Menu
Is it possible to use custom metrics in the ModelCheckpoint callback?
857
ModelCheckpoint callback is used in conjunction with training using model. fit() 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.
Using Callbacks in KerasCallbacks can be provided to the fit() function via the “callbacks” argument. First, callbacks must be instantiated. Then, one or more callbacks that you intend to use must be added to a Python list. Finally, the list of callbacks is provided to the callback argument when fitting the model.
Yes, it is possible.
Define the custom metrics as described in the documentation:
import keras.backend as K def mean_pred(y_true, y_pred): return K.mean(y_pred) model.compile(optimizer='rmsprop', loss='binary_crossentropy', metrics=['accuracy', mean_pred]) To check all available metrics:
print(model.metrics_names) > ['loss', 'acc', 'mean_pred'] Pass the metric name to ModelCheckpoint through monitor. If you want the metric calculated in the validation, use the val_ prefix.
ModelCheckpoint(weights.{epoch:02d}-{val_mean_pred:.2f}.hdf5, monitor='val_mean_pred', save_best_only=True, save_weights_only=True, mode='max', period=1) Don't use mode='auto' for custom metrics. Understand why here.
Why am I answering my own question? Check this.
135
If you love us? You can donate to us via Paypal or buy me a coffee so we can maintain and grow! Thank you!
Donate Us With