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

Custom-defined trainer (load model) #29

Open
pavelxx1 opened this issue May 13, 2023 · 1 comment
Open

Custom-defined trainer (load model) #29

pavelxx1 opened this issue May 13, 2023 · 1 comment
Labels
question Further information is requested

Comments

@pavelxx1
Copy link

Hi, I use Custom-defined trainer
how to corectly load_model via Keras? Thx

@pavelxx1 pavelxx1 added the question Further information is requested label May 13, 2023
@LongxingTan
Copy link
Owner

@pavelxx1
Hey Pavel,

I guess, you have trained and save a trained model via keras, and you want to load the saved weights for inference?
Can't you use keras load_weights?

model.load_weights("weights.h5",  by_name=True,  skip_mismatch=True)

Or you can copy you demo code here?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
question Further information is requested
Projects
None yet
Development

No branches or pull requests

2 participants