0

I have been training several models using 10-fold CV and added the ModelCheckpoint callback which saves the model with the lowest validation loss to an HDF5 file. However, for a while I would then call model.save(filepath) right after training.

I only came to the realization that the last call would probably save the model trained on the very last epoch and that the saved checkpoint is not being used at all. Is my assumption correct? If so, is it normal that the best models from the checkpoint files score lower than the ones saved with model.save()?

Noam Suissa
  • 378
  • 2
  • 17
  • 1
    The `model.save` only just save the mode, regardless of the best model or not. Check this [question/answer](https://stackoverflow.com/questions/67741387/reload-best-weights-from-tensorflow-keras-checkpoints/67744905#67744905). And relevant official [doc](https://www.tensorflow.org/guide/keras/save_and_serialize). – M.Innat Jun 02 '22 at 16:00

0 Answers0