def multiprocess_fit(blueprint):
disable_sysout()
from minos.model.build import ModelBuilder
model = ModelBuilder().build(blueprint, default_device())
model.fit_generator(generator=batch_iterator,
samples_per_epoch=batch_iterator.samples_per_epoch,
nb_epoch=10,
validation_data=test_batch_iterator,
nb_val_samples=test_batch_iterator.sample_count)
def test_early_stopping_condition_test(self):
disable_sysout()
with tempfile.TemporaryDirectory() as tmp_dir:
batch_size = 50
min_epoch = 10
max_epoch = 15
batch_iterator, test_batch_iterator, nb_classes = get_reuters_dataset(
batch_size, 1000)
layout = Layout(input_size=1000,
output_size=nb_classes,
output_activation='softmax')
training = Training(
objective=Objective('categorical_crossentropy'),
optimizer=Optimizer(optimizer='Adam'),
metric=Metric('categorical_accuracy'),
stopping=AccuracyDecreaseStoppingCondition(
metric='categorical_accuracy',
noprogress_count=2,
min_epoch=min_epoch,
max_epoch=max_epoch),
batch_size=batch_size)
experiment_parameters = ExperimentParameters(
use_default_values=True)
experiment_parameters.layout_parameter('rows', 1)
experiment_parameters.layout_parameter('blocks', 1)
experiment_parameters.layout_parameter('layers', 1)
experiment = Experiment('test__reuters_experiment',
layout,
training,
batch_iterator,
test_batch_iterator,
CpuEnvironment(n_jobs=1, data_dir=tmp_dir),
parameters=experiment_parameters)
_assert_valid_training_parameters(experiment)
blueprint = create_random_blueprint(experiment)
trainer = ModelTrainer(batch_iterator, test_batch_iterator)
model, history, _duration = trainer.train(blueprint,
cpu_device(),
save_best_model=False)
self.assertTrue(
len(history.epoch) >= min_epoch,
'Should have trained for at least min epoch')
self.assertTrue(
len(history.epoch) <= max_epoch,
'Should have trained for max epoch')
self.assertIsNotNone(model, 'should have fit the model')
score = model.evaluate_generator(
test_batch_iterator,
val_samples=test_batch_iterator.sample_count)
self.assertIsNotNone(score, 'should have evaluated the model')
def test_save(self):
disable_sysout()
def custom_activation(x):
return x
register_custom_activation('custom_activation', custom_activation)
register_custom_layer('custom_layer', CustomLayer,
{'output_dim': int_param(1, 100)})
with tempfile.TemporaryDirectory() as tmp_dir:
batch_size = 50
batch_iterator, test_batch_iterator, nb_classes = get_reuters_dataset(
batch_size, 1000)
layout = Layout(input_size=1000,
output_size=nb_classes,
output_activation='softmax')
training = Training(
objective=Objective('categorical_crossentropy'),
optimizer=Optimizer(optimizer='Adam'),
metric=Metric('categorical_accuracy'),
stopping=EpochStoppingCondition(10),
batch_size=batch_size)
experiment_parameters = ExperimentParameters(
use_default_values=True)
experiment_parameters.layout_parameter('rows', 1)
experiment_parameters.layout_parameter('blocks', 1)
experiment_parameters.layout_parameter('layers', 1)
experiment_parameters.layout_parameter('block.layer_type',
'custom_layer')
experiment = Experiment('test__reuters_experiment',
layout,
training,
batch_iterator,
test_batch_iterator,
CpuEnvironment(n_jobs=1, data_dir=tmp_dir),
parameters=experiment_parameters)
blueprint = create_random_blueprint(experiment)
model = ModelBuilder().build(blueprint, default_device())
model.fit_generator(
generator=batch_iterator,
samples_per_epoch=batch_iterator.samples_per_epoch,
nb_epoch=10,
validation_data=test_batch_iterator,
nb_val_samples=test_batch_iterator.sample_count)
filepath = join(tmp_dir, 'model')
model.save(filepath)
model = load_keras_model(filepath)
self.assertIsNotNone(model, 'Should have loaded the model')
def test_train(self):
disable_sysout()
with tempfile.TemporaryDirectory() as tmp_dir:
batch_size = 50
batch_iterator, test_batch_iterator, nb_classes = get_reuters_dataset(
batch_size, 1000)
layout = Layout(input_size=1000,
output_size=nb_classes,
output_activation='softmax')
training = Training(
objective=Objective('categorical_crossentropy'),
optimizer=Optimizer(optimizer='Adam'),
metric=Metric('categorical_accuracy'),
stopping=EpochStoppingCondition(10),
batch_size=batch_size)
experiment_parameters = ExperimentParameters(
use_default_values=True)
experiment_parameters.layout_parameter('rows', 1)
experiment_parameters.layout_parameter('blocks', 1)
experiment_parameters.layout_parameter('layers', 1)
experiment = Experiment('test__reuters_experiment',
layout,
training,
batch_iterator,
test_batch_iterator,
CpuEnvironment(n_jobs=1, data_dir=tmp_dir),
parameters=experiment_parameters)
blueprint = create_random_blueprint(experiment)
model = ModelBuilder().build(blueprint, default_device())
result = model.fit_generator(
generator=batch_iterator,
samples_per_epoch=batch_iterator.samples_per_epoch,
nb_epoch=10,
validation_data=test_batch_iterator,
nb_val_samples=test_batch_iterator.sample_count)
