def testInstancesNotAvailableByDefault(self):
num_instances = 4
image_height = 5
image_width = 3
# Randomly generate image.
image_tensor = np.random.randint(255, size=(image_height,
image_width,
3)).astype(np.uint8)
encoded_jpeg = self._EncodeImage(image_tensor)
# Randomly generate instance segmentation masks.
instance_masks = (
np.random.randint(2, size=(num_instances,
image_height,
image_width)).astype(np.float32))
instance_masks_flattened = np.reshape(instance_masks, [-1])
# Randomly generate class labels for each instance.
object_classes = np.random.randint(
100, size=(num_instances)).astype(np.int64)
example = tf.train.Example(features=tf.train.Features(feature={
'image/encoded': self._BytesFeature(encoded_jpeg),
'image/format': self._BytesFeature('jpeg'),
'image/height': self._Int64Feature([image_height]),
'image/width': self._Int64Feature([image_width]),
'image/object/mask': self._FloatFeature(instance_masks_flattened),
'image/object/class/label': self._Int64Feature(
object_classes)})).SerializeToString()
example_decoder = tf_example_decoder.TfExampleDecoder()
tensor_dict = example_decoder.decode(tf.convert_to_tensor(example))
self.assertTrue(fields.InputDataFields.groundtruth_instance_masks
not in tensor_dict)
def testDecodeBoundingBox(self):
image_tensor = np.random.randint(255, size=(4, 5, 3)).astype(np.uint8)
encoded_jpeg = self._EncodeImage(image_tensor)
bbox_ymins = [0.0, 4.0]
bbox_xmins = [1.0, 5.0]
bbox_ymaxs = [2.0, 6.0]
bbox_xmaxs = [3.0, 7.0]
example = tf.train.Example(features=tf.train.Features(feature={
'image/encoded': self._BytesFeature(encoded_jpeg),
'image/format': self._BytesFeature('jpeg'),
'image/object/bbox/ymin': self._FloatFeature(bbox_ymins),
'image/object/bbox/xmin': self._FloatFeature(bbox_xmins),
'image/object/bbox/ymax': self._FloatFeature(bbox_ymaxs),
'image/object/bbox/xmax': self._FloatFeature(bbox_xmaxs),
})).SerializeToString()
example_decoder = tf_example_decoder.TfExampleDecoder()
tensor_dict = example_decoder.decode(tf.convert_to_tensor(example))
self.assertAllEqual((tensor_dict[fields.InputDataFields.groundtruth_boxes].
get_shape().as_list()), [None, 4])
with self.test_session() as sess:
tensor_dict = sess.run(tensor_dict)
expected_boxes = np.vstack([bbox_ymins, bbox_xmins,
bbox_ymaxs, bbox_xmaxs]).transpose()
self.assertAllEqual(expected_boxes,
tensor_dict[fields.InputDataFields.groundtruth_boxes])
def testDecodeInstanceSegmentation(self):
num_instances = 4
image_height = 5
image_width = 3
# Randomly generate image.
image_tensor = np.random.randint(255, size=(image_height,
image_width,
3)).astype(np.uint8)
encoded_jpeg = self._EncodeImage(image_tensor)
# Randomly generate instance segmentation masks.
instance_masks = (
np.random.randint(2, size=(num_instances,
image_height,
image_width)).astype(np.float32))
instance_masks_flattened = np.reshape(instance_masks, [-1])
# Randomly generate class labels for each instance.
object_classes = np.random.randint(
100, size=(num_instances)).astype(np.int64)
example = tf.train.Example(features=tf.train.Features(feature={
'image/encoded': self._BytesFeature(encoded_jpeg),
'image/format': self._BytesFeature('jpeg'),
'image/height': self._Int64Feature([image_height]),
'image/width': self._Int64Feature([image_width]),
'image/object/mask': self._FloatFeature(instance_masks_flattened),
'image/object/class/label': self._Int64Feature(
object_classes)})).SerializeToString()
example_decoder = tf_example_decoder.TfExampleDecoder(
load_instance_masks=True)
tensor_dict = example_decoder.decode(tf.convert_to_tensor(example))
self.assertAllEqual((
tensor_dict[fields.InputDataFields.groundtruth_instance_masks].
get_shape().as_list()), [None, None, None])
self.assertAllEqual((
tensor_dict[fields.InputDataFields.groundtruth_classes].
get_shape().as_list()), [None])
with self.test_session() as sess:
tensor_dict = sess.run(tensor_dict)
self.assertAllEqual(
instance_masks.astype(np.float32),
tensor_dict[fields.InputDataFields.groundtruth_instance_masks])
self.assertAllEqual(
object_classes,
tensor_dict[fields.InputDataFields.groundtruth_classes])
def testDecodeImageKeyAndFilename(self):
image_tensor = np.random.randint(255, size=(4, 5, 3)).astype(np.uint8)
encoded_jpeg = self._EncodeImage(image_tensor)
example = tf.train.Example(features=tf.train.Features(feature={
'image/encoded': self._BytesFeature(encoded_jpeg),
'image/key/sha256': self._BytesFeature('abc'),
'image/filename': self._BytesFeature('filename')
})).SerializeToString()
example_decoder = tf_example_decoder.TfExampleDecoder()
tensor_dict = example_decoder.decode(tf.convert_to_tensor(example))
with self.test_session() as sess:
tensor_dict = sess.run(tensor_dict)
self.assertEqual('abc', tensor_dict[fields.InputDataFields.key])
self.assertEqual('filename', tensor_dict[fields.InputDataFields.filename])
def build(input_reader_config):
"""Builds a tensor dictionary based on the InputReader config.
Args:
input_reader_config: A input_reader_pb2.InputReader object.
Returns:
A tensor dict based on the input_reader_config.
Raises:
ValueError: On invalid input reader proto.
ValueError: If no input paths are specified.
"""
if not isinstance(input_reader_config, input_reader_pb2.InputReader):
raise ValueError('input_reader_config not of type '
'input_reader_pb2.InputReader.')
if input_reader_config.WhichOneof(
'input_reader') == 'tf_record_input_reader':
config = input_reader_config.tf_record_input_reader
if not config.input_path:
raise ValueError('At least one input path must be specified in '
'`input_reader_config`.')
_, string_tensor = parallel_reader.parallel_read(
config.input_path[:], # Convert `RepeatedScalarContainer` to list.
reader_class=tf.TFRecordReader,
num_epochs=(input_reader_config.num_epochs
if input_reader_config.num_epochs else None),
num_readers=input_reader_config.num_readers,
shuffle=input_reader_config.shuffle,
dtypes=[tf.string, tf.string],
capacity=input_reader_config.queue_capacity,
min_after_dequeue=input_reader_config.min_after_dequeue)
label_map_proto_file = None
if input_reader_config.HasField('label_map_path'):
label_map_proto_file = input_reader_config.label_map_path
decoder = tf_example_decoder.TfExampleDecoder(
load_instance_masks=input_reader_config.load_instance_masks,
label_map_proto_file=label_map_proto_file)
return decoder.decode(string_tensor)
raise ValueError('Unsupported input_reader_config.')
def testDecodePngImage(self):
image_tensor = np.random.randint(255, size=(4, 5, 3)).astype(np.uint8)
encoded_png = self._EncodeImage(image_tensor, encoding_type='png')
decoded_png = self._DecodeImage(encoded_png, encoding_type='png')
example = tf.train.Example(features=tf.train.Features(feature={
'image/encoded': self._BytesFeature(encoded_png),
'image/format': self._BytesFeature('png'),
'image/source_id': self._BytesFeature('image_id')
})).SerializeToString()
example_decoder = tf_example_decoder.TfExampleDecoder()
tensor_dict = example_decoder.decode(tf.convert_to_tensor(example))
self.assertAllEqual((tensor_dict[fields.InputDataFields.image].
get_shape().as_list()), [None, None, 3])
with self.test_session() as sess:
tensor_dict = sess.run(tensor_dict)
self.assertAllEqual(decoded_png, tensor_dict[fields.InputDataFields.image])
self.assertEqual('image_id', tensor_dict[fields.InputDataFields.source_id])
def testDecodeObjectArea(self):
image_tensor = np.random.randint(255, size=(4, 5, 3)).astype(np.uint8)
encoded_jpeg = self._EncodeImage(image_tensor)
object_area = [100., 174.]
example = tf.train.Example(features=tf.train.Features(feature={
'image/encoded': self._BytesFeature(encoded_jpeg),
'image/format': self._BytesFeature('jpeg'),
'image/object/area': self._FloatFeature(object_area),
})).SerializeToString()
example_decoder = tf_example_decoder.TfExampleDecoder()
tensor_dict = example_decoder.decode(tf.convert_to_tensor(example))
self.assertAllEqual((tensor_dict[fields.InputDataFields.groundtruth_area].
get_shape().as_list()), [None])
with self.test_session() as sess:
tensor_dict = sess.run(tensor_dict)
self.assertAllEqual(object_area,
tensor_dict[fields.InputDataFields.groundtruth_area])
def testDecodeObjectDifficult(self):
image_tensor = np.random.randint(255, size=(4, 5, 3)).astype(np.uint8)
encoded_jpeg = self._EncodeImage(image_tensor)
object_difficult = [0, 1]
example = tf.train.Example(features=tf.train.Features(feature={
'image/encoded': self._BytesFeature(encoded_jpeg),
'image/format': self._BytesFeature('jpeg'),
'image/object/difficult': self._Int64Feature(object_difficult),
})).SerializeToString()
example_decoder = tf_example_decoder.TfExampleDecoder()
tensor_dict = example_decoder.decode(tf.convert_to_tensor(example))
self.assertAllEqual((tensor_dict[
fields.InputDataFields.groundtruth_difficult].get_shape().as_list()),
[None])
with self.test_session() as sess:
tensor_dict = sess.run(tensor_dict)
self.assertAllEqual([bool(item) for item in object_difficult],
tensor_dict[
fields.InputDataFields.groundtruth_difficult])
def decode(tf_example_string_tensor):
tensor_dict = tf_example_decoder.TfExampleDecoder().decode(
tf_example_string_tensor)
image_tensor = tensor_dict[fields.InputDataFields.image]
return image_tensor
