to be run on step_end model_outputs.append(current_model_part) current_model_part = next_model_part next_model_part

From all the inputs == dimensions of the bayesian optimization, it creates a model, train it, add return its negative accuracy (skopt

:param path: :return:

For the file generate.py :param args: :return:

:param input: :return: The "usefull" outputs of the neural network == List(nb_instruments)[instrument_output]

Same as predict but without messing output :param x: :param args: :param kwargs: :return:

Same as predict but without messing output :param x: :param args: :param kwargs: :return:

:param max_length: :param no_duration: :param verbose: :return:

Generate Midi file from the seed and the trained model :param nb_seeds: number of seeds for the generation :param length: Len

Generate Midi file from the seed and the trained model :param nb_seeds: number of seeds for the generation :param length: Len

:param song_number: :param in_batch_format: :param with_mask: :return:

:param n: the number of color to return :return: a list of colors with a length of n

:param replicate: :param music: :return:

:param replicate: :param music: :return:

:param args: :return:

:param name: :param pc: :param transposed: :param mono: :return:

:param name: The name of the future saved folder :type id: The id of an existing folder :return: the path to the folder to save the resu

:param history: :return: The total validation accuracy

:return: set up a new unique full name and the corresponding path to save the trained model

:param test: :param kwargs: :return:

:param t: :param ax: :return:

:param with_last_tensor: :param song_number: :param step_number: :param with_mask: :return:

:param song_number: :param step_number: :return: The input and output for the step of this

Get the scalar data from the tensorboard files :param path: path of the tensorboard folder :return: dict( train=dict(

:param my_sequence: :param validation_split: :return:

:param key: key in the dictionary "model_infos" :return: the value in model_infos or None if it doesn't exist

:param args: :param l_semitone: :param l_tone: :param l_tritone: :param kwargs: :return:

:param array: (instruments, size, length, channels) :param l1: :param l2: :param l6: :return: (length,)

:param args: :return:

:param sum_axis: axis to sum, if None, there is no sum :param mean: :param std: :return:

:return: load the data

:param id: id of the model to load :return: load the weights of a model

mean squarred error :param y_true: :param y_pred: :return:

:param use_binary: :param mono: :param matrix: shape (nb_instruments, 128, nb_steps, 2) :param instruments: The instruments, :pa

convert Midi file to matrix for DL architecture. :param transpose: :param notes_range: :param filename: path to the Midi file :pa

convert Midi file to matrix for DL architecture. :param notes_range: :param transpose: :param filename: path to the Midi file :pa

:param midinote: :param notes_range: :return:

Add the scale and rhythm reward/cost :param take_all_steps_rhythm: :param l_scale: :param l_rhythm: :param args: :param kwarg

:param args: :return:

:return: Number of all the parameters