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

How to get same output using MNN with model converted from CAFFE #3

Open
peyer opened this issue Aug 27, 2019 · 2 comments
Open

How to get same output using MNN with model converted from CAFFE #3

peyer opened this issue Aug 27, 2019 · 2 comments

Comments

@peyer
Copy link

peyer commented Aug 27, 2019

@liushuan I have successufully run your provided code and got proper face region on some images.
However, I still do not got the same output between MNN and CAFFE with the same model.
If I had a input file(just been decoded by opencv, and have been substracted by mean value and normed, in NCHW layout ), how to send this input file to MNN to get same output ?

@jayle19930918
Copy link

@liushuan I have successufully run your provided code and got proper face region on some images.
However, I still do not got the same output between MNN and CAFFE with the same model.
If I had a input file(just been decoded by opencv, and have been substracted by mean value and normed, in NCHW layout ), how to send this input file to MNN to get same output ?

Hello, I encountered the same problem, have you solved it?

@peyer
Copy link
Author

peyer commented Aug 30, 2019

@jayle19930918 Not yet. I try to compare the first layer(Convolution) output between Caffe and MNN, while MNN has transformed the output that I could not make sure that whether it was the true output or not.

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

2 participants