You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
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).
The text was updated successfully, but these errors were encountered:
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.
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).
The text was updated successfully, but these errors were encountered: