def get_conv_dense_model():
graph = Graph((32, 32, 3), False)
output_node_id = 0
output_node_id = graph.add_layer(StubReLU(), output_node_id)
output_node_id = graph.add_layer(StubConv(3, 3, 3), output_node_id)
output_node_id = graph.add_layer(StubBatchNormalization(3), output_node_id)
output_node_id = graph.add_layer(StubReLU(), output_node_id)
output_node_id = graph.add_layer(StubConv(3, 3, 3), output_node_id)
output_node_id = graph.add_layer(StubBatchNormalization(3), output_node_id)
output_node_id = graph.add_layer(StubFlatten(), output_node_id)
output_node_id = graph.add_layer(StubDropout(Constant.DENSE_DROPOUT_RATE), output_node_id)
output_node_id = graph.add_layer(StubReLU(), output_node_id)
output_node_id = graph.add_layer(StubDense(graph.node_list[output_node_id].shape[0], 5),
output_node_id)
output_node_id = graph.add_layer(StubReLU(), output_node_id)
output_node_id = graph.add_layer(StubDense(5, 5), output_node_id)
graph.add_layer(StubSoftmax(), output_node_id)
graph.produce_model().set_weight_to_graph()
return graph
def get_conv_dense_model():
graph = Graph((32, 32, 3), False)
output_node_id = 0
output_node_id = graph.add_layer(StubReLU(), output_node_id)
output_node_id = graph.add_layer(StubConv(3, 3, 3), output_node_id)
output_node_id = graph.add_layer(StubBatchNormalization(3), output_node_id)
output_node_id = graph.add_layer(StubReLU(), output_node_id)
output_node_id = graph.add_layer(StubConv(3, 3, 3), output_node_id)
output_node_id = graph.add_layer(StubBatchNormalization(3), output_node_id)
output_node_id = graph.add_layer(StubFlatten(), output_node_id)
output_node_id = graph.add_layer(StubDropout(Constant.DENSE_DROPOUT_RATE), output_node_id)
output_node_id = graph.add_layer(StubReLU(), output_node_id)
output_node_id = graph.add_layer(StubDense(graph.node_list[output_node_id].shape[0], 5),
output_node_id)
output_node_id = graph.add_layer(StubReLU(), output_node_id)
output_node_id = graph.add_layer(StubDense(5, 5), output_node_id)
graph.add_layer(StubSoftmax(), output_node_id)
graph.produce_model().set_weight_to_graph()
return graph
def get_add_skip_model():
graph = Graph((5, 5, 3), False)
output_node_id = 0
output_node_id = graph.add_layer(StubReLU(), output_node_id)
output_node_id = graph.add_layer(StubConv(3, 3, 3), output_node_id)
output_node_id = graph.add_layer(StubBatchNormalization(3), output_node_id)
output_node_id = graph.add_layer(StubDropout(constant.CONV_DROPOUT_RATE), output_node_id)
output_node_id = graph.add_layer(StubReLU(), output_node_id)
output_node_id = graph.add_layer(StubConv(3, 3, 3), output_node_id)
output_node_id = graph.add_layer(StubBatchNormalization(3), output_node_id)
output_node_id = graph.add_layer(StubDropout(constant.CONV_DROPOUT_RATE), output_node_id)
temp_node_id = output_node_id
output_node_id = graph.add_layer(StubReLU(), output_node_id)
output_node_id = graph.add_layer(StubConv(3, 3, 3), output_node_id)
output_node_id = graph.add_layer(StubBatchNormalization(3), output_node_id)
output_node_id = graph.add_layer(StubDropout(constant.CONV_DROPOUT_RATE), output_node_id)
temp_node_id = graph.add_layer(StubConv(3, 3, 1), temp_node_id)
output_node_id = graph.add_layer(StubAdd(), [output_node_id, temp_node_id])
temp_node_id = output_node_id
output_node_id = graph.add_layer(StubReLU(), output_node_id)
output_node_id = graph.add_layer(StubConv(3, 3, 3), output_node_id)
output_node_id = graph.add_layer(StubBatchNormalization(3), output_node_id)
output_node_id = graph.add_layer(StubDropout(constant.CONV_DROPOUT_RATE), output_node_id)
temp_node_id = graph.add_layer(StubConv(3, 3, 1), temp_node_id)
output_node_id = graph.add_layer(StubAdd(), [output_node_id, temp_node_id])
output_node_id = graph.add_layer(StubReLU(), output_node_id)
output_node_id = graph.add_layer(StubConv(3, 3, 3), output_node_id)
output_node_id = graph.add_layer(StubBatchNormalization(3), output_node_id)
output_node_id = graph.add_layer(StubDropout(constant.CONV_DROPOUT_RATE), output_node_id)
output_node_id = graph.add_layer(StubFlatten(), output_node_id)
output_node_id = graph.add_layer(StubReLU(), output_node_id)
output_node_id = graph.add_layer(StubDense(graph.node_list[output_node_id].shape[0], 5),
output_node_id)
output_node_id = graph.add_layer(StubDropout(constant.DENSE_DROPOUT_RATE), output_node_id)
output_node_id = graph.add_layer(StubReLU(), output_node_id)
output_node_id = graph.add_layer(StubDense(5, 5), output_node_id)
output_node_id = graph.add_layer(StubDropout(constant.DENSE_DROPOUT_RATE), output_node_id)
graph.add_layer(StubSoftmax(), output_node_id)
graph.produce_model().set_weight_to_graph()
return graph
def search(self, x_train, y_train, x_test, y_test):
"""Override parent's search function. First model is randomly generated"""
if not self.history:
model = DefaultClassifierGenerator(self.n_classes,
self.input_shape).generate()
self.add_model(model, x_train, y_train, x_test, y_test)
pickle_to_file(self, os.path.join(self.path, 'searcher'))
else:
model = self.load_best_model()
new_graphs = transform(Graph(model, False))
new_models = []
for graph in new_graphs:
nm_graph = Graph(model, True)
for args in graph.operation_history:
getattr(nm_graph, args[0])(*list(args[1:]))
new_models.append(nm_graph.produce_model())
new_models = self._remove_duplicate(list(new_models))
for model in new_models:
if self.model_count < constant.MAX_MODEL_NUM:
self.add_model(model, x_train, y_train, x_test, y_test)
pickle_to_file(self, os.path.join(self.path, 'searcher'))
backend.clear_session()
return self.load_best_model()
def cross_validate(self, x_all, y_all, n_splits, trainer_args=None):
"""Do the n_splits cross-validation for the input."""
