Python object_detection.utils.dataset_util.int64_list_feature() Examples
The following are 30
code examples of object_detection.utils.dataset_util.int64_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: input_reader_builder_test.py From MAX-Object-Detector with Apache License 2.0 | 6 votes |
def create_tf_record(self): 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) flat_mask = (4 * 5) * [1.0] with self.test_session(): encoded_jpeg = tf.image.encode_jpeg(tf.constant(image_tensor)).eval() example = tf.train.Example(features=tf.train.Features(feature={ '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), })) writer.write(example.SerializeToString()) writer.close() return path
Example #2
Source File: input_reader_builder_test.py From Live-feed-object-device-identification-using-Tensorflow-and-OpenCV with Apache License 2.0 | 6 votes |
def create_tf_record(self): 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) flat_mask = (4 * 5) * [1.0] with self.test_session(): encoded_jpeg = tf.image.encode_jpeg(tf.constant(image_tensor)).eval() example = tf.train.Example(features=tf.train.Features(feature={ '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), })) writer.write(example.SerializeToString()) writer.close() return path
Example #3
Source File: input_reader_builder_test.py From Live-feed-object-device-identification-using-Tensorflow-and-OpenCV with Apache License 2.0 | 6 votes |
def create_tf_record(self): 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) flat_mask = (4 * 5) * [1.0] with self.test_session(): encoded_jpeg = tf.image.encode_jpeg(tf.constant(image_tensor)).eval() example = tf.train.Example(features=tf.train.Features(feature={ '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), })) writer.write(example.SerializeToString()) writer.close() return path
Example #4
Source File: input_reader_builder_test.py From g-tensorflow-models with Apache License 2.0 | 6 votes |
def create_tf_record(self): 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) flat_mask = (4 * 5) * [1.0] with self.test_session(): encoded_jpeg = tf.image.encode_jpeg(tf.constant(image_tensor)).eval() example = tf.train.Example(features=tf.train.Features(feature={ '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), })) writer.write(example.SerializeToString()) writer.close() return path
Example #5
Source File: input_reader_builder_test.py From vehicle_counting_tensorflow with MIT License | 6 votes |
def create_tf_record(self): 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) flat_mask = (4 * 5) * [1.0] with self.test_session(): encoded_jpeg = tf.image.encode_jpeg(tf.constant(image_tensor)).eval() example = tf.train.Example(features=tf.train.Features(feature={ '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), })) writer.write(example.SerializeToString()) writer.close() return path
Example #6
Source File: input_reader_builder_test.py From multilabel-image-classification-tensorflow with MIT License | 6 votes |
def create_tf_record(self): 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) flat_mask = (4 * 5) * [1.0] with self.test_session(): encoded_jpeg = tf.image.encode_jpeg(tf.constant(image_tensor)).eval() example = tf.train.Example(features=tf.train.Features(feature={ '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), })) writer.write(example.SerializeToString()) writer.close() return path
Example #7
Source File: tf_example_decoder_test.py From multilabel-image-classification-tensorflow with MIT License | 5 votes |
def testDecodeObjectLabel(self): image_tensor = np.random.randint(256, size=(4, 5, 3)).astype(np.uint8) encoded_jpeg = self._EncodeImage(image_tensor) bbox_classes = [0, 1] 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/label': dataset_util.int64_list_feature(bbox_classes), })).SerializeToString() example_decoder = tf_example_decoder.TfExampleDecoder() tensor_dict = example_decoder.decode(tf.convert_to_tensor(example)) self.assertAllEqual((tensor_dict[fields.InputDataFields.groundtruth_classes] .get_shape().as_list()), [2]) with self.test_session() as sess: tensor_dict = sess.run(tensor_dict) self.assertAllEqual(bbox_classes, tensor_dict[fields.InputDataFields.groundtruth_classes])
Example #8
Source File: tf_example_decoder_test.py From MAX-Object-Detector with Apache License 2.0 | 5 votes |
def testInstancesNotAvailableByDefault(self): num_instances = 4 image_height = 5 image_width = 3 # Randomly generate image. image_tensor = np.random.randint( 256, 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': dataset_util.bytes_feature(encoded_jpeg), 'image/format': dataset_util.bytes_feature('jpeg'), 'image/height': dataset_util.int64_feature(image_height), 'image/width': dataset_util.int64_feature(image_width), 'image/object/mask': dataset_util.float_list_feature(instance_masks_flattened), 'image/object/class/label': dataset_util.int64_list_feature(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)
Example #9
Source File: tf_example_decoder_test.py From MAX-Object-Detector with Apache License 2.0 | 5 votes |
def testDecodeObjectGroupOf(self): image_tensor = np.random.randint(256, size=(4, 5, 3)).astype(np.uint8) encoded_jpeg = self._EncodeImage(image_tensor) object_group_of = [0, 1] 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/group_of': dataset_util.int64_list_feature(object_group_of), })).SerializeToString() example_decoder = tf_example_decoder.TfExampleDecoder() tensor_dict = example_decoder.decode(tf.convert_to_tensor(example)) self.assertAllEqual( (tensor_dict[fields.InputDataFields.groundtruth_group_of].get_shape() .as_list()), [2]) with self.test_session() as sess: tensor_dict = sess.run(tensor_dict) self.assertAllEqual( [bool(item) for item in object_group_of], tensor_dict[fields.InputDataFields.groundtruth_group_of])
Example #10
Source File: tf_example_decoder_test.py From MAX-Object-Detector with Apache License 2.0 | 5 votes |
def testDecodeObjectDifficult(self): image_tensor = np.random.randint(256, 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': dataset_util.bytes_feature(encoded_jpeg), 'image/format': dataset_util.bytes_feature('jpeg'), 'image/object/difficult': dataset_util.int64_list_feature(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()), [2]) 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])
Example #11
Source File: tf_example_decoder_test.py From MAX-Object-Detector with Apache License 2.0 | 5 votes |
def testDecodeObjectIsCrowd(self): image_tensor = np.random.randint(256, size=(4, 5, 3)).astype(np.uint8) encoded_jpeg = self._EncodeImage(image_tensor) object_is_crowd = [0, 1] 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/is_crowd': dataset_util.int64_list_feature(object_is_crowd), })).SerializeToString() example_decoder = tf_example_decoder.TfExampleDecoder() tensor_dict = example_decoder.decode(tf.convert_to_tensor(example)) self.assertAllEqual( (tensor_dict[fields.InputDataFields.groundtruth_is_crowd].get_shape() .as_list()), [2]) with self.test_session() as sess: tensor_dict = sess.run(tensor_dict) self.assertAllEqual( [bool(item) for item in object_is_crowd], tensor_dict[fields.InputDataFields.groundtruth_is_crowd])
Example #12
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 #13
Source File: tf_example_decoder_test.py From MAX-Object-Detector with Apache License 2.0 | 5 votes |
def testDecodeObjectLabel(self): image_tensor = np.random.randint(256, size=(4, 5, 3)).astype(np.uint8) encoded_jpeg = self._EncodeImage(image_tensor) bbox_classes = [0, 1] 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/label': dataset_util.int64_list_feature(bbox_classes), })).SerializeToString() example_decoder = tf_example_decoder.TfExampleDecoder() tensor_dict = example_decoder.decode(tf.convert_to_tensor(example)) self.assertAllEqual((tensor_dict[fields.InputDataFields.groundtruth_classes] .get_shape().as_list()), [2]) with self.test_session() as sess: tensor_dict = sess.run(tensor_dict) self.assertAllEqual(bbox_classes, tensor_dict[fields.InputDataFields.groundtruth_classes])
Example #14
Source File: tf_example_decoder_test.py From multilabel-image-classification-tensorflow with MIT License | 5 votes |
def testInstancesNotAvailableByDefault(self): num_instances = 4 image_height = 5 image_width = 3 # Randomly generate image. image_tensor = np.random.randint( 256, 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': dataset_util.bytes_feature(encoded_jpeg), 'image/format': dataset_util.bytes_feature('jpeg'), 'image/height': dataset_util.int64_feature(image_height), 'image/width': dataset_util.int64_feature(image_width), 'image/object/mask': dataset_util.float_list_feature(instance_masks_flattened), 'image/object/class/label': dataset_util.int64_list_feature(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)
Example #15
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
Example #16
Source File: generate_tf_records.py From Emojinator 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
Example #17
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 #18
Source File: tf_example_decoder_test.py From vehicle_counting_tensorflow with MIT License | 5 votes |
def testDecodeObjectLabel(self): image_tensor = np.random.randint(256, size=(4, 5, 3)).astype(np.uint8) encoded_jpeg = self._EncodeImage(image_tensor) bbox_classes = [0, 1] 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/label': dataset_util.int64_list_feature(bbox_classes), })).SerializeToString() example_decoder = tf_example_decoder.TfExampleDecoder() tensor_dict = example_decoder.decode(tf.convert_to_tensor(example)) self.assertAllEqual((tensor_dict[fields.InputDataFields.groundtruth_classes] .get_shape().as_list()), [2]) with self.test_session() as sess: tensor_dict = sess.run(tensor_dict) self.assertAllEqual(bbox_classes, tensor_dict[fields.InputDataFields.groundtruth_classes])
Example #19
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 #20
Source File: tf_example_decoder_test.py From g-tensorflow-models with Apache License 2.0 | 5 votes |
