本文主要是介绍一张图理解Faster—RCNN测试流程,希望对大家解决编程问题提供一定的参考价值,需要的开发者们随着小编来一起学习吧!
请教同学Faster—RCNN测试流程,他让我看一个Faster—RCNN模型文件(自己找哈):
看了后,自己画了一张图:
注:conv:卷积 relu:(rectified linear units)激活函数 fc:全连接 RPN:region proposal network
cls_prob:分类概率 bbox_pred:bounding box predit
...:代表 relu norm pool (为了美观不画)
如果你看过Faster—RCNN论文,一定会想起这张图:
Figure 2: Faster R-CNN is a single, unified network
for object detection. The RPN module serves as the
‘attention’ of this unified network.
不要问我为什么放倒了,和上面的图对应,有木有????(为了美观我把右下的箭头指向了右上!)
图上的单词我还用红笔标注了。
论文提到ZF共享的五个卷积层不就是左边conv1-conv5吗?
再看文章里这段:To generate region proposals, we slide a small network over the convolutional feature map output by the last shared convolutional layer. This small network takes as input an n * n spatial window of the input convolutional feature map. Each sliding window is mapped to a lower-dimensional feature (256-d for ZF and 512-d for VGG, with ReLU [33]following). This feature is fed into two sibling fully connected layers—a box-regression layer (reg) and a box-classification layer (cls).
last shared convolutional layer 不就是conv5吗?reg cls 不就对应 fc7后面的两个分支吗?
顿时思路清晰了,感觉自己棒棒哒。。。。。。
这篇关于一张图理解Faster—RCNN测试流程的文章就介绍到这儿,希望我们推荐的文章对编程师们有所帮助!