def test_export_graph_with_fixed_size_image_tensor_input(self):
input_shape = [1, 320, 320, 3]
tmp_dir = self.get_temp_dir()
trained_checkpoint_prefix = os.path.join(tmp_dir, 'model.ckpt')
self._save_checkpoint_from_mock_model(
trained_checkpoint_prefix, use_moving_averages=False)
with mock.patch.object(
model_builder, 'build', autospec=True) as mock_builder:
mock_builder.return_value = FakeModel()
output_directory = os.path.join(tmp_dir, 'output')
pipeline_config = pipeline_pb2.TrainEvalPipelineConfig()
pipeline_config.eval_config.use_moving_averages = False
exporter.export_inference_graph(
input_type='image_tensor',
pipeline_config=pipeline_config,
trained_checkpoint_prefix=trained_checkpoint_prefix,
output_directory=output_directory,
input_shape=input_shape)
saved_model_path = os.path.join(output_directory, 'saved_model')
self.assertTrue(
os.path.exists(os.path.join(saved_model_path, 'saved_model.pb')))
with tf.Graph().as_default() as od_graph:
with self.test_session(graph=od_graph) as sess:
meta_graph = tf.saved_model.loader.load(
sess, [tf.saved_model.tag_constants.SERVING], saved_model_path)
signature = meta_graph.signature_def['serving_default']
input_tensor_name = signature.inputs['inputs'].name
image_tensor = od_graph.get_tensor_by_name(input_tensor_name)
self.assertSequenceEqual(image_tensor.get_shape().as_list(),
input_shape)
def test_export_model_with_detection_only_nodes(self):
tmp_dir = self.get_temp_dir()
trained_checkpoint_prefix = os.path.join(tmp_dir, 'model.ckpt')
self._save_checkpoint_from_mock_model(trained_checkpoint_prefix,
use_moving_averages=True)
output_directory = os.path.join(tmp_dir, 'output')
inference_graph_path = os.path.join(output_directory,
'frozen_inference_graph.pb')
with mock.patch.object(
model_builder, 'build', autospec=True) as mock_builder:
mock_builder.return_value = FakeModel(add_detection_masks=False)
pipeline_config = pipeline_pb2.TrainEvalPipelineConfig()
exporter.export_inference_graph(
input_type='image_tensor',
pipeline_config=pipeline_config,
trained_checkpoint_prefix=trained_checkpoint_prefix,
output_directory=output_directory)
inference_graph = self._load_inference_graph(inference_graph_path)
with self.test_session(graph=inference_graph):
inference_graph.get_tensor_by_name('image_tensor:0')
inference_graph.get_tensor_by_name('detection_boxes:0')
inference_graph.get_tensor_by_name('detection_scores:0')
inference_graph.get_tensor_by_name('detection_classes:0')
inference_graph.get_tensor_by_name('num_detections:0')
with self.assertRaises(KeyError):
inference_graph.get_tensor_by_name('detection_masks:0')
def main(_):
# Specify which gpu to be used
# os.environ["CUDA_VISIBLE_DEVICES"] = '1'
cls_model = resnet_model.Model(resnet_size=50,
bottleneck=True,
num_classes=26,
num_filters=64,
kernel_size=7,
conv_stride=2,
first_pool_size=3,
first_pool_stride=2,
block_sizes=[3, 4, 6, 3],
block_strides=[1, 2, 2, 2],
resnet_version=resnet_model.DEFAULT_VERSION,
data_format='channels_first',
dtype=resnet_model.DEFAULT_DTYPE)
if FLAGS.input_shape:
input_shape = [
int(dim) if dim != -1 else None
for dim in FLAGS.input_shape.split(',')
]
else:
input_shape = [None, None, None, 3]
exporter.export_inference_graph(FLAGS.input_type, cls_model,
FLAGS.trained_checkpoint_prefix,
FLAGS.output_directory, input_shape)
def test_export_saved_model_and_run_inference(self):
tmp_dir = self.get_temp_dir()
trained_checkpoint_prefix = os.path.join(tmp_dir, 'model.ckpt')
self._save_checkpoint_from_mock_model(trained_checkpoint_prefix,
use_moving_averages=False)
output_directory = os.path.join(tmp_dir, 'output')
