Python object_detection.utils.dataset_util.bytes_list_feature() Examples
The following are 30
code examples of object_detection.utils.dataset_util.bytes_list_feature().
You can vote up the ones you like or vote down the ones you don't like,
and go to the original project or source file by following the links above each example.
You may also want to check out all available functions/classes of the module
object_detection.utils.dataset_util
, or try the search function
.
.
Example #1
| Source File: dataset_builder_test.py From g-tensorflow-models with Apache License 2.0 | 5 votes |
|
def create_tf_record(self, has_additional_channels=False, num_examples=1):
path = os.path.join(self.get_temp_dir(), 'tfrecord')
writer = tf.python_io.TFRecordWriter(path)
image_tensor = np.random.randint(255, size=(4, 5, 3)).astype(np.uint8)
additional_channels_tensor = np.random.randint(
255, size=(4, 5, 1)).astype(np.uint8)
flat_mask = (4 * 5) * [1.0]
with self.test_session():
encoded_jpeg = tf.image.encode_jpeg(tf.constant(image_tensor)).eval()
encoded_additional_channels_jpeg = tf.image.encode_jpeg(
tf.constant(additional_channels_tensor)).eval()
for i in range(num_examples):
features = {
'image/source_id': dataset_util.bytes_feature(str(i)),
'image/encoded': dataset_util.bytes_feature(encoded_jpeg),
'image/format': dataset_util.bytes_feature('jpeg'.encode('utf8')),
'image/height': dataset_util.int64_feature(4),
'image/width': dataset_util.int64_feature(5),
'image/object/bbox/xmin': dataset_util.float_list_feature([0.0]),
'image/object/bbox/xmax': dataset_util.float_list_feature([1.0]),
'image/object/bbox/ymin': dataset_util.float_list_feature([0.0]),
'image/object/bbox/ymax': dataset_util.float_list_feature([1.0]),
'image/object/class/label': dataset_util.int64_list_feature([2]),
'image/object/mask': dataset_util.float_list_feature(flat_mask),
}
if has_additional_channels:
additional_channels_key = 'image/additional_channels/encoded'
features[additional_channels_key] = dataset_util.bytes_list_feature(
[encoded_additional_channels_jpeg] * 2)
example = tf.train.Example(features=tf.train.Features(feature=features))
writer.write(example.SerializeToString())
writer.close()
return path
Example #2
| Source File: tf_example_decoder_test.py From MAX-Object-Detector with Apache License 2.0 | 5 votes |
|
def testDecodeAdditionalChannels(self):
image_tensor = np.random.randint(256, size=(4, 5, 3)).astype(np.uint8)
encoded_jpeg = self._EncodeImage(image_tensor)
additional_channel_tensor = np.random.randint(
256, size=(4, 5, 1)).astype(np.uint8)
encoded_additional_channel = self._EncodeImage(additional_channel_tensor)
decoded_additional_channel = self._DecodeImage(encoded_additional_channel)
example = tf.train.Example(
features=tf.train.Features(
feature={
'image/encoded':
dataset_util.bytes_feature(encoded_jpeg),
'image/additional_channels/encoded':
dataset_util.bytes_list_feature(
[encoded_additional_channel] * 2),
'image/format':
dataset_util.bytes_feature('jpeg'),
'image/source_id':
dataset_util.bytes_feature('image_id'),
})).SerializeToString()
example_decoder = tf_example_decoder.TfExampleDecoder(
num_additional_channels=2)
tensor_dict = example_decoder.decode(tf.convert_to_tensor(example))
with self.test_session() as sess:
tensor_dict = sess.run(tensor_dict)
self.assertAllEqual(
np.concatenate([decoded_additional_channel] * 2, axis=2),
tensor_dict[fields.InputDataFields.image_additional_channels])
Example #3
| Source File: tf_example_decoder_test.py From MAX-Object-Detector with Apache License 2.0 | 5 votes |
|
def testDecodePngInstanceMasks(self):
image_tensor = np.random.randint(256, size=(10, 10, 3)).astype(np.uint8)
encoded_jpeg = self._EncodeImage(image_tensor)
mask_1 = np.random.randint(0, 2, size=(10, 10, 1)).astype(np.uint8)
mask_2 = np.random.randint(0, 2, size=(10, 10, 1)).astype(np.uint8)
encoded_png_1 = self._EncodeImage(mask_1, encoding_type='png')
decoded_png_1 = np.squeeze(mask_1.astype(np.float32))
encoded_png_2 = self._EncodeImage(mask_2, encoding_type='png')
decoded_png_2 = np.squeeze(mask_2.astype(np.float32))
encoded_masks = [encoded_png_1, encoded_png_2]
decoded_masks = np.stack([decoded_png_1, decoded_png_2])
example = tf.train.Example(
features=tf.train.Features(
feature={
'image/encoded':
dataset_util.bytes_feature(encoded_jpeg),
'image/format':
dataset_util.bytes_feature('jpeg'),
'image/object/mask':
dataset_util.bytes_list_feature(encoded_masks)
})).SerializeToString()
example_decoder = tf_example_decoder.TfExampleDecoder(
load_instance_masks=True, instance_mask_type=input_reader_pb2.PNG_MASKS)
tensor_dict = example_decoder.decode(tf.convert_to_tensor(example))
with self.test_session() as sess:
tensor_dict = sess.run(tensor_dict)
self.assertAllEqual(
decoded_masks,
tensor_dict[fields.InputDataFields.groundtruth_instance_masks])
Example #4
| Source File: tf_example_decoder_test.py From MAX-Object-Detector with Apache License 2.0 | 5 votes |
|
def testDecodeEmptyPngInstanceMasks(self):
image_tensor = np.random.randint(256, size=(10, 10, 3)).astype(np.uint8)
encoded_jpeg = self._EncodeImage(image_tensor)
encoded_masks = []
example = tf.train.Example(
features=tf.train.Features(
feature={
'image/encoded':
dataset_util.bytes_feature(encoded_jpeg),
'image/format':
dataset_util.bytes_feature('jpeg'),
'image/object/mask':
dataset_util.bytes_list_feature(encoded_masks),
'image/height':
dataset_util.int64_feature(10),
'image/width':
dataset_util.int64_feature(10),
})).SerializeToString()
example_decoder = tf_example_decoder.TfExampleDecoder(
load_instance_masks=True, instance_mask_type=input_reader_pb2.PNG_MASKS)
tensor_dict = example_decoder.decode(tf.convert_to_tensor(example))
with self.test_session() as sess:
tensor_dict = sess.run(tensor_dict)
self.assertAllEqual(
tensor_dict[fields.InputDataFields.groundtruth_instance_masks].shape,
[0, 10, 10])
Example #5
| Source File: tf_example_decoder_test.py From MAX-Object-Detector with Apache License 2.0 | 5 votes |
|
def testDecodeObjectLabelUnrecognizedName(self):
image_tensor = np.random.randint(256, size=(4, 5, 3)).astype(np.uint8)
encoded_jpeg = self._EncodeImage(image_tensor)
bbox_classes_text = ['cat', 'cheetah']
example = tf.train.Example(
features=tf.train.Features(
feature={
'image/encoded':
dataset_util.bytes_feature(encoded_jpeg),
'image/format':
dataset_util.bytes_feature('jpeg'),
'image/object/class/text':
dataset_util.bytes_list_feature(bbox_classes_text),
})).SerializeToString()
label_map_string = """
item {
id:2
name:'cat'
}
item {
id:1
name:'dog'
}
"""
label_map_path = os.path.join(self.get_temp_dir(), 'label_map.pbtxt')
with tf.gfile.Open(label_map_path, 'wb') as f:
f.write(label_map_string)
example_decoder = tf_example_decoder.TfExampleDecoder(
label_map_proto_file=label_map_path)
tensor_dict = example_decoder.decode(tf.convert_to_tensor(example))
self.assertAllEqual((tensor_dict[fields.InputDataFields.groundtruth_classes]
.get_shape().as_list()), [None])
with self.test_session() as sess:
sess.run(tf.tables_initializer())
tensor_dict = sess.run(tensor_dict)
self.assertAllEqual([2, -1],
tensor_dict[fields.InputDataFields.groundtruth_classes])
Example #6
| Source File: tf_example_decoder_test.py From MAX-Object-Detector with Apache License 2.0 | 5 votes |
|
def testDecodeObjectLabelWithMappingWithDisplayName(self):
image_tensor = np.random.randint(256, size=(4, 5, 3)).astype(np.uint8)
encoded_jpeg = self._EncodeImage(image_tensor)
bbox_classes_text = ['cat', 'dog']
example = tf.train.Example(
features=tf.train.Features(
feature={
'image/encoded':
dataset_util.bytes_feature(encoded_jpeg),
'image/format':
dataset_util.bytes_feature('jpeg'),
'image/object/class/text':
dataset_util.bytes_list_feature(bbox_classes_text),
})).SerializeToString()
label_map_string = """
item {
id:3
display_name:'cat'
}
item {
id:1
display_name:'dog'
}
"""
label_map_path = os.path.join(self.get_temp_dir(), 'label_map.pbtxt')
with tf.gfile.Open(label_map_path, 'wb') as f:
f.write(label_map_string)
example_decoder = tf_example_decoder.TfExampleDecoder(
label_map_proto_file=label_map_path)
tensor_dict = example_decoder.decode(tf.convert_to_tensor(example))
self.assertAllEqual((tensor_dict[fields.InputDataFields.groundtruth_classes]
.get_shape().as_list()), [None])
with self.test_session() as sess:
sess.run(tf.tables_initializer())
tensor_dict = sess.run(tensor_dict)
self.assertAllEqual([3, 1],
tensor_dict[fields.InputDataFields.groundtruth_classes])
Example #7
| Source File: dataset_builder_test.py From MAX-Object-Detector with Apache License 2.0 | 5 votes |
|
def create_tf_record(self, has_additional_channels=False, num_examples=1):
path = os.path.join(self.get_temp_dir(), 'tfrecord')
writer = tf.python_io.TFRecordWriter(path)
image_tensor = np.random.randint(255, size=(4, 5, 3)).astype(np.uint8)
additional_channels_tensor = np.random.randint(
255, size=(4, 5, 1)).astype(np.uint8)
flat_mask = (4 * 5) * [1.0]
with self.test_session():
encoded_jpeg = tf.image.encode_jpeg(tf.constant(image_tensor)).eval()
encoded_additional_channels_jpeg = tf.image.encode_jpeg(
tf.constant(additional_channels_tensor)).eval()
for i in range(num_examples):
features = {
'image/source_id': dataset_util.bytes_feature(str(i)),
'image/encoded': dataset_util.bytes_feature(encoded_jpeg),
'image/format': dataset_util.bytes_feature('jpeg'.encode('utf8')),
'image/height': dataset_util.int64_feature(4),
'image/width': dataset_util.int64_feature(5),
'image/object/bbox/xmin': dataset_util.float_list_feature([0.0]),
'image/object/bbox/xmax': dataset_util.float_list_feature([1.0]),
'image/object/bbox/ymin': dataset_util.float_list_feature([0.0]),
'image/object/bbox/ymax': dataset_util.float_list_feature([1.0]),
'image/object/class/label': dataset_util.int64_list_feature([2]),
'image/object/mask': dataset_util.float_list_feature(flat_mask),
}
if has_additional_channels:
additional_channels_key = 'image/additional_channels/encoded'
features[additional_channels_key] = dataset_util.bytes_list_feature(
[encoded_additional_channels_jpeg] * 2)
example = tf.train.Example(features=tf.train.Features(feature=features))
writer.write(example.SerializeToString())
writer.close()
return path
Example #8
