ModelCheckpoint callback is used with training the model to save a model or weights in a checkpoint file at some interval, so the model or weights can be loaded later to continue the training from the state saved or to use for deployment.
Classes, function, and attributes:
keras.callbacks.ModelCheckpoint: ModelCheckpoint class from keras callbacks apifilepath: path to save the model filemonitor: the metric name to monitorsave_best_only: only save when the model is considered the best according to the metric provided inmonitormodel: overwrite the save file based on either maximum or the minimum scores according the metric provided inmonitor
Add notes from the video (PRs are welcome)
- checkpointing saves the model after each training iteration
- checkpoint conditions may include reaching the best performance
- keras callbacks
|
The notes are written by the community. If you see an error here, please create a PR with a fix. |