saved_model_path = os.path.join(output_directory, 'saved_model')
with mock.patch.object(
model_builder, 'build', autospec=True) as mock_builder:
mock_builder.return_value = FakeModel(add_detection_masks=True)
pipeline_config = pipeline_pb2.TrainEvalPipelineConfig()
pipeline_config.eval_config.use_moving_averages = False
exporter.export_inference_graph(
input_type='tf_example',
pipeline_config=pipeline_config,
trained_checkpoint_prefix=trained_checkpoint_prefix,
output_directory=output_directory)
tf_example_np = np.hstack([self._create_tf_example(
np.ones((4, 4, 3)).astype(np.uint8))] * 2)
with tf.Graph().as_default() as od_graph:
with self.test_session(graph=od_graph) as sess:
meta_graph = tf.saved_model.loader.load(
sess, [tf.saved_model.tag_constants.SERVING], saved_model_path)
signature = meta_graph.signature_def['serving_default']
input_tensor_name = signature.inputs['inputs'].name
tf_example = od_graph.get_tensor_by_name(input_tensor_name)
boxes = od_graph.get_tensor_by_name(
signature.outputs['detection_boxes'].name)
scores = od_graph.get_tensor_by_name(
signature.outputs['detection_scores'].name)
classes = od_graph.get_tensor_by_name(
signature.outputs['detection_classes'].name)
masks = od_graph.get_tensor_by_name(
signature.outputs['detection_masks'].name)
num_detections = od_graph.get_tensor_by_name(
signature.outputs['num_detections'].name)
(boxes_np, scores_np, classes_np, masks_np,
num_detections_np) = sess.run(
[boxes, scores, classes, masks, num_detections],
feed_dict={tf_example: tf_example_np})
self.assertAllClose(boxes_np, [[[0.0, 0.0, 0.5, 0.5],
[0.5, 0.5, 0.8, 0.8]],
[[0.5, 0.5, 1.0, 1.0],
[0.0, 0.0, 0.0, 0.0]]])
self.assertAllClose(scores_np, [[0.7, 0.6],
[0.9, 0.0]])
self.assertAllClose(classes_np, [[1, 2],
[2, 1]])
self.assertAllClose(masks_np, np.arange(64).reshape([2, 2, 4, 4]))
self.assertAllClose(num_detections_np, [2, 1])
def main(_):
cls_model = model.Model(is_training=False)
if FLAGS.input_shape:
input_shape = [
int(dim) if dim != -1 else None
for dim in FLAGS.input_shape.split(',')
]
else:
input_shape = [None, 28, 28, 3]
exporter.export_inference_graph(FLAGS.input_type, cls_model,
FLAGS.trained_checkpoint_prefix,
FLAGS.output_directory, input_shape)
def main(_):
assert FLAGS.pipeline_config_path, '`pipeline_config_path` is missing'
assert FLAGS.trained_checkpoint_prefix, (
'`trained_checkpoint_prefix` is missing')
assert FLAGS.output_directory, '`output_directory` is missing'
pipeline_config = pipeline_pb2.TrainEvalPipelineConfig()
with tf.gfile.GFile(FLAGS.pipeline_config_path, 'r') as f:
text_format.Merge(f.read(), pipeline_config)
exporter.export_inference_graph(FLAGS.input_type, pipeline_config,
FLAGS.trained_checkpoint_prefix,
FLAGS.output_directory)
def main(_):
cls_model = model.Model(is_training=False, num_classes=CLASS_NUM)
if FLAGS.input_shape:
input_shape = [
int(dim) if dim != -1 else None
for dim in FLAGS.input_shape.split(',')
]
else:
input_shape = [None, INPUT_HEIGHT, INPUT_WIDTH, INPUT_CHANNEL]
exporter.export_inference_graph(FLAGS.input_type, cls_model,
FLAGS.checkpoint_prefix, FLAGS.output_dir,
input_shape)
def main(_):
pipeline_config = pipeline_pb2.TrainEvalPipelineConfig()
with tf.gfile.GFile(FLAGS.pipeline_config_path, 'r') as f:
text_format.Merge(f.read(), pipeline_config)
if FLAGS.input_shape:
input_shape = [
int(dim) if dim != '-1' else None
for dim in FLAGS.input_shape.split(',')
]
else:
input_shape = None
exporter.export_inference_graph(FLAGS.input_type, pipeline_config,
FLAGS.trained_checkpoint_prefix,
FLAGS.output_directory, input_shape)
