From 4d9ee930a1c43c370d2733ec44951793e0e8b9bd Mon Sep 17 00:00:00 2001 From: Cezary Pukownik Date: Sun, 27 Oct 2019 14:34:02 +0100 Subject: [PATCH] code clarity --- project/extract.py | 106 +++++++++++++++++++--------------- project/generate.py | 20 +++++-- project/midi_processing.py | 4 +- project/model.py | 1 - project/train.py | 113 +++++++++++++++++++++---------------- 5 files changed, 141 insertions(+), 103 deletions(-) diff --git a/project/extract.py b/project/extract.py index 55c0e26..c98d112 100644 --- a/project/extract.py +++ b/project/extract.py @@ -5,54 +5,70 @@ import pickle from midi_processing import extract_data, analyze_data -parser = argparse.ArgumentParser() -parser.add_argument('midi_pack', help='folder name for midi pack in midi_packs folder', type=str) -parser.add_argument('name', help='name for experiment', type=str) -parser.add_argument('--b', help='lengh of sequence in bars', type=int) -parser.add_argument('-a', help='analize data', action='store_true') -args = parser.parse_args() +def make_folder_if_not_exist(path): + try: + os.mkdir(path) + except: + pass -'''SETTINGS''' -MIDI_PACK_NAME = args.midi_pack -EXPERIMENT_NAME = args.name -BARS_IN_SEQ = args.b +def parse_argv(): + parser = argparse.ArgumentParser() + parser.add_argument('midi_pack', help='folder name for midi pack in midi_packs folder', type=str) + parser.add_argument('--n', help='name for experiment', type=str) + parser.add_argument('--b', help='lengh of sequence in bars', type=int) + parser.add_argument('-a', help='analize data', action='store_true') + args = parser.parse_args() + return args -midi_folder_path = os.path.join('midi_packs', MIDI_PACK_NAME) +def ask_for_workflow(): + '''MODEL WORKFLOW DIALOG''' + number_of_instruments = int(input('Please specify number of instruments\n')) + model_workflow = dict() + for i in range(number_of_instruments): + input_string = input('Please specify a workflow step [] {m : melody, a : arrangment}\n') + tokens = input_string.split() + if tokens[-1] == 'm': + model_workflow[i] = (tokens[0], 'melody') + elif tokens[-1] == 'a': + model_workflow[i] = ((tokens[1], tokens[0]), 'arrangment') + else: + raise ValueError("The step definitiom must end with {'m', 'a'}"); + + make_folder_if_not_exist(os.path.join('training_sets', EXPERIMENT_NAME)) + pickle.dump(model_workflow, open(os.path.join('training_sets', EXPERIMENT_NAME, 'workflow.pkl'),'wb')) + + return model_workflow -# analyze data set for intresting intruments -if args.a: - analyze_data(midi_folder_path) - sys.exit() +def extract_from_folder(model_workflow): + for key, (instrument, how) in model_workflow.items(): + if how == 'melody': + instrument_name = instrument + else: + instrument_name = instrument[1] + + make_folder_if_not_exist(os.path.join('training_sets', EXPERIMENT_NAME)) + save_path = os.path.join('training_sets', EXPERIMENT_NAME, instrument_name.lower() + '_data.pkl') + + x_train, y_train, program = extract_data(midi_folder_path=os.path.join('midi_packs', MIDI_PACK_NAME), + how=how, + instrument=instrument, + bar_in_seq=BARS_IN_SEQ) + + pickle.dump((x_train, y_train, program), open(save_path,'wb')) +if __name__ == '__main__': + args = parse_argv() -'''MODEL WORKFLOW DIALOG''' -number_of_instruments = int(input('Please specify number of instruments\n')) -model_workflow = dict() -input_list = [] -for i in range(number_of_instruments): - input_string = input('Please specify a workflow step\n') - tokens = input_string.split() - if tokens[-1] == 'melody': - model_workflow[i] = (tokens[0], tokens[1]) + MIDI_PACK_NAME = args.midi_pack + EXPERIMENT_NAME = args.n + BARS_IN_SEQ = args.b + if not EXPERIMENT_NAME: + EXPERIMENT_NAME = MIDI_PACK_NAME + if not BARS_IN_SEQ: + BARS_IN_SEQ = 4 + ANALIZE = args.a + + if ANALIZE: + analyze_data(os.path.join('midi_packs', MIDI_PACK_NAME)) else: - model_workflow[i] = ((tokens[1], tokens[0]), tokens[2]) - -# make folder for new experiment if no exist -try: - os.mkdir(os.path.join('training_sets', EXPERIMENT_NAME)) -except: - pass - -# extract process -for key, (instrument, how) in