multiml.task.keras.keras_util module

multiml.task.keras.keras_util.compile(obj, obj_args, modules)

multiml.task.keras.keras_util.training_keras_model(model, num_epochs, batch_size, max_patience, x_train, y_train, x_valid, y_valid, chpt_path=None, callbacks=['EarlyStopping', 'ModelCheckpoint', 'TensorBoard'], tensorboard_path=None, verbose=None)

Training keras model.

Parameters:

• num_epochs (int) – maximum number of epochs

• batch_size (int) – mini-batch size

• max_patience (int) – maximum patience for early stopping

• x_train (np.darray) – input array for training

• y_train (np.darray) – output array for training

• x_valid (np.darray) – input array for validation

• y_valid (np.darray) – output array for validation

• chpt_path (str) – path for Keras check-point saving. If None, temporary directory will be used.

• callbacks (str or keras.Callback) – callback for keras model training. Predefined callbacks (EarlyStopping, ModelCheckpoint, and TensorBoard) can be selected by str. Other user-defined callbacks should be given as keras.Callback object.

• tensorboard_path (str) – Path for tensorboard callbacks. If None, tensorboard callback is not used.

• verbose (int) – verbose option for Model.fit(). If None, it’s set based on logger.MIN_LEVEL

Returns:

training results, which contains loss histories.

Return type:

dict

multiml.task.keras.keras_util.get_optimizer(optimizer, optimizer_args=None)

Get Keras optimizer.

Parameters:

• optimizer (str or obj) – If str, the corresponding optimizer is searched for in the keras class.

• learning_rate (float) – learning rate for the optimizer