| Source File: tf_example_decoder_test.py From g-tensorflow-models with Apache License 2.0 | 5 votes |
|
def testDecodeAdditionalChannels(self):
image_tensor = np.random.randint(256, size=(4, 5, 3)).astype(np.uint8)
encoded_jpeg = self._EncodeImage(image_tensor)
additional_channel_tensor = np.random.randint(
256, size=(4, 5, 1)).astype(np.uint8)
encoded_additional_channel = self._EncodeImage(additional_channel_tensor)
decoded_additional_channel = self._DecodeImage(encoded_additional_channel)
example = tf.train.Example(
features=tf.train.Features(
feature={
'image/encoded':
dataset_util.bytes_feature(encoded_jpeg),
'image/additional_channels/encoded':
dataset_util.bytes_list_feature(
[encoded_additional_channel] * 2),
'image/format':
dataset_util.bytes_feature('jpeg'),
'image/source_id':
dataset_util.bytes_feature('image_id'),
})).SerializeToString()
example_decoder = tf_example_decoder.TfExampleDecoder(
num_additional_channels=2)
tensor_dict = example_decoder.decode(tf.convert_to_tensor(example))
with self.test_session() as sess:
tensor_dict = sess.run(tensor_dict)
self.assertAllEqual(
np.concatenate([decoded_additional_channel] * 2, axis=2),
tensor_dict[fields.InputDataFields.image_additional_channels])
Example #9
| Source File: tf_example_decoder_test.py From g-tensorflow-models with Apache License 2.0 | 5 votes |
|
def testDecodePngInstanceMasks(self):
image_tensor = np.random.randint(256, size=(10, 10, 3)).astype(np.uint8)
encoded_jpeg = self._EncodeImage(image_tensor)
mask_1 = np.random.randint(0, 2, size=(10, 10, 1)).astype(np.uint8)
mask_2 = np.random.randint(0, 2, size=(10, 10, 1)).astype(np.uint8)
encoded_png_1 = self._EncodeImage(mask_1, encoding_type='png')
decoded_png_1 = np.squeeze(mask_1.astype(np.float32))
encoded_png_2 = self._EncodeImage(mask_2, encoding_type='png')
decoded_png_2 = np.squeeze(mask_2.astype(np.float32))
encoded_masks = [encoded_png_1, encoded_png_2]
decoded_masks = np.stack([decoded_png_1, decoded_png_2])
example = tf.train.Example(
features=tf.train.Features(
feature={
'image/encoded':
dataset_util.bytes_feature(encoded_jpeg),
'image/format':
dataset_util.bytes_feature('jpeg'),
'image/object/mask':
dataset_util.bytes_list_feature(encoded_masks)
})).SerializeToString()
example_decoder = tf_example_decoder.TfExampleDecoder(
load_instance_masks=True, instance_mask_type=input_reader_pb2.PNG_MASKS)
tensor_dict = example_decoder.decode(tf.convert_to_tensor(example))
with self.test_session() as sess:
tensor_dict = sess.run(tensor_dict)
self.assertAllEqual(
decoded_masks,
tensor_dict[fields.InputDataFields.groundtruth_instance_masks])
Example #10
| Source File: tf_example_decoder_test.py From g-tensorflow-models with Apache License 2.0 | 5 votes |
|
def testDecodeEmptyPngInstanceMasks(self):
image_tensor = np.random.randint(256, size=(10, 10, 3)).astype(np.uint8)
encoded_jpeg = self._EncodeImage(image_tensor)
encoded_masks = []
example = tf.train.Example(
features=tf.train.Features(
feature={
'image/encoded':
dataset_util.bytes_feature(encoded_jpeg),
'image/format':
dataset_util.bytes_feature('jpeg'),
'image/object/mask':
dataset_util.bytes_list_feature(encoded_masks),
'image/height':
dataset_util.int64_feature(10),
'image/width':
dataset_util.int64_feature(10),
})).SerializeToString()
example_decoder = tf_example_decoder.TfExampleDecoder(
load_instance_masks=True, instance_mask_type=input_reader_pb2.PNG_MASKS)
tensor_dict = example_decoder.decode(tf.convert_to_tensor(example))
with self.test_session() as sess:
tensor_dict = sess.run(tensor_dict)
self.assertAllEqual(
tensor_dict[fields.InputDataFields.groundtruth_instance_masks].shape,
[0, 10, 10])
Example #11
| Source File: tf_example_decoder_test.py From g-tensorflow-models with Apache License 2.0 | 5 votes |
|
def testDecodeObjectLabelUnrecognizedName(self):
image_tensor = np.random.randint(256, size=(4, 5, 3)).astype(np.uint8)
encoded_jpeg = self._EncodeImage(image_tensor)
bbox_classes_text = ['cat', 'cheetah']
example = tf.train.Example(
features=tf.train.Features(
feature={
'image/encoded':
dataset_util.bytes_feature(encoded_jpeg),
'image/format':
dataset_util.bytes_feature('jpeg'),
'image/object/class/text':
dataset_util.bytes_list_feature(bbox_classes_text),
})).SerializeToString()
label_map_string = """
item {
id:2
name:'cat'
}
item {
id:1
name:'dog'
}
"""
label_map_path = os.path.join(self.get_temp_dir(), 'label_map.pbtxt')
with tf.gfile.Open(label_map_path, 'wb') as f:
f.write(label_map_string)
example_decoder = tf_example_decoder.TfExampleDecoder(
label_map_proto_file=label_map_path)
tensor_dict = example_decoder.decode(tf.convert_to_tensor(example))
self.assertAllEqual((tensor_dict[fields.InputDataFields.groundtruth_classes]
.get_shape().as_list()), [None])
with self.test_session() as sess:
sess.run(tf.tables_initializer())
tensor_dict = sess.run(tensor_dict)
self.assertAllEqual([2, -1],
tensor_dict[fields.InputDataFields.groundtruth_classes])
Example #12
| Source File: tf_example_decoder_test.py From g-tensorflow-models with Apache License 2.0 | 5 votes |
|
def testDecodeObjectLabelWithMappingWithDisplayName(self):
image_tensor = np.random.randint(256, size=(4, 5, 3)).astype(np.uint8)
encoded_jpeg = self._EncodeImage(image_tensor)
bbox_classes_text = ['cat', 'dog']
example = tf.train.Example(
features=tf.train.Features(
feature={
'image/encoded':
dataset_util.bytes_feature(encoded_jpeg),
'image/format':
dataset_util.bytes_feature('jpeg'),
'image/object/class/text':
dataset_util.bytes_list_feature(bbox_classes_text),
})).SerializeToString()
label_map_string = """
item {
id:3
display_name:'cat'
}
item {
id:1
display_name:'dog'
}
"""
label_map_path = os.path.join(self.get_temp_dir(), 'label_map.pbtxt')
with tf.gfile.Open(label_map_path, 'wb') as f:
f.write(label_map_string)
example_decoder = tf_example_decoder.TfExampleDecoder(
label_map_proto_file=label_map_path)
tensor_dict = example_decoder.decode(tf.convert_to_tensor(example))
self.assertAllEqual((tensor_dict[fields.InputDataFields.groundtruth_classes]
.get_shape().as_list()), [None])
with self.test_session() as sess:
sess.run(tf.tables_initializer())
tensor_dict = sess.run(tensor_dict)
self.assertAllEqual([3, 1],
tensor_dict[fields.InputDataFields.groundtruth_classes])
Example #13
| Source File: tf_example_decoder_test.py From vehicle_counting_tensorflow with MIT License | 5 votes |
|
def testDecodePngInstanceMasks(self):
image_tensor = np.random.randint(256, size=(10, 10, 3)).astype(np.uint8)
encoded_jpeg = self._EncodeImage(image_tensor)
mask_1 = np.random.randint(0, 2, size=(10, 10, 1)).astype(np.uint8)
mask_2 = np.random.randint(0, 2, size=(10, 10, 1)).astype(np.uint8)
encoded_png_1 = self._EncodeImage(mask_1, encoding_type='png')
decoded_png_1 = np.squeeze(mask_1.astype(np.float32))
encoded_png_2 = self._EncodeImage(mask_2, encoding_type='png')
decoded_png_2 = np.squeeze(mask_2.astype(np.float32))
encoded_masks = [encoded_png_1, encoded_png_2]
decoded_masks = np.stack([decoded_png_1, decoded_png_2])
example = tf.train.Example(
features=tf.train.Features(
feature={
'image/encoded':
dataset_util.bytes_feature(encoded_jpeg),
'image/format':
dataset_util.bytes_feature('jpeg'),
'image/object/mask':
dataset_util.bytes_list_feature(encoded_masks)
})).SerializeToString()
example_decoder = tf_example_decoder.TfExampleDecoder(
load_instance_masks=True, instance_mask_type=input_reader_pb2.PNG_MASKS)
tensor_dict = example_decoder.decode(tf.convert_to_tensor(example))
with self.test_session() as sess:
tensor_dict = sess.run(tensor_dict)
self.assertAllEqual(
decoded_masks,
tensor_dict[fields.InputDataFields.groundtruth_instance_masks])
Example #14
| Source File: tf_example_decoder_test.py From models with Apache License 2.0 | 5 votes |
|
def testDecodeAdditionalChannels(self):
image = np.random.randint(256, size=(4, 5, 3)).astype(np.uint8)
encoded_jpeg, _ = self._create_encoded_and_decoded_data(image, 'jpeg')
additional_channel = np.random.randint(256, size=(4, 5, 1)).astype(np.uint8)
(encoded_additional_channel,
decoded_additional_channel) = self._create_encoded_and_decoded_data(
additional_channel, 'jpeg')
def graph_fn():
example = tf.train.Example(
features=tf.train.Features(
feature={
'image/encoded':
dataset_util.bytes_feature(encoded_jpeg),
'image/additional_channels/encoded':
dataset_util.bytes_list_feature(
[encoded_additional_channel] * 2),
'image/format':
dataset_util.bytes_feature(six.b('jpeg')),
'image/source_id':
dataset_util.bytes_feature(six.b('image_id')),
})).SerializeToString()
example_decoder = tf_example_decoder.TfExampleDecoder(
num_additional_channels=2)
return example_decoder.decode(tf.convert_to_tensor(example))
tensor_dict = self.execute_cpu(graph_fn, [])
self.assertAllEqual(
np.concatenate([decoded_additional_channel] * 2, axis=2),
tensor_dict[fields.InputDataFields.image_additional_channels])
Example #15
| Source File: tf_example_decoder_test.py From models with Apache License 2.0 | 5 votes |
|
def testDecodePngInstanceMasks(self):
image = np.random.randint(256, size=(4, 5, 3)).astype(np.uint8)
encoded_png, _ = self._create_encoded_and_decoded_data(image, 'png')
mask_1 = np.random.randint(0, 2, size=(10, 10, 1)).astype(np.uint8)
mask_2 = np.random.randint(0, 2, size=(10, 10, 1)).astype(np.uint8)
encoded_png_1, _ = self._create_encoded_and_decoded_data(mask_1, 'png')
decoded_png_1 = np.squeeze(mask_1.astype(np.float32))
encoded_png_2, _ = self._create_encoded_and_decoded_data(mask_2, 'png')
decoded_png_2 = np.squeeze(mask_2.astype(np.float32))
encoded_masks = [encoded_png_1, encoded_png_2]
decoded_masks = np.stack([decoded_png_1, decoded_png_2])
def graph_fn():
example = tf.train.Example(
features=tf.train.Features(
feature={
'image/encoded':
dataset_util.bytes_feature(encoded_png),
'image/format':
dataset_util.bytes_feature(six.b('png')),
'image/object/mask':
dataset_util.bytes_list_feature(encoded_masks)
})).SerializeToString()
example_decoder = tf_example_decoder.TfExampleDecoder(
load_instance_masks=True,
instance_mask_type=input_reader_pb2.PNG_MASKS)
return example_decoder.decode(tf.convert_to_tensor(example))
tensor_dict = self.execute_cpu(graph_fn, [])
self.assertAllEqual(
decoded_masks,
tensor_dict[fields.InputDataFields.groundtruth_instance_masks])
Example #16
| Source File: tf_example_decoder_test.py From models with Apache License 2.0 | 5 votes |
|
def testDecodeEmptyPngInstanceMasks(self):
image_tensor = np.random.randint(256, size=(10, 10, 3)).astype(np.uint8)
encoded_png, _ = self._create_encoded_and_decoded_data(image_tensor, 'png')
encoded_masks = []
def graph_fn():
example = tf.train.Example(
features=tf.train.Features(
feature={
'image/encoded':
dataset_util.bytes_feature(encoded_png),
'image/format':
dataset_util.bytes_feature(six.b('png')),
'image/object/mask':
dataset_util.bytes_list_feature(encoded_masks),
'image/height':
dataset_util.int64_feature(10),
'image/width':
dataset_util.int64_feature(10),
})).SerializeToString()
example_decoder = tf_example_decoder.TfExampleDecoder(
load_instance_masks=True,
instance_mask_type=input_reader_pb2.PNG_MASKS)
return example_decoder.decode(tf.convert_to_tensor(example))
tensor_dict = self.execute_cpu(graph_fn, [])
self.assertAllEqual(
tensor_dict[fields.InputDataFields.groundtruth_instance_masks].shape,
[0, 10, 10])
Example #17
| Source File: decoder_builder_test.py From models with Apache License 2.0 | 5 votes |
|
def _make_serialized_tf_example(self, has_additional_channels=False):
image_tensor_np = np.random.randint(255, size=(4, 5, 3)).astype(np.uint8)
additional_channels_tensor_np = np.random.randint(
255, size=(4, 5, 1)).astype(np.uint8)
flat_mask = (4 * 5) * [1.0]
def graph_fn(image_tensor):
encoded_jpeg = tf.image.encode_jpeg(image_tensor)
return encoded_jpeg
encoded_jpeg = self.execute_cpu(graph_fn, [image_tensor_np])
encoded_additional_channels_jpeg = self.execute_cpu(
graph_fn, [additional_channels_tensor_np])
features = {
'image/source_id': dataset_util.bytes_feature('0'.encode()),
'image/encoded': dataset_util.bytes_feature(encoded_jpeg),
'image/format': dataset_util.bytes_feature('jpeg'.encode('utf8')),
'image/height': dataset_util.int64_feature(4),
'image/width': dataset_util.int64_feature(5),
'image/object/bbox/xmin': dataset_util.float_list_feature([0.0]),
'image/object/bbox/xmax': dataset_util.float_list_feature([1.0]),
'image/object/bbox/ymin': dataset_util.float_list_feature([0.0]),
'image/object/bbox/ymax': dataset_util.float_list_feature([1.0]),
'image/object/class/label': dataset_util.int64_list_feature([2]),
'image/object/mask': dataset_util.float_list_feature(flat_mask),
}
if has_additional_channels:
additional_channels_key = 'image/additional_channels/encoded'
features[additional_channels_key] = dataset_util.bytes_list_feature(
[encoded_additional_channels_jpeg] * 2)
example = tf.train.Example(features=tf.train.Features(feature=features))
return example.SerializeToString()
Example #18
| Source File: tf_example_decoder_test.py From multilabel-image-classification-tensorflow with MIT License | 5 votes |
|
def testDecodeAdditionalChannels(self):
image_tensor = np.random.randint(256, size=(4, 5, 3)).astype(np.uint8)
encoded_jpeg = self._EncodeImage(image_tensor)
additional_channel_tensor = np.random.randint(
256, size=(4, 5, 1)).astype(np.uint8)
encoded_additional_channel = self._EncodeImage(additional_channel_tensor)
decoded_additional_channel = self._DecodeImage(encoded_additional_channel)
example = tf.train.Example(
features=tf.train.Features(
feature={
'image/encoded':
dataset_util.bytes_feature(encoded_jpeg),
'image/additional_channels/encoded':
dataset_util.bytes_list_feature(
[encoded_additional_channel] * 2),
'image/format':
dataset_util.bytes_feature('jpeg'),
'image/source_id':
dataset_util.bytes_feature('image_id'),
})).SerializeToString()
example_decoder = tf_example_decoder.TfExampleDecoder(
num_additional_channels=2)
tensor_dict = example_decoder.decode(tf.convert_to_tensor(example))
with self.test_session() as sess:
tensor_dict = sess.run(tensor_dict)
self.assertAllEqual(
np.concatenate([decoded_additional_channel] * 2, axis=2),
tensor_dict[fields.InputDataFields.image_additional_channels])
Example #19
| Source File: tf_example_decoder_test.py From multilabel-image-classification-tensorflow with MIT License | 5 votes |
|
def testDecodePngInstanceMasks(self):
image_tensor = np.random.randint(256, size=(10, 10, 3)).astype(np.uint8)
encoded_jpeg = self._EncodeImage(image_tensor)
mask_1 = np.random.randint(0, 2, size=(10, 10, 1)).astype(np.uint8)
mask_2 = np.random.randint(0, 2, size=(10, 10, 1)).astype(np.uint8)
encoded_png_1 = self._EncodeImage(mask_1, encoding_type='png')
decoded_png_1 = np.squeeze(mask_1.astype(np.float32))
encoded_png_2 = self._EncodeImage(mask_2, encoding_type='png')
decoded_png_2 = np.squeeze(mask_2.astype(np.float32))
encoded_masks = [encoded_png_1, encoded_png_2]
decoded_masks = np.stack([decoded_png_1, decoded_png_2])
example = tf.train.Example(
features=tf.train.Features(
feature={
'image/encoded':
dataset_util.bytes_feature(encoded_jpeg),
'image/format':
dataset_util.bytes_feature('jpeg'),
'image/object/mask':
dataset_util.bytes_list_feature(encoded_masks)
})).SerializeToString()
example_decoder = tf_example_decoder.TfExampleDecoder(
load_instance_masks=True, instance_mask_type=input_reader_pb2.PNG_MASKS)
tensor_dict = example_decoder.decode(tf.convert_to_tensor(example))
with self.test_session() as sess:
tensor_dict = sess.run(tensor_dict)
self.assertAllEqual(
decoded_masks,
tensor_dict[fields.InputDataFields.groundtruth_instance_masks])
Example #20
| Source File: tf_example_decoder_test.py From multilabel-image-classification-tensorflow with MIT License | 5 votes |
|
def testDecodeEmptyPngInstanceMasks(self):
image_tensor = np.random.randint(256, size=(10, 10, 3)).astype(np.uint8)
encoded_jpeg = self._EncodeImage(image_tensor)
encoded_masks = []
example = tf.train.Example(
features=tf.train.Features(
feature={
'image/encoded':
dataset_util.bytes_feature(encoded_jpeg),
'image/format':
dataset_util.bytes_feature('jpeg'),
'image/object/mask':
dataset_util.bytes_list_feature(encoded_masks),
'image/height':
dataset_util.int64_feature(10),
'image/width':
dataset_util.int64_feature(10),
})).SerializeToString()
example_decoder = tf_example_decoder.TfExampleDecoder(
load_instance_masks=True, instance_mask_type=input_reader_pb2.PNG_MASKS)
tensor_dict = example_decoder.decode(tf.convert_to_tensor(example))
with self.test_session() as sess:
tensor_dict = sess.run(tensor_dict)
self.assertAllEqual(
tensor_dict[fields.InputDataFields.groundtruth_instance_masks].shape,
[0, 10, 10])
Example #21
| Source File: tf_example_decoder_test.py From multilabel-image-classification-tensorflow with MIT License | 5 votes |
|
def testDecodeObjectLabelUnrecognizedName(self):
image_tensor = np.random.randint(256, size=(4, 5, 3)).astype(np.uint8)
encoded_jpeg = self._EncodeImage(image_tensor)
bbox_classes_text = ['cat', 'cheetah']
example = tf.train.Example(
features=tf.train.Features(
feature={
'image/encoded':
dataset_util.bytes_feature(encoded_jpeg),
'image/format':
dataset_util.bytes_feature('jpeg'),
'image/object/class/text':
dataset_util.bytes_list_feature(bbox_classes_text),
})).SerializeToString()
label_map_string = """
item {
id:2
name:'cat'
}
item {
id:1
name:'dog'
}
"""
label_map_path = os.path.join(self.get_temp_dir(), 'label_map.pbtxt')
with tf.gfile.Open(label_map_path, 'wb') as f:
f.write(label_map_string)
example_decoder = tf_example_decoder.TfExampleDecoder(
label_map_proto_file=label_map_path)
tensor_dict = example_decoder.decode(tf.convert_to_tensor(example))
self.assertAllEqual((tensor_dict[fields.InputDataFields.groundtruth_classes]
.get_shape().as_list()), [None])
with self.test_session() as sess:
sess.run(tf.tables_initializer())
tensor_dict = sess.run(tensor_dict)
self.assertAllEqual([2, -1],
tensor_dict[fields.InputDataFields.groundtruth_classes])
Example #22
| Source File: tf_example_decoder_test.py From multilabel-image-classification-tensorflow with MIT License | 5 votes |
|
def testDecodeObjectLabelWithMappingWithDisplayName(self):
image_tensor = np.random.randint(256, size=(4, 5, 3)).astype(np.uint8)
encoded_jpeg = self._EncodeImage(image_tensor)
bbox_classes_text = ['cat', 'dog']
example = tf.train.Example(
features=tf.train.Features(
feature={
'image/encoded':
dataset_util.bytes_feature(encoded_jpeg),
'image/format':
dataset_util.bytes_feature('jpeg'),
'image/object/class/text':
dataset_util.bytes_list_feature(bbox_classes_text),
})).SerializeToString()
label_map_string = """
item {
id:3
display_name:'cat'
}
item {
id:1
display_name:'dog'
}
"""
label_map_path = os.path.join(self.get_temp_dir(), 'label_map.pbtxt')
with tf.gfile.Open(label_map_path, 'wb') as f:
f.write(label_map_string)
example_decoder = tf_example_decoder.TfExampleDecoder(
label_map_proto_file=label_map_path)
tensor_dict = example_decoder.decode(tf.convert_to_tensor(example))
self.assertAllEqual((tensor_dict[fields.InputDataFields.groundtruth_classes]
.get_shape().as_list()), [None])
with self.test_session() as sess:
sess.run(tf.tables_initializer())
tensor_dict = sess.run(tensor_dict)
self.assertAllEqual([3, 1],
tensor_dict[fields.InputDataFields.groundtruth_classes])
Example #23
| Source File: dataset_builder_test.py From multilabel-image-classification-tensorflow with MIT License | 5 votes |
|
def create_tf_record(self, has_additional_channels=False, num_examples=1):
path = os.path.join(self.get_temp_dir(), 'tfrecord')
writer = tf.python_io.TFRecordWriter(path)
image_tensor = np.random.randint(255, size=(4, 5, 3)).astype(np.uint8)
additional_channels_tensor = np.random.randint(
255, size=(4, 5, 1)).astype(np.uint8)
flat_mask = (4 * 5) * [1.0]
with self.test_session():
encoded_jpeg = tf.image.encode_jpeg(tf.constant(image_tensor)).eval()
encoded_additional_channels_jpeg = tf.image.encode_jpeg(
tf.constant(additional_channels_tensor)).eval()
for i in range(num_examples):
features = {
'image/source_id': dataset_util.bytes_feature(str(i)),
'image/encoded': dataset_util.bytes_feature(encoded_jpeg),
'image/format': dataset_util.bytes_feature('jpeg'.encode('utf8')),
'image/height': dataset_util.int64_feature(4),
'image/width': dataset_util.int64_feature(5),
'image/object/bbox/xmin': dataset_util.float_list_feature([0.0]),
'image/object/bbox/xmax': dataset_util.float_list_feature([1.0]),
'image/object/bbox/ymin': dataset_util.float_list_feature([0.0]),
'image/object/bbox/ymax': dataset_util.float_list_feature([1.0]),
'image/object/class/label': dataset_util.int64_list_feature([2]),
'image/object/mask': dataset_util.float_list_feature(flat_mask),
}
if has_additional_channels:
additional_channels_key = 'image/additional_channels/encoded'
features[additional_channels_key] = dataset_util.bytes_list_feature(
[encoded_additional_channels_jpeg] * 2)
example = tf.train.Example(features=tf.train.Features(feature=features))
writer.write(example.SerializeToString())
writer.close()
return path
Example #24
| Source File: gen_tfrecord.py From DeepLogo with MIT License | 5 votes |
|
def create_tf_example(csv, img_dir):
img_fname = csv[0]
x1, y1, x2, y2 = list(map(int, csv[1:-1]))
cls_idx = int(csv[-1])
cls_text = config.CLASS_NAMES[cls_idx].encode('utf8')
with tf.gfile.GFile(os.path.join(img_dir, img_fname), 'rb') as fid:
encoded_jpg = fid.read()
encoded_jpg_io = io.BytesIO(encoded_jpg)
image = Image.open(encoded_jpg_io)
width, height = image.size
xmin = [x1 / width]
xmax = [x2 / width]
ymin = [y1 / height]
ymax = [y2 / height]
cls_text = [cls_text]
cls_idx = [cls_idx]
filename = img_fname.encode('utf8')
image_format = b'jpg'
tf_example = tf.train.Example(features=tf.train.Features(feature={
'image/height': dataset_util.int64_feature(height),
'image/width': dataset_util.int64_feature(width),
'image/filename': dataset_util.bytes_feature(filename),
'image/source_id': dataset_util.bytes_feature(filename),
'image/encoded': dataset_util.bytes_feature(encoded_jpg),
'image/format': dataset_util.bytes_feature(image_format),
'image/object/bbox/xmin': dataset_util.float_list_feature(xmin),
'image/object/bbox/xmax': dataset_util.float_list_feature(xmax),
'image/object/bbox/ymin': dataset_util.float_list_feature(ymin),
'image/object/bbox/ymax': dataset_util.float_list_feature(ymax),
'image/object/class/text': dataset_util.bytes_list_feature(cls_text),
'image/object/class/label': dataset_util.int64_list_feature(cls_idx),
}))
return tf_example
Example #25
| Source File: tf_example_decoder_test.py From vehicle_counting_tensorflow with MIT License | 5 votes |
|
def testDecodeAdditionalChannels(self):
image_tensor = np.random.randint(256, size=(4, 5, 3)).astype(np.uint8)
encoded_jpeg = self._EncodeImage(image_tensor)
additional_channel_tensor = np.random.randint(
256, size=(4, 5, 1)).astype(np.uint8)
encoded_additional_channel = self._EncodeImage(additional_channel_tensor)
decoded_additional_channel = self._DecodeImage(encoded_additional_channel)
example = tf.train.Example(
features=tf.train.Features(
feature={
'image/encoded':
dataset_util.bytes_feature(encoded_jpeg),
'image/additional_channels/encoded':
dataset_util.bytes_list_feature(
[encoded_additional_channel] * 2),
'image/format':
dataset_util.bytes_feature('jpeg'),
'image/source_id':
dataset_util.bytes_feature('image_id'),
})).SerializeToString()
example_decoder = tf_example_decoder.TfExampleDecoder(
num_additional_channels=2)
tensor_dict = example_decoder.decode(tf.convert_to_tensor(example))
with self.test_session() as sess:
tensor_dict = sess.run(tensor_dict)
self.assertAllEqual(
np.concatenate([decoded_additional_channel] * 2, axis=2),
tensor_dict[fields.InputDataFields.image_additional_channels])
Example #26
| Source File: tf_example_decoder_test.py From vehicle_counting_tensorflow with MIT License | 5 votes |
|
def testDecodeEmptyPngInstanceMasks(self):
image_tensor = np.random.randint(256, size=(10, 10, 3)).astype(np.uint8)
encoded_jpeg = self._EncodeImage(image_tensor)
encoded_masks = []
example = tf.train.Example(
features=tf.train.Features(
feature={
'image/encoded':
dataset_util.bytes_feature(encoded_jpeg),
'image/format':
dataset_util.bytes_feature('jpeg'),
'image/object/mask':
dataset_util.bytes_list_feature(encoded_masks),
'image/height':
dataset_util.int64_feature(10),
'image/width':
dataset_util.int64_feature(10),
})).SerializeToString()
example_decoder = tf_example_decoder.TfExampleDecoder(
load_instance_masks=True, instance_mask_type=input_reader_pb2.PNG_MASKS)
tensor_dict = example_decoder.decode(tf.convert_to_tensor(example))
with self.test_session() as sess:
tensor_dict = sess.run(tensor_dict)
self.assertAllEqual(
tensor_dict[fields.InputDataFields.groundtruth_instance_masks].shape,
[0, 10, 10])
Example #27
| Source File: tf_example_decoder_test.py From vehicle_counting_tensorflow with MIT License | 5 votes |
|
def testDecodeObjectLabelUnrecognizedName(self):
image_tensor = np.random.randint(256, size=(4, 5, 3)).astype(np.uint8)
encoded_jpeg = self._EncodeImage(image_tensor)
bbox_classes_text = ['cat', 'cheetah']
example = tf.train.Example(
features=tf.train.Features(
feature={
'image/encoded':
dataset_util.bytes_feature(encoded_jpeg),
'image/format':
dataset_util.bytes_feature('jpeg'),
'image/object/class/text':
dataset_util.bytes_list_feature(bbox_classes_text),
})).SerializeToString()
label_map_string = """
item {
id:2
name:'cat'
}
item {
id:1
name:'dog'
}
"""
label_map_path = os.path.join(self.get_temp_dir(), 'label_map.pbtxt')
with tf.gfile.Open(label_map_path, 'wb') as f:
f.write(label_map_string)
example_decoder = tf_example_decoder.TfExampleDecoder(
label_map_proto_file=label_map_path)
tensor_dict = example_decoder.decode(tf.convert_to_tensor(example))
self.assertAllEqual((tensor_dict[fields.InputDataFields.groundtruth_classes]
.get_shape().as_list()), [None])
with self.test_session() as sess:
sess.run(tf.tables_initializer())
tensor_dict = sess.run(tensor_dict)
self.assertAllEqual([2, -1],
tensor_dict[fields.InputDataFields.groundtruth_classes])
Example #28
| Source File: tf_example_decoder_test.py From vehicle_counting_tensorflow with MIT License | 5 votes |
|
def testDecodeObjectLabelWithMappingWithDisplayName(self):
image_tensor = np.random.randint(256, size=(4, 5, 3)).astype(np.uint8)
encoded_jpeg = self._EncodeImage(image_tensor)
bbox_classes_text = ['cat', 'dog']
example = tf.train.Example(
features=tf.train.Features(
feature={
'image/encoded':
dataset_util.bytes_feature(encoded_jpeg),
'image/format':
dataset_util.bytes_feature('jpeg'),
'image/object/class/text':
dataset_util.bytes_list_feature(bbox_classes_text),
})).SerializeToString()
label_map_string = """
item {
id:3
display_name:'cat'
}
item {
id:1
display_name:'dog'
}
"""
label_map_path = os.path.join(self.get_temp_dir(), 'label_map.pbtxt')
with tf.gfile.Open(label_map_path, 'wb') as f:
f.write(label_map_string)
example_decoder = tf_example_decoder.TfExampleDecoder(
label_map_proto_file=label_map_path)
tensor_dict = example_decoder.decode(tf.convert_to_tensor(example))
self.assertAllEqual((tensor_dict[fields.InputDataFields.groundtruth_classes]
.get_shape().as_list()), [None])
with self.test_session() as sess:
sess.run(tf.tables_initializer())
tensor_dict = sess.run(tensor_dict)
self.assertAllEqual([3, 1],
tensor_dict[fields.InputDataFields.groundtruth_classes])
Example #29
| Source File: dataset_builder_test.py From vehicle_counting_tensorflow with MIT License | 5 votes |
|
def create_tf_record(self, has_additional_channels=False, num_examples=1):
path = os.path.join(self.get_temp_dir(), 'tfrecord')
writer = tf.python_io.TFRecordWriter(path)
image_tensor = np.random.randint(255, size=(4, 5, 3)).astype(np.uint8)
additional_channels_tensor = np.random.randint(
255, size=(4, 5, 1)).astype(np.uint8)
flat_mask = (4 * 5) * [1.0]
with self.test_session():
encoded_jpeg = tf.image.encode_jpeg(tf.constant(image_tensor)).eval()
encoded_additional_channels_jpeg = tf.image.encode_jpeg(
tf.constant(additional_channels_tensor)).eval()
for i in range(num_examples):
features = {
'image/source_id': dataset_util.bytes_feature(str(i)),
'image/encoded': dataset_util.bytes_feature(encoded_jpeg),
'image/format': dataset_util.bytes_feature('jpeg'.encode('utf8')),
'image/height': dataset_util.int64_feature(4),
'image/width': dataset_util.int64_feature(5),
'image/object/bbox/xmin': dataset_util.float_list_feature([0.0]),
'image/object/bbox/xmax': dataset_util.float_list_feature([1.0]),
'image/object/bbox/ymin': dataset_util.float_list_feature([0.0]),
'image/object/bbox/ymax': dataset_util.float_list_feature([1.0]),
'image/object/class/label': dataset_util.int64_list_feature([2]),
'image/object/mask': dataset_util.float_list_feature(flat_mask),
}
if has_additional_channels:
additional_channels_key = 'image/additional_channels/encoded'
features[additional_channels_key] = dataset_util.bytes_list_feature(
[encoded_additional_channels_jpeg] * 2)
example = tf.train.Example(features=tf.train.Features(feature=features))
writer.write(example.SerializeToString())
writer.close()
return path
Example #30
| Source File: generate_tfrecord.py From vehicle_counting_tensorflow with MIT License | 5 votes |
|
def create_tf_example(group, path):
with tf.gfile.GFile(os.path.join(path, '{}'.format(group.filename)), 'rb') as fid:
encoded_jpg = fid.read()
encoded_jpg_io = io.BytesIO(encoded_jpg)
image = Image.open(encoded_jpg_io)
width, height = image.size
filename = group.filename.encode('utf8')
image_format = b'jpg'
xmins = []
xmaxs = []
ymins = []
ymaxs = []
classes_text = []
classes = []
for index, row in group.object.iterrows():
xmins.append(row['xmin'] / width)
xmaxs.append(row['xmax'] / width)
ymins.append(row['ymin'] / height)
ymaxs.append(row['ymax'] / height)
classes_text.append(row['class'].encode('utf8'))
classes.append(class_text_to_int(row['class']))
tf_example = tf.train.Example(features=tf.train.Features(feature={
'image/height': dataset_util.int64_feature(height),
'image/width': dataset_util.int64_feature(width),
'image/filename': dataset_util.bytes_feature(filename),
'image/source_id': dataset_util.bytes_feature(filename),
'image/encoded': dataset_util.bytes_feature(encoded_jpg),
'image/format': dataset_util.bytes_feature(image_format),
'image/object/bbox/xmin': dataset_util.float_list_feature(xmins),
'image/object/bbox/xmax': dataset_util.float_list_feature(xmaxs),
'image/object/bbox/ymin': dataset_util.float_list_feature(ymins),
'image/object/bbox/ymax': dataset_util.float_list_feature(ymaxs),
'image/object/class/text': dataset_util.bytes_list_feature(classes_text),
'image/object/class/label': dataset_util.int64_list_feature(classes),
}))
return tf_example