model_workflow.items(): - if how == 'melody': - instrument_name = instrument - else: - instrument_name = instrument[1] - - save_path = os.path.join('training_sets', EXPERIMENT_NAME, instrument_name.lower() + '_data.pkl') - x_train, y_train, program = extract_data(midi_folder_path=midi_folder_path, how=how, - instrument=instrument, bar_in_seq=BARS_IN_SEQ) - pickle.dump((x_train, y_train, program), open(save_path,'wb')) - -pickle.dump(model_workflow, open(os.path.join('training_sets', EXPERIMENT_NAME, 'workflow.pkl'),'wb')) \ No newline at end of file + extract_from_folder(ask_for_workflow()) \ No newline at end of file diff --git a/project/generate.py b/project/generate.py index fabdc0a..ddbb19e 100644 --- a/project/generate.py +++ b/project/generate.py @@ -7,19 +7,27 @@ import pickle parser = argparse.ArgumentParser() parser.add_argument('n', help='name for experiment', type=str) +parser.add_argument('s', help='session name', type=str) parser.add_argument('--i', help='number of midis to generate', type=int) parser.add_argument('--l', help='latent_dim_of_model', type=int) parser.add_argument('--m', help="mode {'from_seq', 'from_state}'", type=str) args = parser.parse_args() EXPERIMENT_NAME = args.n +SESSION_NAME = args.s GENERETIONS_COUNT = args.i LATENT_DIM = args.l MODE = args.m -if GENERETIONS_COUNT == None: +if not GENERETIONS_COUNT: GENERETIONS_COUNT = 1 +if not LATENT_DIM: + LATENT_DIM = 256 + +if not MODE: + MODE = 'from_seq' + model_workflow = pickle.load(open(os.path.join('training_sets', EXPERIMENT_NAME, 'workflow.pkl'),'rb')) band = dict() @@ -45,7 +53,7 @@ for instrument in tqdm(band): band[instrument][0] = model band[instrument][1] = program -for midi_counter in range(GENERETIONS_COUNT): +for midi_counter in tqdm(range(GENERETIONS_COUNT)): ''' MAKE MULTIINSTRUMENTAL MUSIC !!!''' notes = dict() @@ -76,7 +84,11 @@ for midi_counter in range(GENERETIONS_COUNT): os.mkdir(os.path.join('generated_music', EXPERIMENT_NAME)) except: pass + try: + os.mkdir(os.path.join('generated_music', EXPERIMENT_NAME, SESSION_NAME)) + except: + pass - save_path = os.path.join('generated_music', EXPERIMENT_NAME, f'{EXPERIMENT_NAME}_{midi_counter}_{MODE}_{LATENT_DIM}.mid') + save_path = os.path.join('generated_music', EXPERIMENT_NAME, SESSION_NAME, f'{EXPERIMENT_NAME}_{midi_counter}_{MODE}_{LATENT_DIM}.mid') generated_midi.save(save_path) - print(f'Generated succefuly to {save_path}') + # print(f'Generated succefuly to {save_path}') diff --git a/project/midi_processing.py b/project/midi_processing.py index 0d00780..3110f74 100644 --- a/project/midi_processing.py +++ b/project/midi_processing.py @@ -10,8 +10,6 @@ from random import randint import pretty_midi as pm from tqdm import tqdm - - # TODO: Stream class is no logner needed <- remore from code and make just SingleTrack.notes instead on SingleTrack.stream.notes class Stream(): @@ -486,7 +484,7 @@ def round_to_sixteenth_note(x, base=0.25): ''' return base * round(x/base) - + def parse_pretty_midi_instrument(instrument, resolution, time_to_tick, key_offset): ''' arguments: a prettyMidi instrument object return: a custom SingleTrack object diff --git a/project/model.py b/project/model.py index 1a2c77e..677c0fe 100644 --- a/project/model.py +++ b/project/model.py @@ -52,7 +52,6 @@ class Seq2SeqTransformer(): self.x_vocab_size = len(self.x_vocab) self.y_vocab_size = len(self.y_vocab) - self.x_transform_dict = dict( [(char, i) for i, char in enumerate(self.x_vocab)]) self.y_transform_dict = dict( diff --git a/project/train.py b/project/train.py index 9160132..44c0529 100644 --- a/project/train.py +++ b/project/train.py @@ -3,64 +3,77 @@ import sys import pickle import keras import argparse +import warnings from model import Seq2SeqModel +from extract import make_folder_if_not_exist -parser = argparse.ArgumentParser() -parser.add_argument('n', help='name for experiment', type=str) -parser.add_argument('--b', help='batch_size', type=int) -parser.add_argument('--l', help='latent_dim', type=int) -parser.add_argument('--e', help='epochs', type=int) -parser.add_argument('--r', help='reset, use