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

run binary error #28

Open
tonycui0401 opened this issue Jul 25, 2017 · 4 comments
Open

run binary error #28

tonycui0401 opened this issue Jul 25, 2017 · 4 comments

Comments

@tonycui0401
Copy link

Hi when I run binary, I have got the following error:

Reading model from ./dumped.nnet
Layers 221
Layer 0 InputLayer
Layer is empty, maybe it is not defined? Cannot define network.
Segmentation fault (core dumped)

could you please let me know what is the problem.

@pplonski
Copy link
Owner

Hi! Maybe there was some problem during network dump. Please check the dumped file if it looks ok. Which version of keras are you using?

@tonycui0401
Copy link
Author

Hi, I think it's heras 2, can I send you my network dump file to check and my hdf5 and model.json file, do you have an email address? Also if I run binary file successfully, how can I do a prediction in C++, I want to read a input image file and predict it in C++

@pplonski
Copy link
Owner

there are problems with keras 2. Please try to train your network in keras 1.2.2 and it should work.

@tonycui0401
Copy link
Author

hi I installed keras 1.2.2, but still the same error, also after this error? How can I write a predict function to predict images based on my model in c++

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