样才能更好地把GPU卡发挥出来.最近真是和GPU卡较上劲了. 上午解决了g++的问题不是. 然后 ...
- Faster RCNN代码理解(Python)
转自http://www.infocool.net/kb/Python/201611/209696.html#原文地址 第一步,准备 从train_faster_rcnn_alt_opt.py入: 初 ...
- Faster rcnn代码理解(1)
这段时间看了不少论文,回头看看,感觉还是有必要将Faster rcnn的源码理解一下,毕竟后来很多方法都和它有相近之处,同时理解该框架也有助于以后自己修改和编写自己的框架.好的开始吧- 这里我们跟着F ...
- Faster R-CNN代码例子
主要参考文章:1,从编程实现角度学习Faster R-CNN(附极简实现) 经常是做到一半发现收敛情况不理想,然后又回去看看这篇文章的细节. 另外两篇: 2,Faster R-CNN学习总结 ...
- Faster rcnn代码理解(4)
上一篇我们说完了AnchorTargetLayer层,然后我将Faster rcnn中的其他层看了,这里把ROIPoolingLayer层说一下: 我先说一下它的实现原理:RPN生成的roi区域大小是 ...
- Faster rcnn代码理解(2)
接着上篇的博客,咱们继续看一下Faster RCNN的代码- 上次大致讲完了Faster rcnn在训练时是如何获取imdb和roidb文件的,主要都在train_rpn()的get_roidb()函 ...
- Faster rcnn代码理解(3)
紧接着之前的博客,我们继续来看faster rcnn中的AnchorTargetLayer层: 该层定义在lib>rpn>中,见该层定义: 首先说一下这一层的目的是输出在特征图上所有点的a ...
- tensorflow faster rcnn 代码分析一 demo.py
os.environ["CUDA_VISIBLE_DEVICES"]=2 # 设置使用的GPU tfconfig=tf.ConfigProto(allow_soft_placeme ...
- Faster RCNN代码解析
1.faster_rcnn_end2end训练 1.1训练入口及配置 def train(): cfg.GPU_ID = 0 cfg_file = "../experiments/cfgs/ ...
- py faster rcnn的lib编译出错问题
真是好事多磨啊,计算机系统依然是14.04,而cuda依然是8.0,唯一不同的是时间不一样,下载的各种库版本有差别,GPU的driver不一样. 但是这样就出问题了,py-faster rcnn的li ...
随机推荐
- How to secure the ASP.NET_SessionId cookie? 设置ASP.NET_SessionId Secure=true
How to secure the ASP.NET_SessionId cookie? To add the ; secure suffix to the Set-Cookie http header ...
- BarTender安装常见问题集结
很多人在安装BarTender时,会出现各种安装程序信息警告提示,导致软件无法继续安装下去,那么针对这些Bartender安装问题我们要怎么正确解决呢?下面,小编将BarTender安装失败常见问题, ...
- 我的订单页面List
<%@ page language="java" contentType="text/html;charset=UTF-8"%> <%@ ta ...
- centos7上修改lv逻辑卷的大小
author:headsen chen date: 2019-03-18 15:24:22 1,查看 [root@localhost mnt]# df -h Filesystem Size Used ...
- nodejs electron 创建桌面应用
//首先安装cnpm npm install -g cnpm --registry=https://registry.npm.taobao.org //使用cnpm进行安装,使用方法和npm相同 cn ...
- Logistic 最大熵 朴素贝叶斯 HMM MEMM CRF 几个模型的总结
朴素贝叶斯(NB) , 最大熵(MaxEnt) (逻辑回归, LR), 因马尔科夫模型(HMM), 最大熵马尔科夫模型(MEMM), 条件随机场(CRF) 这几个模型之间有千丝万缕的联系,本文首先会 ...
- python装饰器语法
@就是decorator,早Python的高效开发中会用到,当然和java的annotation有一定的相似,但又不完全相同,看这篇文章:https://blog.csdn.net/zkp_987/a ...
- postgresql数据库安装及简单操作
自从MySQL被Oracle收购以后,PostgreSQL逐渐成为开源关系型数据库的首选. 本文介绍PostgreSQL的安装和基本用法,供初次使用者上手.以下内容基于Debian操作系统,其他操作系 ...
- 一次完整的从webshell到域控的探索之路
前言 内网渗透测试资料基本上都是很多大牛的文章告诉我们思路如何,但是对于我等小菜一直是云里雾里. 于是使用什么样的工具才内网才能畅通无阻,成了大家一直以来的渴求. 今天小菜我本着所有师傅们无私分享的精 ...
- python语法_if判断
age_of_princal = 56 guess_age = int(input("e guess a age:")) if guess_age == age_of_princa ...