def main(_):
# Specify which gpu to be used
os.environ["CUDA_VISIBLE_DEVICES"] = '1'
cls_model = model.Model(is_training=False)
if FLAGS.input_shape:
input_shape = [
int(dim) if dim != -1 else None
for dim in FLAGS.input_shape.split(',')
]
else:
input_shape = [None, None, None, 3]
exporter.export_inference_graph(FLAGS.input_type, cls_model,
FLAGS.trained_checkpoint_prefix,
FLAGS.output_directory, input_shape)
def test_export_and_run_inference_with_encoded_image_string_tensor(self):
tmp_dir = self.get_temp_dir()
trained_checkpoint_prefix = os.path.join(tmp_dir, 'model.ckpt')
self._save_checkpoint_from_mock_model(trained_checkpoint_prefix,
use_moving_averages=True)
output_directory = os.path.join(tmp_dir, 'output')
inference_graph_path = os.path.join(output_directory,
'frozen_inference_graph.pb')
with mock.patch.object(
model_builder, 'build', autospec=True) as mock_builder:
mock_builder.return_value = FakeModel(add_detection_masks=True)
pipeline_config = pipeline_pb2.TrainEvalPipelineConfig()
pipeline_config.eval_config.use_moving_averages = False
exporter.export_inference_graph(
input_type='encoded_image_string_tensor',
pipeline_config=pipeline_config,
trained_checkpoint_prefix=trained_checkpoint_prefix,
output_directory=output_directory)
inference_graph = self._load_inference_graph(inference_graph_path)
jpg_image_str = self._create_encoded_image_string(
np.ones((4, 4, 3)).astype(np.uint8), 'jpg')
png_image_str = self._create_encoded_image_string(
np.ones((4, 4, 3)).astype(np.uint8), 'png')
with self.test_session(graph=inference_graph) as sess:
image_str_tensor = inference_graph.get_tensor_by_name(
'encoded_image_string_tensor:0')
boxes = inference_graph.get_tensor_by_name('detection_boxes:0')
scores = inference_graph.get_tensor_by_name('detection_scores:0')
classes = inference_graph.get_tensor_by_name('detection_classes:0')
masks = inference_graph.get_tensor_by_name('detection_masks:0')
num_detections = inference_graph.get_tensor_by_name('num_detections:0')
for image_str in [jpg_image_str, png_image_str]:
image_str_batch_np = np.hstack([image_str]* 2)
(boxes_np, scores_np, classes_np, masks_np,
num_detections_np) = sess.run(
[boxes, scores, classes, masks, num_detections],
feed_dict={image_str_tensor: image_str_batch_np})
self.assertAllClose(boxes_np, [[[0.0, 0.0, 0.5, 0.5],
[0.5, 0.5, 0.8, 0.8]],
[[0.5, 0.5, 1.0, 1.0],
[0.0, 0.0, 0.0, 0.0]]])
self.assertAllClose(scores_np, [[0.7, 0.6],
[0.9, 0.0]])
self.assertAllClose(classes_np, [[1, 2],
[2, 1]])
self.assertAllClose(masks_np, np.arange(64).reshape([2, 2, 4, 4]))
self.assertAllClose(num_detections_np, [2, 1])
def test_export_graph_with_moving_averages(self):
tmp_dir = self.get_temp_dir()
trained_checkpoint_prefix = os.path.join(tmp_dir, 'model.ckpt')
self._save_checkpoint_from_mock_model(trained_checkpoint_prefix,
use_moving_averages=True)
output_directory = os.path.join(tmp_dir, 'output')
with mock.patch.object(
model_builder, 'build', autospec=True) as mock_builder:
mock_builder.return_value = FakeModel()
pipeline_config = pipeline_pb2.TrainEvalPipelineConfig()
pipeline_config.eval_config.use_moving_averages = True
exporter.export_inference_graph(
input_type='image_tensor',
pipeline_config=pipeline_config,
trained_checkpoint_prefix=trained_checkpoint_prefix,
output_directory=output_directory)
def main(_):
if FLAGS.input_type not in input_type:
raise ValueError("The input_type must be one from 'image_tensor' or 'inputs':{}".format(FLAGS.input_type))
if FLAGS.data_type not in types:
raise ValueError("The data_type must be one from 'uint' or float:{}".format(FLAGS.data_type))