if trainer_args is None:
trainer_args = {}
if constant.LIMIT_MEMORY:
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
sess = tf.Session(config=config)
init = tf.global_variables_initializer()
sess.run(init)
backend.set_session(sess)
k_fold = StratifiedKFold(n_splits=n_splits, shuffle=False, random_state=7)
ret = []
y_raw_all = y_all
y_all = self.y_encoder.transform(y_all)
model = self.load_searcher().load_best_model()
for train, test in k_fold.split(x_all, y_raw_all):
graph = Graph(model, False)
backend.clear_session()
model = graph.produce_model()
ModelTrainer(model,
x_all[train],
y_all[train],
x_all[test],
y_all[test], False).train_model(**trainer_args)
scores = model.evaluate(x_all[test], y_all[test], verbose=self.verbose)
if self.verbose:
print('Score:', scores[1])
ret.append(scores[1] * 100)
return np.array(ret)
def copy_conv_model(model):
"""Return copied convolution model
Args:
model: the model we want to copy
Returns:
The copied model
"""
graph = Graph(model)
return graph.produce_model()
def maximize_acq(self):
model_ids = self.search_tree.adj_list.keys()
target_graph = None
father_id = None
descriptors = self.descriptors
pq = PriorityQueue()
temp_list = []
for model_id in model_ids:
accuracy = self.get_accuracy_by_id(model_id)
temp_list.append((accuracy, model_id))
temp_list = sorted(temp_list)
if len(temp_list) > 5:
temp_list = temp_list[:-5]
for accuracy, model_id in temp_list:
model = self.load_model_by_id(model_id)
graph = Graph(model, False)
pq.put(Elem(accuracy, model_id, graph))
t = 1.0
t_min = self.t_min
alpha = 0.9
max_acq = -1
while not pq.empty() and t > t_min:
elem = pq.get()
ap = math.exp((elem.accuracy - max_acq) / t)
if ap > random.uniform(0, 1):
graphs = transform(elem.graph)
graphs = list(
filter(lambda x: x.extract_descriptor() not in descriptors,
graphs))
if not graphs:
continue
for temp_graph in graphs:
temp_acq_value = self.acq(temp_graph)
pq.put(Elem(temp_acq_value, elem.father_id, temp_graph))
descriptors[temp_graph.extract_descriptor()] = True
if temp_acq_value > max_acq:
max_acq = temp_acq_value
father_id = elem.father_id
target_graph = temp_graph
t *= alpha
model = self.load_model_by_id(father_id)
nm_graph = Graph(model, True)
if self.verbose:
print('Father ID: ', father_id)
print(target_graph.operation_history)
for args in target_graph.operation_history:
getattr(nm_graph, args[0])(*list(args[1:]))
return nm_graph.produce_model(), father_id
def search(self, x_train, y_train, x_test, y_test):
if not self.history:
model = DefaultClassifierGenerator(self.n_classes,
self.input_shape).generate(
self.default_model_len,
self.default_model_width)
history_item = self.add_model(model, x_train, y_train, x_test,
y_test)
self.search_tree.add_child(-1, history_item['model_id'])
graph = Graph(model)
self.init_search_queue = []
# for child_graph in transform(graph):
# self.init_search_queue.append((child_graph, history_item['model_id']))
self.init_gpr_x.append(graph.extract_descriptor())
self.init_gpr_y.append(history_item['accuracy'])
pickle_to_file(self, os.path.join(self.path, 'searcher'))
return
if self.init_search_queue:
graph, father_id = self.init_search_queue.pop()
model = graph.produce_model()
history_item = self.add_model(model, x_train, y_train, x_test,
y_test)
self.search_tree.add_child(father_id, history_item['model_id'])
self.init_gpr_x.append(graph.extract_descriptor())
self.init_gpr_y.append(history_item['accuracy'])
pickle_to_file(self, os.path.join(self.path, 'searcher'))
return
if not self.init_search_queue and not self.gpr.first_fitted:
self.gpr.first_fit(self.init_gpr_x, self.init_gpr_y)
new_model, father_id = self.maximize_acq()
history_item = self.add_model(new_model, x_train, y_train, x_test,
y_test)
self.search_tree.add_child(father_id, history_item['model_id'])
self.gpr.incremental_fit(
Graph(new_model).extract_descriptor(), history_item['accuracy'])
pickle_to_file(self, os.path.join(self.path, 'searcher'))