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 use pretrained model from TF #9

Open
cygerts opened this issue May 22, 2018 · 1 comment
Open

How to use pretrained model from TF #9

cygerts opened this issue May 22, 2018 · 1 comment

Comments

@cygerts
Copy link

cygerts commented May 22, 2018

Hi,
how can I use pretrained TF model (on KITTI dataset) from original repo:
https://github.com/BichenWuUCB/squeezeDet ?
It is stored as binary file there, whereas we need hdf5 file.

Or perhaps you can provide your fine-tuned model on KITTI dataset? (Unfortunately no GPU here no train myself).

@Sileadim
Copy link
Contributor

If you want to convert the original checkpoint, check out this. keras-team/keras#8026
I have not a properly trained model on KITTI, just for testing the implementation. Although, I just pushed a model that was trained for around 250 epochs and you can use that as a starting point.

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