-
Notifications
You must be signed in to change notification settings - Fork 229
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
调用evaluation脚本时每次准确率结果会有细微的差别 #104
Comments
可以将除改变图像大小的增强全部取消,readme顶部我有提及 |
我看你截图怎么感觉没有用对权重啊,全都不匹配,记得修改对应配置文件调用权重 |
关于评估时每次有细微差别,因为图片与模型规定的输入尺寸不一致,使用的随机裁剪结果次次可能不同,从而导致了这个问题,在我理解来看数据量越少越明显,可以尝试的一个解决方法是预先将图片通过补边再等比缩放的方式处理成所要求的大小,这样可保证每次推理的数据一致 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
调用evaluation脚本时每次准确率结果会有较大的差别,如下图所示,会出现这样子提示:The model and loaded state dict do not match exactly,帮忙看下是什么原因,模型是swin-transformer-v2-tiny
The text was updated successfully, but these errors were encountered: