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.

Sign up for GitHub

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

Jump to bottom

tensorflow2ncnn cannot convert batch_normalization layer #413

Closed
jjjjohnson opened this issue May 21, 2018 · 1 comment
Closed

tensorflow2ncnn cannot convert batch_normalization layer #413

jjjjohnson opened this issue May 21, 2018 · 1 comment
Labels
tensorflow do not like ncnn

Comments

@jjjjohnson
Copy link

Hello @nihui 大神,
我发现如果加上batch_normalization层，用转换工具tensorflow2ncnn转换模型不会报错，但是前向使用时输出是nan, 如果去掉batch_normalization，则输出正常。请问是否现在还没有支持tensorflow batch_normalization的转换？
以是有batch_normalization的ncnn.proto 文件：
screen shot 2018-05-21 at 5 25 08 pm
万分感激！
Junjie
@nihui
Copy link
Member

nihui commented Jun 10, 2018

generally, it is hard to convert tensorflow model to others. you'd better try caffe pytorch or mxnet ...
see #5

@nihui nihui closed this as completed Jun 10, 2018
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
tensorflow do not like ncnn
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@nihui @jjjjohnson