dcase_models.util.SEDCallback¶

class dcase_models.util.SEDCallback(data, file_weights=None, best_F1=0, early_stopping=0, considered_improvement=0.01, sequence_time_sec=0.5, metric_resolution_sec=1.0, label_list=[])[source]¶

Bases: keras.callbacks.Callback

Keras callback to calculate F1 and ER after each epoch and save file with the weights if the evaluation improves.

Use sed_eval library.

__init__(data, file_weights=None, best_F1=0, early_stopping=0, considered_improvement=0.01, sequence_time_sec=0.5, metric_resolution_sec=1.0, label_list=[])[source]¶

Initialize the keras callback

Parameters:	data : tuple or KerasDataGenerator Validation data for model evaluation (X_val, Y_val) or KerasDataGenerator file_weights : string Path to the file with the weights best_acc : float Last accuracy value, only if continue early_stopping : int Number of epochs for cut the training if not improves if 0, do not use it

Methods

`__init__`(data[, file_weights, best_F1, …])	Initialize the keras callback
`on_batch_begin`(batch[, logs])	A backwards compatibility alias for on_train_batch_begin.
`on_batch_end`(batch[, logs])	A backwards compatibility alias for on_train_batch_end.
`on_epoch_begin`(epoch[, logs])	Called at the start of an epoch.
`on_epoch_end`(epoch[, logs])	This function is run when each epoch ends.
`on_predict_batch_begin`(batch[, logs])	Called at the beginning of a batch in predict methods.
`on_predict_batch_end`(batch[, logs])	Called at the end of a batch in predict methods.
`on_predict_begin`([logs])	Called at the beginning of prediction.
`on_predict_end`([logs])	Called at the end of prediction.
`on_test_batch_begin`(batch[, logs])	Called at the beginning of a batch in evaluate methods.
`on_test_batch_end`(batch[, logs])	Called at the end of a batch in evaluate methods.
`on_test_begin`([logs])	Called at the beginning of evaluation or validation.
`on_test_end`([logs])	Called at the end of evaluation or validation.
`on_train_batch_begin`(batch[, logs])	Called at the beginning of a training batch in fit methods.
`on_train_batch_end`(batch[, logs])	Called at the end of a training batch in fit methods.
`on_train_begin`([logs])	Called at the beginning of training.
`on_train_end`([logs])	Called at the end of training.
`set_model`(model)
`set_params`(params)

on_batch_begin(batch, logs=None)¶: A backwards compatibility alias for on_train_batch_begin.

on_batch_end(batch, logs=None)¶: A backwards compatibility alias for on_train_batch_end.

on_epoch_begin(epoch, logs=None)¶

Called at the start of an epoch.

Subclasses should override for any actions to run. This function should only be called during train mode.

# Arguments: epoch: integer, index of epoch. logs: dict, currently no data is passed to this argument for this method

but that may change in the future.

on_epoch_end(epoch, logs={})[source]¶

This function is run when each epoch ends. The metrics are calculated, printed and saved to the log file.

Parameters:	epoch : int number of epoch (from Callback class) logs : dict log data (from Callback class)

on_predict_batch_begin(batch, logs=None)¶

Called at the beginning of a batch in predict methods.