-
Notifications
You must be signed in to change notification settings - Fork 245
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
你的resnet50作为backbone时,输入(3,448,448)的图片,输出维度不是(7,7,30)! #29
Comments
S那里是不是就有问题 |
作者复现时进行了改进感觉是把特征图尺寸设置为14x14 |
的確,雖然作者在註解部分都寫 grid size 為 7x7x30,但實際上程式的寫法都是 14x14x30, |
最后边改了,用的是卷积层而不是全连接层 |
我说,看了半天,注释跟代码没对应上 |
Resnet原论文的输入是224224,对应输出77,因此448输出是14*14的feature map |
准确地来说不是有问题,是这个代码是预训练代码,应该还要有一个微调部分,预训练输入是224,微调才是448 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
No description provided.
The text was updated successfully, but these errors were encountered: