def TrainEvaluate(self, request, context):
current_input = []
core_hyperparameters = []
for i in range(len(request.current_input.values)):
current_input.append(request.current_input.values[i])
for i in range(len(request.hyperparameters)):
core_hyperparameters.append(request.hyperparameters[i])
hyperparameters = [self.worker_id] + core_hyperparameters
current_input_reshaped = np.array(current_input)
tag = request.tag
proposed_perturbations = []
for j in range(len(request.perturbations)):
proposed_perturbation = []
for k in range(len(request.perturbations[j].values)):
proposed_perturbation.append(
request.perturbations[j].values[k])
proposed_perturbations.append(proposed_perturbation)
perturbations = []
function_values = []
evaluation_stats = []
for i in range(len(proposed_perturbations)):
perturbation = np.array(proposed_perturbations[i])
perturbations.append(
zero_order_pb2.Vector(values=perturbation.tolist()))
task_id_list = np.random.choice(self.task_ids,
size=self.task_batch_size,
replace=False)
task_list = [
self.blackbox_object.config.make_task_fn(task_id=task_id)
for task_id in task_id_list
]
function_value, evaluation_stat = self.blackbox_object.execute(
current_input_reshaped + perturbation,
task_list,
hyperparameters=hyperparameters)
evaluation_stats.append(evaluation_stat)
function_values.append(function_value)
evaluation_stats_reduced = [sum(x) for x in zip(*evaluation_stats)]
if not proposed_perturbations:
results = zero_order_pb2.EvaluationResponse(
perturbations=perturbations,
function_values=function_values,
evaluation_stats=evaluation_stats_reduced,
tag=tag)
else:
results = zero_order_pb2.EvaluationResponse(
perturbations=[],
function_values=function_values,
evaluation_stats=evaluation_stats_reduced,
tag=tag)
return results
def TestEvaluate(self, request, context):
current_input = []
core_hyperparameters = []
for i in range(len(request.current_input.values)):
current_input.append(request.current_input.values[i])
for i in range(len(request.hyperparameters)):
core_hyperparameters.append(request.hyperparameters[i])
hyperparameters = [self.worker_id] + core_hyperparameters
current_input = np.array(current_input)
iteration = request.tag
if iteration % self.blackbox_object.config.test_frequency == 0:
task = self.blackbox_object.config.make_task_fn(
task_id=self.task_ids[self.worker_id])
mamlpt_value = self.blackbox_object.task_value(
params=current_input,
task=task,
hyperparameters=hyperparameters,
test_mode=True,
horizon=self.blackbox_object.config.horizon)
mamlpt_value_list = [mamlpt_value]
for _ in range(self.blackbox_object.config.test_parallel_evals -
1):
temp_mamlpt_value = self.blackbox_object.task_value(
params=current_input,
task=task,
hyperparameters=hyperparameters,
test_mode=True,
horizon=self.blackbox_object.config.horizon)
mamlpt_value_list.append(temp_mamlpt_value)
adaptation_param = self.blackbox_object.adaptation_step(
params=current_input,
task=task,
hyperparameters=hyperparameters,
test_mode=True,
horizon=self.blackbox_object.config.horizon)
adaptation_value = self.blackbox_object.task_value(
params=adaptation_param,
task=task,
hyperparameters=hyperparameters,
test_mode=True,
horizon=self.blackbox_object.config.horizon)
adaptation_value_list = [adaptation_value]
for _ in range(self.blackbox_object.config.test_parallel_evals -
1):
temp_adaptation_value = self.blackbox_object.task_value(
params=adaptation_param,
task=task,
hyperparameters=hyperparameters,
test_mode=True,
horizon=self.blackbox_object.config.horizon)
adaptation_value_list.append(temp_adaptation_value)
test_vals = mamlpt_value_list + adaptation_value_list
results = zero_order_pb2.EvaluationResponse(
perturbations=[],
function_values=test_vals,
evaluation_stats=[],
tag=0)
else:
results = zero_order_pb2.EvaluationResponse(perturbations=[],
function_values=[],
evaluation_stats=[],
tag=0)
return results