작성일: 2022.08.17 (Wed)
What is ModelCheckpoint func?
Checkpoint is the tensorflow that store the model being trained.
You can use it like the code below.
tf.keras.callbacks.ModelCheckpoint(
filepath, monitor='val_loss', verbose=0, save_best_only=False,
save_weights_only=False, mode='auto', save_freq='epoch', options=None, **kwargs
)
Python
복사
Usage of ModelCheckpoint()
What is ReduceLROnPlateau func?
ReduceLROnPlateau is the tensorflow that reduce learning rate if no progress on the validatoin set (or train, you can decide it).
You can use it like the code below.
tf.keras.callbacks.ReduceLROnPlateau(
monitor='val_loss', factor=0.1, patience=10, verbose=0, mode='auto',
min_delta=0.0001, cooldown=0, min_lr=0, **kwargs
)
Python
복사
Usage of ReduceLROnPlateau()
What is EarlyStopping func?
EarlyStopping is the tensorflow callback that early stop if no progress on the validation set (or tarin, you can decide it).
You can use it like the code below.
tf.keras.callbacks.EarlyStopping(
monitor='val_loss', min_delta=0, patience=0, verbose=0, mode='auto',
baseline=None, restore_best_weights=False
)
Python
복사
Usage of EarlyStopping()
For more detail parameters, visit to the reference website.
Reference