if not os.path.exists(FLAGS.pipline_config_path):
raise FileNotFoundError("The file {} is not found".format(FLAGS.pipline_config_path))
if not os.path.exists(FLAGS.output_dict):
os.mkdir(FLAGS.output_dict)
print("Create model's save output path {}".format(FLAGS.output_dict))
exporter.export_inference_graph(input_type=FLAGS.input_type,config=FLAGS.pipline_config_path,
trained_checkpoint_prefix=FLAGS.trained_checkpoint_prefix,output_directory=FLAGS.output_dict)
def test_export_graph_with_tf_example_input(self):
tmp_dir = self.get_temp_dir()
trained_checkpoint_prefix = os.path.join(tmp_dir, 'model.ckpt')
self._save_checkpoint_from_mock_model(trained_checkpoint_prefix,
use_moving_averages=False)
with mock.patch.object(
model_builder, 'build', autospec=True) as mock_builder:
mock_builder.return_value = FakeModel()
output_directory = os.path.join(tmp_dir, 'output')
pipeline_config = pipeline_pb2.TrainEvalPipelineConfig()
pipeline_config.eval_config.use_moving_averages = False
exporter.export_inference_graph(
input_type='tf_example',
pipeline_config=pipeline_config,
trained_checkpoint_prefix=trained_checkpoint_prefix,
output_directory=output_directory)
self.assertTrue(os.path.exists(os.path.join(
output_directory, 'saved_model', 'saved_model.pb')))
def test_raise_runtime_error_on_images_with_different_sizes(self):
tmp_dir = self.get_temp_dir()
trained_checkpoint_prefix = os.path.join(tmp_dir, 'model.ckpt')
self._save_checkpoint_from_mock_model(trained_checkpoint_prefix,
use_moving_averages=True)
output_directory = os.path.join(tmp_dir, 'output')
inference_graph_path = os.path.join(output_directory,
'frozen_inference_graph.pb')
with mock.patch.object(model_builder, 'build',
autospec=True) as mock_builder:
mock_builder.return_value = FakeModel(add_detection_masks=True)
pipeline_config = pipeline_pb2.TrainEvalPipelineConfig()
pipeline_config.eval_config.use_moving_averages = False
exporter.export_inference_graph(
input_type='encoded_image_string_tensor',
pipeline_config=pipeline_config,
trained_checkpoint_prefix=trained_checkpoint_prefix,
output_directory=output_directory)
inference_graph = self._load_inference_graph(inference_graph_path)
large_image = self._create_encoded_image_string(
np.ones((4, 4, 3)).astype(np.uint8), 'jpg')
small_image = self._create_encoded_image_string(
np.ones((2, 2, 3)).astype(np.uint8), 'jpg')
image_str_batch_np = np.hstack([large_image, small_image])
with self.test_session(graph=inference_graph) as sess:
image_str_tensor = inference_graph.get_tensor_by_name(
'encoded_image_string_tensor:0')
boxes = inference_graph.get_tensor_by_name('detection_boxes:0')
scores = inference_graph.get_tensor_by_name('detection_scores:0')
classes = inference_graph.get_tensor_by_name('detection_classes:0')
masks = inference_graph.get_tensor_by_name('detection_masks:0')
num_detections = inference_graph.get_tensor_by_name(
'num_detections:0')
with self.assertRaisesRegexp(
tf.errors.InvalidArgumentError,
'^TensorArray has inconsistent shapes.'):
sess.run([boxes, scores, classes, masks, num_detections],
feed_dict={image_str_tensor: image_str_batch_np})
def test_export_graph_with_moving_averages(self):
tmp_dir = self.get_temp_dir()
trained_checkpoint_prefix = os.path.join(tmp_dir, 'model.ckpt')
self._save_checkpoint_from_mock_model(trained_checkpoint_prefix,
use_moving_averages=True)
output_directory = os.path.join(tmp_dir, 'output')
with mock.patch.object(
model_builder, 'build', autospec=True) as mock_builder:
mock_builder.return_value = FakeModel()
pipeline_config = pipeline_pb2.TrainEvalPipelineConfig()
