赞
踩
在上一篇文章中:
《python基于轻量级CNN模型开发构建手写藏文数字识别系统》
开发实现了轻量级的藏文手写数字识别系统,这里主要是想基于前文的数据,整合目标检测模型来进一步挖掘藏文手写数字数据集的可玩性,基于yolov5n开发构建轻量级的藏文手写数字检测识别系统,首先来看效果图:
共仿真生成了3000的样本数据集,接下来简单看下:
YOLO格式标注文件如下所示:
实例标注内容如下:
VOC格式标注文件如下所示:
实例标注内容如下所示:
- <annotation>
- <folder>JiaGuWen</folder>
- <filename>JPEGImages/0a48304e-c797-4686-9c2a-09eeb029404d.jpg</filename>
- <source>
- <database>The JiaGuWen Database</database>
- <annotation>JiaGuWen</annotation>
- <image>JiaGuWen</image>
- </source>
- <owner>
- <name>CGB</name>
- </owner>
- <size>
- <width>640</width>
- <height>640</height>
- <depth>3</depth>
- </size>
- <segmented>0</segmented>
-
- <object>
- <name>0</name>
- <pose>Unspecified</pose>
- <truncated>0</truncated>
- <difficult>0</difficult>
- <bndbox>
- <xmin>590</xmin>
- <ymin>14</ymin>
- <xmax>618</xmax>
- <ymax>42</ymax>
- </bndbox>
- </object>
-
- <object>
- <name>7</name>
- <pose>Unspecified</pose>
- <truncated>0</truncated>
- <difficult>0</difficult>
- <bndbox>
- <xmin>392</xmin>
- <ymin>98</ymin>
- <xmax>448</xmax>
- <ymax>154</ymax>
- </bndbox>
- </object>
-
- <object>
- <name>1</name>
- <pose>Unspecified</pose>
- <truncated>0</truncated>
- <difficult>0</difficult>
- <bndbox>
- <xmin>145</xmin>
- <ymin>134</ymin>
- <xmax>187</xmax>
- <ymax>176</ymax>
- </bndbox>
- </object>
-
- <object>
- <name>1</name>
- <pose>Unspecified</pose>
- <truncated>0</truncated>
- <difficult>0</difficult>
- <bndbox>
- <xmin>380</xmin>
- <ymin>352</ymin>
- <xmax>408</xmax>
- <ymax>380</ymax>
- </bndbox>
- </object>
-
- </annotation>
模型文件如下:
- # YOLOv5 本文内容由网友自发贡献,转载请注明出处:https://www.wpsshop.cn/w/小蓝xlanll/article/detail/218672推荐阅读
相关标签
Copyright © 2003-2013 www.wpsshop.cn 版权所有,并保留所有权利。