def train(q, graph, train_data, test_data, trainer_args, metric, loss, verbose,
path):
"""Train the neural architecture."""
try:
model = graph.produce_model()
loss, metric_value = ModelTrainer(
model=model,
path=path,
train_data=train_data,
test_data=test_data,
metric=metric,
loss_function=loss,
verbose=verbose).train_model(**trainer_args)
model.set_weight_to_graph()
if q:
q.put((metric_value, loss, model.graph))
return metric_value, loss, model.graph
except RuntimeError as e:
if not re.search('out of memory', str(e)):
raise e
if verbose:
print(
'\nCurrent model size is too big. Discontinuing training this model to search for other models.'
)
Constant.MAX_MODEL_SIZE = graph.size() - 1
if q:
q.put((None, None, None))
return None, None, None
except TimeoutError:
if q:
q.put((None, None, None))
return None, None, None
def test_model_trainer_classification():
model = CnnGenerator(3, (28, 28, 3)).generate().produce_model()
train_data, test_data = get_classification_data_loaders()
ModelTrainer(model,
train_data=train_data,
test_data=test_data,
metric=Accuracy,
loss_function=classification_loss,
verbose=True).train_model(max_iter_num=3)
def test_model_trainer_regression():
model = CnnGenerator(1, (28, 28, 3)).generate().produce_model()
train_data, test_data = get_regression_data_loaders()
ModelTrainer(model,
train_data=train_data,
test_data=test_data,
metric=MSE,
loss_function=regression_loss,
verbose=False).train_model(max_iter_num=3)
def test_model_trainer_timout():
model = CnnGenerator(3, (28, 28, 3)).generate().produce_model()
timeout = 1
train_data, test_data = get_classification_data_loaders()
with pytest.raises(TimeoutError):
ModelTrainer(model,
train_data=train_data,
test_data=test_data,
metric=Accuracy,
loss_function=classification_loss,
verbose=True,
path=TEST_TEMP_DIR).train_model(max_iter_num=300, timeout=timeout)
clean_dir(TEST_TEMP_DIR)
def train(args):
graph, train_data, test_data, trainer_args, path, metric, loss, verbose = args
model = graph.produce_model()
# if path is not None:
# plot_model(model, to_file=path, show_shapes=True)
loss, metric_value = ModelTrainer(model=model,
train_data=train_data,
test_data=test_data,
metric=metric,
loss_function=loss,
verbose=verbose).train_model(**trainer_args)
model.set_weight_to_graph()
return metric_value, loss, model.graph
def train(q, graph, train_data, test_data, trainer_args, metric, loss, verbose,
path):
"""Train the neural architecture."""
model = graph.produce_model()
loss, metric_value = ModelTrainer(
model=model,
path=path,
train_data=train_data,
test_data=test_data,
metric=metric,
loss_function=loss,
verbose=verbose).train_model(**trainer_args)
model.set_weight_to_graph()
if q:
q.put((metric_value, loss, model.graph))
return metric_value, loss, model.graph
def final_fit(self,
x_train,
y_train,
x_test,
y_test,
trainer_args=None,
retrain=True):
x_train = self.preprocess(x_train)
x_test = self.preprocess(x_test)
self.encoder.fit(y_train)
y_train = self.encoder.transform(y_train)
y_test = self.encoder.transform(y_test)
self.data_transformer = ImageDataTransformer(x_train,
augment=self.augment)
train_data = self.data_transformer.transform_train(x_train,
y_train,
batch_size=1)
test_data = self.data_transformer.transform_test(x_test,
y_test,
batch_size=1)
self.net = CnnGenerator(self.encoder.n_classes, x_train.shape[1:]) \
.generate(model_len=self.Length, model_width=self.Width).produce_model()
pickle_to_file(self, os.path.join(self.path, 'classifier'))
self.model_trainer = ModelTrainer(self.net,