pipeline_config.eval_config.use_moving_averages = True
exporter.export_inference_graph(
input_type='image_tensor',
pipeline_config=pipeline_config,
trained_checkpoint_prefix=trained_checkpoint_prefix,
output_directory=output_directory)
self.assertTrue(os.path.exists(os.path.join(
output_directory, 'saved_model', 'saved_model.pb')))
expected_variables = set(['conv2d/bias', 'conv2d/kernel', 'global_step'])
actual_variables = set(
[var_name for var_name, _ in tf.train.list_variables(output_directory)])
self.assertTrue(expected_variables.issubset(actual_variables))
def main(_):
pipeline_config = pipeline_pb2.TrainEvalPipelineConfig()
with tf.gfile.GFile(FLAGS.pipeline_config_path, 'r') as f:
text_format.Merge(f.read(), pipeline_config)
text_format.Merge(FLAGS.config_override, pipeline_config)
if FLAGS.input_shape:
input_shape = [
int(dim) if dim != '-1' else None
for dim in FLAGS.input_shape.split(',')
]
else:
input_shape = None
if FLAGS.use_side_inputs:
side_input_shapes, side_input_names, side_input_types = (
exporter.parse_side_inputs(FLAGS.side_input_shapes,
FLAGS.side_input_names,
FLAGS.side_input_types))
else:
side_input_shapes = None
side_input_names = None
side_input_types = None
if FLAGS.additional_output_tensor_names:
additional_output_tensor_names = list(
FLAGS.additional_output_tensor_names.split(','))
else:
additional_output_tensor_names = None
exporter.export_inference_graph(
FLAGS.input_type,
pipeline_config,
FLAGS.trained_checkpoint_prefix,
FLAGS.output_directory,
input_shape=input_shape,
write_inference_graph=FLAGS.write_inference_graph,
additional_output_tensor_names=additional_output_tensor_names,
use_side_inputs=FLAGS.use_side_inputs,
side_input_shapes=side_input_shapes,
side_input_names=side_input_names,
side_input_types=side_input_types)
def main(_):
# 选择要使用的硬件
# os.environ['CUDA_VISIBLE_DEVICES'] = '1'
original_image_size = (480, 640)
model_image_size = (240, 320)
class_model = model.Model(num_classes=10,
is_training=False,
fixed_resize_side_min=300,
default_image_height=model_image_size[0],
default_image_width=model_image_size[1])
input_shape = [None, None, None, 3]
input_type = 'image_tensor'
ckpt_name = 'model.ckpt-3901'
ckpt_name = 'model.ckpt-29878'
out_dir = r"E:\tmp\data\state-farm-distracted-driver-detection\output"
logs_dir = os.path.join(out_dir, "logs")
trained_checkpoint_prefix = os.path.join(logs_dir, ckpt_name)
exporter.export_inference_graph(input_type,
class_model,
trained_checkpoint_prefix,
output_directory=out_dir,
input_shape=input_shape)
def test_export_graph_saves_pipeline_file(self):
tmp_dir = self.get_temp_dir()
trained_checkpoint_prefix = os.path.join(tmp_dir, 'model.ckpt')
self._save_checkpoint_from_mock_model(trained_checkpoint_prefix,
use_moving_averages=True)
output_directory = os.path.join(tmp_dir, 'output')
with mock.patch.object(
model_builder, 'build', autospec=True) as mock_builder:
mock_builder.return_value = FakeModel()
pipeline_config = pipeline_pb2.TrainEvalPipelineConfig()
exporter.export_inference_graph(
input_type='image_tensor',
pipeline_config=pipeline_config,
trained_checkpoint_prefix=trained_checkpoint_prefix,
output_directory=output_directory)
expected_pipeline_path = os.path.join(
output_directory, 'pipeline.config')
self.assertTrue(os.path.exists(expected_pipeline_path))
written_pipeline_config = pipeline_pb2.TrainEvalPipelineConfig()
with tf.gfile.GFile(expected_pipeline_path, 'r') as f:
proto_str = f.read()
text_format.Merge(proto_str, written_pipeline_config)
self.assertProtoEquals(pipeline_config, written_pipeline_config)
