def main():
args = TrainData.parse_args(create_parser(usage))
inject_params(args.model)
save_params(args.model)
data = TrainData.from_both(args.db_file, args.db_folder, args.data_dir)
print('Data:', data)
(inputs, outputs), test_data = data.load(True, not args.no_validation)
print('Inputs shape:', inputs.shape)
print('Outputs shape:', outputs.shape)
if test_data:
print('Test inputs shape:', test_data[0].shape)
print('Test outputs shape:', test_data[1].shape)
if 0 in inputs.shape or 0 in outputs.shape:
print('Not enough data to train')
exit(1)
model = create_model(args.model, args.no_validation, args.extra_metrics)
model.summary()
from keras.callbacks import ModelCheckpoint
checkpoint = ModelCheckpoint(args.model, monitor=args.metric_monitor,
save_best_only=args.save_best)
try:
model.fit(inputs, outputs, 5000, args.epochs, validation_data=test_data,
callbacks=[checkpoint])
except KeyboardInterrupt:
print()
finally:
model.save(args.model)
def __init__(self, parser=None):
parser = parser or ArgumentParser()
add_to_parser(parser, self.usage, True)
args = TrainData.parse_args(parser)
self.args = args = self.process_args(args) or args
if args.invert_samples and not args.samples_file:
parser.error(
'You must specify --samples-file when using --invert-samples')
if args.samples_file and not isfile(args.samples_file):
parser.error('No such file: ' +
(args.invert_samples or args.samples_file))
if not 0.0 <= args.sensitivity <= 1.0:
parser.error('sensitivity must be between 0.0 and 1.0')
output_folder = os.path.join(args.folder, splitext(args.model)[0])
if not os.path.exists(output_folder):
print('Creating output folder:', output_folder)
os.makedirs(output_folder)
args.model = os.path.join(output_folder, args.model)
inject_params(args.model)
save_params(args.model)
self.train, self.test = self.load_data(self.args)
set_loss_bias(1.0 - args.sensitivity)
params = ModelParams(skip_acc=args.no_validation,
extra_metrics=args.extra_metrics)
self.model = create_model(args.model, params)
self.model.summary()
from keras.callbacks import ModelCheckpoint, TensorBoard
checkpoint = ModelCheckpoint(args.model,
monitor=args.metric_monitor,
save_best_only=args.save_best)
epoch_file = splitext(args.model)[0]
epoch_file = os.path.join(epoch_file + '.epoch')
epoch_fiti = Fitipy(epoch_file)
self.epoch = epoch_fiti.read().read(0, int)
def on_epoch_end(a, b):
self.epoch += 1
epoch_fiti.write().write(self.epoch, str)
self.model_base = splitext(self.args.model)[0]
if args.samples_file:
self.samples, self.hash_to_ind = self.load_sample_data(
args.samples_file, self.train)
else:
self.samples = set()
self.hash_to_ind = {}
self.callbacks = [
checkpoint,
TensorBoard(log_dir=self.model_base + '.logs', ),
LambdaCallback(on_epoch_end=on_epoch_end)
]
def __init__(self):
super().__init__(create_parser(usage))
for i in (join(self.args.folder, 'not-wake-word', 'generated'),
join(self.args.folder, 'test', 'not-wake-word',
'generated')):
makedirs(i, exist_ok=True)
self.trained_fns = load_trained_fns(self.args.model)
self.audio_buffer = np.zeros(pr.buffer_samples, dtype=float)
if not isfile(self.args.model):
params = ModelParams(skip_acc=self.args.no_validation,
extra_metrics=self.args.extra_metrics)
create_model(self.args.model, params).save(self.args.model)
self.listener = Listener(self.args.model,
self.args.chunk_size,
runner_cls=KerasRunner)
def __init__(self, args):
self.args = args
self.trained_fns = load_trained_fns(args.model)
pr = inject_params(args.model)
self.audio_buffer = np.zeros(pr.buffer_samples, dtype=float)
from keras.callbacks import ModelCheckpoint
self.checkpoint = ModelCheckpoint(args.model,
monitor=args.metric_monitor,
save_best_only=args.save_best)
data = TrainData.from_tags(args.tags_file, args.tags_folder)
self.tags_data = data.load(True, not args.no_validation)
if not isfile(args.model):
create_model(args.model, args.no_validation,
args.extra_metrics).save(args.model)
self.listener = Listener(args.model,
args.chunk_size,
runner_cls=KerasRunner)
def __init__(self, args):
super().__init__(args)
if args.invert_samples and not args.samples_file:
raise ValueError(
'You must specify --samples-file when using --invert-samples')
if args.samples_file and not isfile(args.samples_file):
raise ValueError('No such file: ' +
(args.invert_samples or args.samples_file))
if not 0.0 <= args.sensitivity <= 1.0:
raise ValueError('sensitivity must be between 0.0 and 1.0')
inject_params(args.model)
save_params(args.model)
params = ModelParams(skip_acc=args.no_validation,
extra_metrics=args.extra_metrics,
loss_bias=1.0 - args.sensitivity,