path=self.path,
loss_function=classification_loss,
metric=Accuracy,
train_data=train_data,
test_data=test_data,
verbose=True)
self.model_trainer.train_model(self.Epochs, 3)
print('Finished Final Fit')
compose_list = Compose([])
train_data = DataLoader(MultiTransformDataset(torch.Tensor(train_x),
torch.Tensor(train_y),
compose_list),
batch_size=batch_size,
shuffle=False)
test_data = DataLoader(MultiTransformDataset(torch.Tensor(test_x),
torch.Tensor(test_y),
compose_list),
batch_size=batch_size,
shuffle=False)
model_trainer = ModelTrainer(model,
loss_function=classification_loss,
metric=Accuracy,
train_data=train_data,
test_data=test_data,
verbose=True)
model_trainer.train_model(2, 1)
model.eval()
outputs = []
with torch.no_grad():
for index, (inputs, _) in enumerate(test_data):
outputs.append(model(inputs).numpy())
output = reduce(lambda x, y: np.concatenate((x, y)), outputs)
predicted = encoder.inverse_transform(output)
print(predicted)
def fit(self, x_train=None, y_train=None, time_limit=60 * 60 * 6):
end_time = time.time() + time_limit
x_train = self.preprocess(x_train)
x_train, x_valid, y_train, y_valid = train_test_split(x_train,
y_train,
test_size=0.25,
shuffle=True)
x_train, y_train = np.array(x_train), np.array(y_train)
x_valid, y_valid = np.array(x_valid), np.array(y_valid)
self.encoder.fit(y_train)
y_train = self.encoder.transform(y_train)
y_valid = self.encoder.transform(y_valid)
self.data_transformer = ImageDataTransformer(x_train,
augment=self.augment)
train_data = self.data_transformer.transform_train(x_train,
y_train,
batch_size=1)
test_data = self.data_transformer.transform_test(x_valid,
y_valid,
batch_size=1)
y_valid = self.encoder.inverse_transform(y_valid)
visited = set()
pq = []
trainingQ = [(self.Length, self.Width, self.Epochs)]
accuracy = 0.0
while trainingQ:
for len, width, epoch in trainingQ:
if time.time() < end_time and (len, width,
epoch) not in visited:
visited.add((len, width, epoch))
try:
net = CnnGenerator(self.encoder.n_classes, x_train.shape[1:])\
.generate(model_len=len, model_width=width).produce_model()
model_trainer = ModelTrainer(
net,
path=self.path,
loss_function=classification_loss,
metric=Accuracy,
train_data=train_data,
test_data=test_data,
verbose=True)
model_trainer.train_model(epoch, 3)
outputs = []
with torch.no_grad():
for index, (inputs, _) in enumerate(test_data):
outputs.append(net(inputs).numpy())
output = reduce(lambda x, y: np.concatenate((x, y)),
outputs)
pred_valid = self.encoder.inverse_transform(output)
accu = self.metric().evaluate(y_valid, pred_valid)
print("Accuracy: ", accu, " Parameters: ", len, width,
epoch)
pq.append((-accu, (len, width, epoch)))
if pq.__len__() > self.capacity:
heapq.heapify(pq)
pq.remove(heapq.nlargest(1, pq)[0])
if accu > accuracy:
self.Epochs = epoch
self.Length = len
self.Width = width
accuracy = accu
except Exception as e:
print(e)
if not pq:
break
heapq.heapify(pq)
_, (nexlen, nexwidth, nexepoch) = heapq.heappop(pq)
# Create children
trainingQ = []
trainingQ.append((nexlen + 1, nexwidth, nexepoch))
trainingQ.append((nexlen, nexwidth * 2, nexepoch))
trainingQ.append((nexlen, nexwidth, nexepoch + 5))
trainingQ.append((nexlen + 2, nexwidth, nexepoch + 3))
trainingQ.append((nexlen, nexwidth * 2, nexepoch + 2))
trainingQ.append((nexlen + 1, nexwidth, nexepoch + 3))
print('Finished Fit')
print("Optimal Conv3D Network Parameters:")
print("Number of Layers (Length):", self.Length)
print("Number of Filters (Width):", self.Width)
print("Number of Epochs", self.Epochs)
print()