Skip to content
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

Open
07hyx06 opened this issue Sep 27, 2019 · 7 comments

Comments

@07hyx06
Copy link

07hyx06 commented Sep 27, 2019

No description provided.

@2017TJM
Copy link

2017TJM commented Oct 22, 2019

S那里是不是就有问题

@2017TJM
Copy link

2017TJM commented Oct 22, 2019

作者复现时进行了改进感觉是把特征图尺寸设置为14x14

@rox38431
Copy link

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,
我想會這麼做應該是因為作者提高了輸入的尺寸(448x448),使得 resnet50 的輸出會變成 14x14x30。

@freemedom
Copy link

最后边改了,用的是卷积层而不是全连接层

@Vandaci
Copy link

Vandaci commented Jul 20, 2022

我说,看了半天,注释跟代码没对应上

@yitianad
Copy link

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

@ZXTFINAL
Copy link

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
Labels
None yet
Projects
None yet
Development

No branches or pull requests

7 participants