CheckPoint option

[QuandoSJ]

Is there a option for me to save checkpoint while training and then continue training from the checkpoint. Cause right now I cannot start from where I stopped but to start over again

[magloiretouh]

The model is saved at the end of each epoch if the total loss is less than the previous epoch total loss. This is done using a ModelCheckpoint callback. So to resume where you left off, you just have to use the load option the next time you want to initialize your training