-
-
Notifications
You must be signed in to change notification settings - Fork 1k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
reid部署时模型输出的疑问 #381
Comments
你好。感谢
|
好的,谢谢,解决了我的疑问 |
1.你好,作者,有一个想法不知道可不可行,用reid的方法去训练大类(比如车辆大类,卡车、轿车、公家车、SUV等,而不是每个车单独一类),同样使用metric loss和id loss,最后部署的时候保留liner和cls分类头,用分类头去对图像分类,这种reid方式训练能否提升单独使用分类头去训练分类的效果呢, |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
刚刚接触reid,关于reid部署时的一些疑问,希望作者或者各位大佬能够帮忙回答,感谢!
1.训练的时候metric loss和id loss中间有conv+bn层,metric lossloss输入的特征去算特征的距离,比如余弦距离,id loss输入的特征去算交叉熵损失这些。
2.模型评价或者部署的时候,输出的特征变为了id loss的输入特征,为何不直接使用metric loss的输入特征作为输出用于后续特征相似度计算?这样计算特征相似度不会产生偏差吗,毕竟训练时metric loss的输入是用作特征距离计算的。
The text was updated successfully, but these errors were encountered: