![](https://img-blog.csdnimg.cn/20201014180756919.png?x-oss-process=image/resize,m_fixed,h_64,w_64)
目标识别
Legolas~
这个作者很懒,什么都没留下…
展开
-
目标识别网络Faster RCNN:Pytorch源码分析(二)
锚框(anchors)产生: 感觉论文这块内容说的不太细致,只能深挖源码了~ from __future__ import print_function # -------------------------------------------------------- # Faster R-CNN # Copyright (c) 2015 Microsoft # Licensed under The MIT License [see LICENSE for details] # Written by Ro原创 2020-11-21 21:50:00 · 173 阅读 · 0 评论 -
目标识别网络Faster-RCNN:Pytorch源码分析(一)
Faster-RCNN base & Faster-RCNN top (除去RPN部分) : Github源码如下(vgg16.py): # -------------------------------------------------------- # Tensorflow Faster R-CNN # Licensed under The MIT License [see LICENSE for details] # Written by Xinlei Chen # ------------原创 2020-11-21 11:20:28 · 401 阅读 · 0 评论 -
目标识别网络SSD:Pytorch源码分析(二)
1.先验框生成 Github源码: from __future__ import division from math import sqrt as sqrt from itertools import product as product import torch class PriorBox(object): """Compute priorbox coordinates in center-offset form for each source feature map. ""原创 2020-11-20 10:25:44 · 272 阅读 · 0 评论 -
目标识别网络SSD:Pytorch源码分析(一)
1.IOU计算: 先验框表示方式变换: (cx, cy, w, h) to (xmin, ymin, xmax, ymax): def point_form(boxes): """ Convert prior_boxes to (xmin, ymin, xmax, ymax) representation for comparison to point form ground truth data. Args: boxes: (tensor) center-size原创 2020-11-18 13:38:10 · 246 阅读 · 0 评论