是否支持把没有目标的空背景和标签输入训练？
wwzh2015 opened this issue · 2 comments
wwzh2015 commented
这样可以提高错检率是嘛？让模型更稳定
AIWintermuteAI commented
Please use the template.
And while I do speak and read Mandarin Chinese, my main working language is English.
Kindly re-create the issue and fill in the issue template in English.
wwzh2015 commented
OK，If these empty negative sample be trained that is no target of image and just a background image, that relevant xml also no target element.
The aXeleRate network have supported these empty negative sample that can be trained?
The work can improve AP or PR?