when you want to reset waights and train from scratch', action='store_true') -parser.add_argument('--i', help='refrance to instrument to train, if you want to train only one instument') -args = parser.parse_args() +# TODO: +# FIXME: +def parse_argv(): + parser = argparse.ArgumentParser() + parser.add_argument('n', help='name for experiment', type=str) + parser.add_argument('--b', help='batch_size', type=int) + parser.add_argument('--l', help='latent_dim', type=int) + parser.add_argument('--e', help='epochs', type=int) + parser.add_argument('--i', help='refrance to instrument to train, if you want to train only one instument') + parser.add_argument('-r', help='reset, use when you want to reset waights and train from scratch', action='store_true') + args = parser.parse_args() + return args -'''HYPER PARAMETERS''' -EXPERIMENT_NAME = args.n -BATCH_SIZE = args.b -LATENT_DIM = args.l -EPOCHS = args.e -RESET = args.r -INSTRUMENT = args.i +def load_workflow(): + workflow_path = os.path.join('training_sets', EXPERIMENT_NAME, 'workflow.pkl') + if os.path.isfile(workflow_path): + model_workflow = pickle.load(open(workflow_path,'rb')) + else: + raise FileNotFoundError(f'There is no workflow.pkl file in trainig_sets/{EXPERIMENT_NAME}/ folder') + return model_workflow -if BATCH_SIZE == None: - BATCH_SIZE = 32 -if LATENT_DIM == None: - LATENT_DIM = 256 -if EPOCHS == None: - EPOCHS = 1 -if RESET == None: - RESET = False +def train_models(model_workflow): + + instruments = [instrument if how == 'melody' else instrument[1] for key, (instrument, how) in model_workflow.items()] + # make_folder_if_not_exist(os.mkdir(os.path.join('models',EXPERIMENT_NAME))) + + found = False + for instrument in instruments: -## TODO: raise error if file not found -model_workflow = pickle.load(open(os.path.join('training_sets', EXPERIMENT_NAME, 'workflow.pkl'),'rb')) -tbCallBack = keras.callbacks.TensorBoard(log_dir='./Graph', histogram_freq=0, write_graph=True, write_images=True) + if INSTRUMENT == None or INSTRUMENT == instrument: + data_path = os.path.join('training_sets', EXPERIMENT_NAME, instrument.lower() + '_data.pkl') + model_path = os.path.join('models', EXPERIMENT_NAME, f'{instrument.lower()}_model.h5') -instruments = [instrument if how == 'melody' else instrument[1] for key, (instrument, how) in model_workflow.items()] + x_train, y_train, _ = pickle.load(open(data_path,'rb')) + model = Seq2SeqModel(LATENT_DIM, x_train, y_train) + if os.path.isfile(model_path) and not RESET: + model.load(model_path) -# make folder for new experiment -try: - os.mkdir(os.path.join('models',EXPERIMENT_NAME)) -except: - pass + print(f'Training: {instrument}') + model.fit(BATCH_SIZE, EPOCHS, callbacks=[]) + model.save(model_path) + found = True -# init models -found = False -for instrument in instruments: + if not found: + raise ValueError(f'Instrument not found. Use one of the {instruments}') + +if __name__ == '__main__': - if INSTRUMENT == None or INSTRUMENT == instrument: - data_path = os.path.join('training_sets', EXPERIMENT_NAME, instrument.lower() + '_data.pkl') - model_path = os.path.join('models', EXPERIMENT_NAME, f'{instrument.lower()}_model.h5') + warnings.filterwarnings("ignore") + args = parse_argv() + + EXPERIMENT_NAME = args.n + BATCH_SIZE = args.b + LATENT_DIM = args.l + EPOCHS = args.e + RESET = args.r + INSTRUMENT = args.i - x_train, y_train, _ = pickle.load(open(data_path,'rb')) - model = Seq2SeqModel(LATENT_DIM, x_train, y_train) - if os.path.isfile(model_path) and not RESET: - model.load(model_path) - - print(f'Training: {instrument}') - train_history = model.fit(BATCH_SIZE, EPOCHS, callbacks=[tbCallBack]) - model.save(model_path) - found = True - -if not found: - raise ValueError(f'Instrument not found. Use one of the {instruments}') \ No newline at end of file + # default settings if not args passed + if not BATCH_SIZE: + BATCH_SIZE = 32 + if not LATENT_DIM: + LATENT_DIM = 256 + if not EPOCHS: + EPOCHS = 1 + if not RESET: + RESET = False + + train_models(load_workflow()) \ No newline at end of file