def _train_and_test(self,
model_path,
output_model_path,
training_datapoints,
test_datapoints,
keep_classes=False):
engine = ImprintingEngine(model_path, keep_classes)
image_shape = self._get_image_shape(model_path)
data_dir = test_utils.test_data_path('imprinting')
# train.
for training_datapoint in training_datapoints:
engine.train(
test_utils.prepare_images(training_datapoint['image_names'],
data_dir, image_shape),
training_datapoint['label_id'])
engine.save_model(output_model_path)
# Test.
engine = ClassificationEngine(output_model_path)
self.assertEqual(1, engine.get_num_of_output_tensors())
if not keep_classes:
self.assertEqual(len(training_datapoints),
engine.get_output_tensor_size(0))
for test_datapoint in test_datapoints:
self._classify_image(engine, data_dir,
test_datapoint['image_name'],
test_datapoint['label_id'],
test_datapoint['score'])
def run_benchmark(model):
"""Measures training time for given model with random data.
Args:
model: string, file name of the input model.
Returns:
float, training time.
"""
input_size = input_tensor_size(model)
engine = ImprintingEngine(test_utils.test_data_path(model),
keep_classes=False)
np.random.seed(12345)
data_by_category = {}
# 10 Categories, each has 20 images.
for i in range(0, 10):
data_by_category[i] = []
for j in range(0, 20):
data_by_category[i].append(np.random.randint(0, 255, input_size))
start = time.perf_counter()
for class_id, tensors in enumerate(data_by_category.values()):
engine.train(tensors, class_id)
with tempfile.NamedTemporaryFile() as f:
engine.save_model(f.name)
training_time = time.perf_counter() - start
print('Model: %s' % model)
print('Training time: %.2fs' % training_time)
return training_time
def _train_and_test_run_inference(self,
model_path,
training_datapoints,
test_datapoints,
keep_classes=False):
engine = ImprintingEngine(model_path, keep_classes)
image_shape = self._get_image_shape(model_path)
data_dir = test_utils.test_data_path('imprinting')
# train.
for training_datapoint in training_datapoints:
engine.train(
test_utils.prepare_images(training_datapoint['image_names'],
data_dir, image_shape),
training_datapoint['label_id'])
# Test with running inference.
for test_datapoint in test_datapoints:
self._classify_image_by_inference(engine, image_shape, data_dir,
test_datapoint['image_name'],
test_datapoint['label_id'],
test_datapoint['score'])
def _benchmark_for_training(model, data_set):
"""Measures training time for given model and data set.
Args:
model: string, file name of the input model.
data_set: string, name of the folder storing images. Labels file is also
named as '[data_set].csv'.
Returns:
float, training time.
"""
shape = _get_shape(model)
engine = ImprintingEngine(test_utils.test_data_path('imprinting', model),
keep_classes=False)
output_model_path = '/tmp/model_for_benchmark.tflite'
data_dir = test_utils.test_data_path(data_set)
# The labels file is named as '[data_set].csv'.
image_list_by_category = test_utils.prepare_classification_data_set(
test_utils.test_data_path(data_set + '.csv'))
start_time = time.monotonic()
for category, image_list in image_list_by_category.items():
category_dir = os.path.join(data_dir, category)
image_list_by_category[category] = test_utils.prepare_images(
image_list, category_dir, shape)
end_time = time.monotonic()
print('Image pre-processing time: ', end_time - start_time, 's')
start_time = end_time
for class_id, tensors in enumerate(image_list_by_category.values()):
engine.train(tensors, class_id)
engine.save_model(output_model_path)
training_time = time.monotonic() - start_time
print('Model: ', model)
print('Data set : ', data_set)
print('Training time : ', training_time, 's')
# Remove the model.
subprocess.call(['rm', output_model_path])
return training_time