def test_node_consistency():
graph = CnnGenerator(10, (32, 32, 3)).generate()
assert graph.layer_list[6].output.shape == (16, 16, 64)
for layer in graph.layer_list:
assert layer.output.shape == layer.output_shape
graph.to_wider_model(5, 64)
assert graph.layer_list[5].output.shape == (16, 16, 128)
for layer in graph.layer_list:
assert layer.output.shape == layer.output_shape
graph.to_conv_deeper_model(5, 3)
assert graph.layer_list[19].output.shape == (16, 16, 128)
for layer in graph.layer_list:
assert layer.output.shape == layer.output_shape
graph.to_add_skip_model(5, 18)
assert graph.layer_list[23].output.shape == (16, 16, 128)
for layer in graph.layer_list:
assert layer.output.shape == layer.output_shape
graph.to_concat_skip_model(5, 18)
assert graph.layer_list[25].output.shape == (16, 16, 256)
for layer in graph.layer_list:
assert layer.output.shape == layer.output_shape
def test_wider_dense():
graph = CnnGenerator(10, (32, 32, 3)).generate()
graph.produce_model().set_weight_to_graph()
history = [('to_wider_model', 14, 64)]
for args in history:
getattr(graph, args[0])(*list(args[1:]))
graph.produce_model()
assert legal_graph(graph)
def test_wider_conv():
model = CnnGenerator(10, (28, 28, 3)).generate().produce_model()
model.set_weight_to_graph()
graph = model.graph
assert isinstance(wider_pre_conv(graph.layer_list[1], 3), StubConv)
assert isinstance(wider_bn(graph.layer_list[2], 3, 3, 3), StubBatchNormalization)
assert isinstance(wider_next_conv(graph.layer_list[5], 3, 3, 3), StubConv)
def test_long_transform():
graph = CnnGenerator(10, (32, 32, 3)).generate()
history = [('to_wider_model', 1, 256), ('to_conv_deeper_model', 1, 3),
('to_concat_skip_model', 5, 9)]
for args in history:
getattr(graph, args[0])(*list(args[1:]))
graph.produce_model()
assert legal_graph(graph)
def test_long_transform():
graph = CnnGenerator(10, (32, 32, 3)).generate()
history = [('to_wider_model', 1, 256), ('to_conv_deeper_model', 1, 3),
('to_concat_skip_model', 5, 9)]
for args in history:
getattr(graph, args[0])(*list(args[1:]))
graph.produce_model()
assert legal_graph(graph)
def test_wider_conv():
model = CnnGenerator(10, (28, 28, 3)).generate().produce_model()
model.set_weight_to_graph()
graph = model.graph
assert isinstance(wider_pre_conv(graph.layer_list[1], 3), StubConv)
assert isinstance(wider_bn(graph.layer_list[2], 3, 3, 3),
StubBatchNormalization)
assert isinstance(wider_next_conv(graph.layer_list[5], 3, 3, 3), StubConv)
def test_node_consistency():
graph = CnnGenerator(10, (32, 32, 3)).generate()
assert graph.layer_list[6].output.shape == (16, 16, 64)
for layer in graph.layer_list:
assert layer.output.shape == layer.output_shape
graph.to_wider_model(5, 64)
assert graph.layer_list[5].output.shape == (16, 16, 128)
for layer in graph.layer_list:
assert layer.output.shape == layer.output_shape
graph.to_conv_deeper_model(5, 3)
assert graph.layer_list[19].output.shape == (16, 16, 128)
for layer in graph.layer_list:
assert layer.output.shape == layer.output_shape
graph.to_add_skip_model(5, 18)
assert graph.layer_list[23].output.shape == (16, 16, 128)
for layer in graph.layer_list:
assert layer.output.shape == layer.output_shape
graph.to_concat_skip_model(5, 18)
assert graph.layer_list[25].output.shape == (16, 16, 256)
for layer in graph.layer_list:
assert layer.output.shape == layer.output_shape
def init_search(self):
if self.verbose:
print('Initializing search.')
graph = CnnGenerator(self.n_classes, self.input_shape).generate(
self.default_model_len, self.default_model_width)
model_id = self.model_count
self.model_count += 1
self.training_queue.append((graph, -1, model_id))
self.descriptors.append(graph.extract_descriptor())
for child_graph in default_transform(graph):
child_id = self.model_count
self.model_count += 1
self.training_queue.append((child_graph, model_id, child_id))
self.descriptors.append(child_graph.extract_descriptor())
if self.verbose:
print('Initialization finished.')
def init_search(self):
if self.verbose:
print('\nInitializing search.')
graph = CnnGenerator(self.n_classes,
self.input_shape).generate(self.default_model_len,
self.default_model_width)
model_id = self.model_count
self.model_count += 1
self.training_queue.append((graph, -1, model_id))
self.descriptors.append(graph.extract_descriptor())
for child_graph in default_transform(graph):
child_id = self.model_count
self.model_count += 1
self.training_queue.append((child_graph, model_id, child_id))
self.descriptors.append(child_graph.extract_descriptor())
if self.verbose:
print('Initialization finished.')
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_wider_dense():
graph = CnnGenerator(10, (32, 32, 3)).generate()
graph.produce_model().set_weight_to_graph()
history = [('to_wider_model', 14, 64)]
for args in history:
getattr(graph, args[0])(*list(args[1:]))
graph.produce_model()
assert legal_graph(graph)
def test_graph_size():
graph = CnnGenerator(10, (32, 32, 3)).generate()
assert graph.size() == 68938
def test_deeper_conv_block():
graph = CnnGenerator(10, (28, 28, 3)).generate()
layers = deeper_conv_block(graph.layer_list[1], 3)
assert len(layers) == Constant.CONV_BLOCK_DISTANCE + 1
def test_graph_size():
graph = CnnGenerator(10, (32, 32, 3)).generate()
assert graph.size() == 68938
def test_search_space_limit():
graph = CnnGenerator(10, (32, 32, 3)).generate(model_len=3, model_width=2048)
assert to_wider_graph(graph) is None
graph = CnnGenerator(10, (32, 32, 3)).generate(model_len=14)
assert to_deeper_graph(graph) is None
def test_model_trainer_regression():
model = CnnGenerator(1, (28, 28, 3)).generate().produce_model()
train_data, test_data = get_regression_dataloaders()
ModelTrainer(model, train_data, test_data, MSE, regression_loss, False).train_model(max_iter_num=3)
def test_model_trainer_classification():
model = CnnGenerator(3, (28, 28, 3)).generate().produce_model()
train_data, test_data = get_classification_dataloaders()
ModelTrainer(model, train_data, test_data, Accuracy, classification_loss, False).train_model(max_iter_num=3)
def test_default_transform():
graphs = default_transform(CnnGenerator(10, (32, 32, 3)).generate())
model = graphs[0].produce_model()
model(torch.Tensor(get_conv_data()))
assert len(graphs) == 1
assert len(graphs[0].layer_list) == 43