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

关于模型转换和模型输入大小的几个问题 #4

Open
ShaofengZou opened this issue Jul 22, 2019 · 0 comments
Open

关于模型转换和模型输入大小的几个问题 #4

ShaofengZou opened this issue Jul 22, 2019 · 0 comments

Comments

@ShaofengZou
Copy link

您好, 有几个小问题想请教您一下:
1, eval.py和Create_pb_file_4Android.py都能生成对应的pb文件,这两者生成的pb文件有什么不同呢?
2,模型训练时的输入图像大小被rescale到了256256,测试的时候输入大小可以是任意值,输出对应的大小。我看了安卓的工程里,图像被rescale到256256作为网络的输入,在这里为什么要rescale呢?我尝试了下其他的大小比如512*512,app就会闪退了,想请教下这是什么原因呢?
期待您的回复~

Hello, there are a few questions I would like to ask you:
1, Both eval.py and Create_pb_file_4Android.py can generate the corresponding pb file. And what is the difference between the two generated pb files?
2. The input image size during model training is rescaled to 256256. When testing, the input size can be any value and the output size is corresponding to the input size. I have read the Android project, and the image was rescaled to 256256 as the input of the network. Why should the image size have to be rescaled here? I tried other sizes such as 512*512, and the app will flash back. Would you like to ask what is the reason?
Looking forward to your reply~
Best wishes.

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

1 participant