freeze_till=args.freeze_till)
self.model = create_model(args.model, params)
self.train, self.test = self.load_data(self.args)
from keras.callbacks import ModelCheckpoint, TensorBoard
checkpoint = ModelCheckpoint(args.model,
monitor=args.metric_monitor,
save_best_only=args.save_best)
epoch_fiti = Fitipy(splitext(args.model)[0] + '.epoch')
self.epoch = epoch_fiti.read().read(0, int)
def on_epoch_end(_a, _b):
self.epoch += 1
epoch_fiti.write().write(self.epoch, str)
self.model_base = splitext(self.args.model)[0]
if args.samples_file:
self.samples, self.hash_to_ind = self.load_sample_data(
args.samples_file, self.train)
else:
self.samples = set()
self.hash_to_ind = {}
self.callbacks = [
checkpoint,
TensorBoard(log_dir=self.model_base + '.logs', ),
LambdaCallback(on_epoch_end=on_epoch_end)
]
def __init__(self, args):
super().__init__(args)
for i in (
join(self.args.folder, 'not-wake-word', 'generated'),
join(self.args.folder, 'test', 'not-wake-word', 'generated')
):
makedirs(i, exist_ok=True)
self.trained_fns = load_trained_fns(self.args.model)
self.audio_buffer = np.zeros(pr.buffer_samples, dtype=float)
params = ModelParams(
skip_acc=self.args.no_validation, extra_metrics=self.args.extra_metrics,
loss_bias=1.0 - self.args.sensitivity
)
model = create_model(self.args.model, params)
self.listener = Listener(self.args.model, self.args.chunk_size, runner_cls=KerasRunner)
self.listener.runner = KerasRunner(self.args.model)
self.listener.runner.model = model
self.samples_since_train = 0
def __init__(self):
parser = create_parser(usage)
self.args = args = TrainData.parse_args(parser)
self.audio_buffer = np.zeros(pr.buffer_samples, dtype=float)
self.vals_buffer = np.zeros(pr.buffer_samples, dtype=float)
params = ModelParams(skip_acc=args.no_validation,
extra_metrics=args.extra_metrics,
loss_bias=1.0 - args.sensitivity)
self.model = create_model(args.model, params)
self.listener = Listener('',
args.chunk_size,
runner_cls=lambda x: None)
from keras.callbacks import ModelCheckpoint, TensorBoard
checkpoint = ModelCheckpoint(args.model,
monitor=args.metric_monitor,
save_best_only=args.save_best)
epoch_fiti = Fitipy(splitext(args.model)[0] + '.epoch')
self.epoch = epoch_fiti.read().read(0, int)
def on_epoch_end(a, b):
self.epoch += 1
epoch_fiti.write().write(self.epoch, str)
self.model_base = splitext(self.args.model)[0]
self.callbacks = [
checkpoint,
TensorBoard(log_dir=self.model_base + '.logs', ),
LambdaCallback(on_epoch_end=on_epoch_end)
]
self.data = TrainData.from_both(args.tags_file, args.tags_folder,
args.folder)
pos_files, neg_files = self.data.train_files
self.neg_files_it = iter(cycle(neg_files))
self.pos_files_it = iter(cycle(pos_files))
def run(self):
print('Writing to:', self.args.trials_name + '.bbopt.json')
for i in range(self.args.cycles):
self.bb.run(backend="random")
print("\n= %d = (example #%d)" %
(i + 1, len(self.bb.get_data()["examples"]) + 1))
params = ModelParams(recurrent_units=self.bb.randint("units",
1,
70,
guess=50),
dropout=self.bb.uniform("dropout",
0.1,
0.9,
guess=0.6),
extra_metrics=self.args.extra_metrics,
skip_acc=self.args.no_validation,
loss_bias=1.0 - self.args.sensitivity)
print('Testing with:', params)
model = create_model(self.args.model, params)
model.fit(*self.sampled_data,
batch_size=self.args.batch_size,
epochs=self.epoch + self.args.epochs,
validation_data=self.test *
(not self.args.no_validation),
callbacks=self.callbacks,
initial_epoch=self.epoch)
resp = model.evaluate(*self.test, batch_size=self.args.batch_size)
if not isinstance(resp, (list, tuple)):
resp = [resp, None]
test_loss, test_acc = resp
predictions = model.predict(self.test[0],
batch_size=self.args.batch_size)
num_false_positive = numpy.sum(predictions *
(1 - self.test[1]) > 0.5)
num_false_negative = numpy.sum(
(1 - predictions) * self.test[1] > 0.5)
false_positives = num_false_positive / numpy.sum(
self.test[1] < 0.5)
false_negatives = num_false_negative / numpy.sum(
self.test[1] > 0.5)
from math import exp
param_score = 1.0 / (1.0 + exp(
(model.count_params() - 11000) / 2000))
fitness = param_score * (1.0 - 0.2 * false_negatives -
0.8 * false_positives)
self.bb.remember({
"test loss": test_loss,
"test accuracy": test_acc,
"false positive%": false_positives,
"false negative%": false_negatives,
"fitness": fitness
})
print("False positive: ", false_positives * 100, "%")
self.bb.maximize(fitness)
pprint(self.bb.get_current_run())
best_example = self.bb.get_optimal_run()
print("\n= BEST = (example #%d)" %
self.bb.get_data()["examples"].index(best_example))
pprint(best_example)