self.assertIsNotNone(result, 'should have fit the model')
score = model.evaluate_generator(
test_batch_iterator,
val_samples=test_batch_iterator.sample_count)
self.assertIsNotNone(score, 'should have evaluated the model')
def test_model_trainer(self):
disable_sysout()
with tempfile.TemporaryDirectory() as tmp_dir:
batch_size = 50
batch_iterator, test_batch_iterator, nb_classes = get_reuters_dataset(
batch_size, 1000)
layout = Layout(input_size=1000,
output_size=nb_classes,
output_activation='softmax')
training = Training(
objective=Objective('categorical_crossentropy'),
optimizer=Optimizer(optimizer='Adam'),
metric=Metric('categorical_accuracy'),
stopping=EpochStoppingCondition(10),
batch_size=batch_size)
experiment_parameters = ExperimentParameters(
use_default_values=True)
experiment_parameters.layout_parameter('rows', 1)
experiment_parameters.layout_parameter('blocks', 1)
experiment_parameters.layout_parameter('layers', 1)
experiment = Experiment('test__reuters_experiment',
layout,
training,
batch_iterator,
test_batch_iterator,
CpuEnvironment(n_jobs=1, data_dir=tmp_dir),
parameters=experiment_parameters)
blueprint = create_random_blueprint(experiment)
trainer = ModelTrainer(batch_iterator, test_batch_iterator)
model_filename = join(tmp_dir, 'model')
model, history, _duration = trainer.train(
blueprint,
cpu_device(),
save_best_model=True,
model_filename=model_filename)
self.assertIsNotNone(model, 'should have fit the model')
self.assertTrue(isfile(model_filename),
'Should have saved the model')
self.assertIsNotNone(history, 'Should have the training history')
def model_training_worker(batch_iterator, test_batch_iterator, device_id,
device, work_queue, result_queue):
disable_sysout()
model_trainer = ModelTrainer(batch_iterator, test_batch_iterator)
work = work_queue.get()
while work:
try:
idx, _total, blueprint = work
model, history, duration = model_trainer.train(blueprint, device)
if model and history:
epoch_total = len(history.epoch)
val_metric = get_associated_validation_metric(
blueprint.training.metric.metric)
epoch_best = numpy.argmax(history.history[val_metric])
score = history.history[val_metric][epoch_best]
else:
score, epoch_best, epoch_total = 0, 0, 0
result_queue.put((idx, score, epoch_best, epoch_total, blueprint,
duration, device_id))
work = work_queue.get()
except Exception as ex:
logging.error(ex)
result_queue.put(None)
def test_ga_search(self):
with tempfile.TemporaryDirectory() as tmp_dir:
epoch = 3
generations = 2
batch_size = 50
batch_iterator, test_batch_iterator, nb_classes = get_reuters_dataset(
batch_size, 1000)
layout = Layout(input_size=1000,
output_size=nb_classes,
output_activation='softmax')
training = Training(
objective=Objective('categorical_crossentropy'),
optimizer=Optimizer(optimizer='Adam'),
metric=Metric('categorical_accuracy'),
stopping=EpochStoppingCondition(epoch),
batch_size=batch_size)
experiment_parameters = ExperimentParameters(
use_default_values=False)
experiment_parameters.layout_parameter('rows', 1)
experiment_parameters.layout_parameter('blocks', 1)
experiment_parameters.layout_parameter('layers', 1)
experiment_parameters.layer_parameter('Dense.output_dim',
int_param(10, 500))
experiment_parameters.all_search_parameters(True)
experiment_label = 'test__reuters_experiment'
experiment = Experiment(experiment_label,
layout,
training,
batch_iterator,
test_batch_iterator,
CpuEnvironment(n_jobs=2, data_dir=tmp_dir),
parameters=experiment_parameters)
run_ga_search_experiment(experiment,
population_size=2,
generations=2)
self.assertTrue(isfile(experiment.get_log_filename()),
'Should have logged')
self.assertTrue(isfile(experiment.get_step_data_filename(0)),
'Should have logged')
self.assertTrue(isfile(experiment.get_step_log_filename(0)),
'Should have logged')
blueprints = load_experiment_blueprints(
experiment_label, 0, Environment(data_dir=tmp_dir))
self.assertTrue(
len(blueprints) > 0, 'Should have saved/loaded blueprints')
model = ModelBuilder().build(blueprints[0], cpu_device())
disable_sysout()
model.fit_generator(
generator=batch_iterator,
samples_per_epoch=batch_iterator.samples_per_epoch,
nb_epoch=5,
validation_data=test_batch_iterator,
nb_val_samples=test_batch_iterator.sample_count)
score = model.evaluate_generator(
test_batch_iterator,
val_samples=test_batch_iterator.sample_count)
self.assertTrue(score[1] > 0, 'Should have valid score')
step, population = load_experiment_checkpoint(experiment)
self.assertEqual(generations - 1, step,
'Should have loaded checkpoint')
self.assertIsNotNone(population, 'Should have loaded checkpoint')
blueprint = load_experiment_best_blueprint(
experiment.label,
environment=CpuEnvironment(n_jobs=2, data_dir=tmp_dir))
model = ModelBuilder().build(blueprint,
cpu_device(),
compile_model=False)
self.assertIsNotNone(
model,
'Should have loaded and built best model from experiment')