def testDecodeObjectLabel(self): image_tensor = np.random.randint(256, size=(4, 5, 3)).astype(np.uint8) encoded_jpeg = self._EncodeImage(image_tensor) bbox_classes = [0, 1] 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/label': dataset_util.int64_list_feature(bbox_classes), })).SerializeToString() example_decoder = tf_example_decoder.TfExampleDecoder() tensor_dict = example_decoder.decode(tf.convert_to_tensor(example)) self.assertAllEqual((tensor_dict[fields.InputDataFields.groundtruth_classes] .get_shape().as_list()), [2]) with self.test_session() as sess: tensor_dict = sess.run(tensor_dict) self.assertAllEqual(bbox_classes, tensor_dict[fields.InputDataFields.groundtruth_classes])
Example #21
Source File: tf_example_decoder_test.py From g-tensorflow-models with Apache License 2.0 | 5 votes |
def testDecodeObjectIsCrowd(self): image_tensor = np.random.randint(256, size=(4, 5, 3)).astype(np.uint8) encoded_jpeg = self._EncodeImage(image_tensor) object_is_crowd = [0, 1] 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/is_crowd': dataset_util.int64_list_feature(object_is_crowd), })).SerializeToString() example_decoder = tf_example_decoder.TfExampleDecoder() tensor_dict = example_decoder.decode(tf.convert_to_tensor(example)) self.assertAllEqual( (tensor_dict[fields.InputDataFields.groundtruth_is_crowd].get_shape() .as_list()), [2]) with self.test_session() as sess: tensor_dict = sess.run(tensor_dict) self.assertAllEqual( [bool(item) for item in object_is_crowd], tensor_dict[fields.InputDataFields.groundtruth_is_crowd])
Example #22
Source File: tf_example_decoder_test.py From g-tensorflow-models with Apache License 2.0 | 5 votes |
def testDecodeObjectDifficult(self): image_tensor = np.random.randint(256, 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': dataset_util.bytes_feature(encoded_jpeg), 'image/format': dataset_util.bytes_feature('jpeg'), 'image/object/difficult': dataset_util.int64_list_feature(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()), [2]) 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])
Example #23
Source File: tf_example_decoder_test.py From g-tensorflow-models with Apache License 2.0 | 5 votes |
def testDecodeObjectGroupOf(self): image_tensor = np.random.randint(256, size=(4, 5, 3)).astype(np.uint8) encoded_jpeg = self._EncodeImage(image_tensor) object_group_of = [0, 1] 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/group_of': dataset_util.int64_list_feature(object_group_of), })).SerializeToString() example_decoder = tf_example_decoder.TfExampleDecoder() tensor_dict = example_decoder.decode(tf.convert_to_tensor(example)) self.assertAllEqual( (tensor_dict[fields.InputDataFields.groundtruth_group_of].get_shape() .as_list()), [2]) with self.test_session() as sess: tensor_dict = sess.run(tensor_dict) self.assertAllEqual( [bool(item) for item in object_group_of], tensor_dict[fields.InputDataFields.groundtruth_group_of])
Example #24
Source File: tf_example_decoder_test.py From g-tensorflow-models with Apache License 2.0 | 5 votes |
def testInstancesNotAvailableByDefault(self): num_instances = 4 image_height = 5 image_width = 3 # Randomly generate image. image_tensor = np.random.randint( 256, 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': dataset_util.bytes_feature(encoded_jpeg), 'image/format': dataset_util.bytes_feature('jpeg'), 'image/height': dataset_util.int64_feature(image_height), 'image/width': dataset_util.int64_feature(image_width), 'image/object/mask': dataset_util.float_list_feature(instance_masks_flattened), 'image/object/class/label': dataset_util.int64_list_feature(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)
Example #25
Source File: input_reader_builder_tf1_test.py From models with Apache License 2.0 | 5 votes |
def create_tf_record_with_context(self): 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) flat_mask = (4 * 5) * [1.0] context_features = (10 * 3) * [1.0] with self.test_session(): encoded_jpeg = tf.image.encode_jpeg(tf.constant(image_tensor)).eval() example = tf.train.Example( features=tf.train.Features( feature={ '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), 'image/context_features': dataset_util.float_list_feature(context_features), 'image/context_feature_length': dataset_util.int64_list_feature([10]), })) writer.write(example.SerializeToString()) writer.close() return path
Example #26
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 #27
Source File: tf_example_decoder_test.py From models with Apache License 2.0 | 5 votes |
def testDecodeObjectLabel(self): image_tensor = np.random.randint(256, size=(4, 5, 3)).astype(np.uint8) encoded_jpeg, _ = self._create_encoded_and_decoded_data( image_tensor, 'jpeg') bbox_classes = [0, 1] def graph_fn(): example = tf.train.Example( features=tf.train.Features( feature={ 'image/encoded': dataset_util.bytes_feature(encoded_jpeg), 'image/format': dataset_util.bytes_feature(six.b('jpeg')), 'image/object/class/label': dataset_util.int64_list_feature(bbox_classes), })).SerializeToString() example_decoder = tf_example_decoder.TfExampleDecoder() output = example_decoder.decode(tf.convert_to_tensor(example)) self.assertAllEqual((output[ fields.InputDataFields.groundtruth_classes].get_shape().as_list()), [2]) return output tensor_dict = self.execute_cpu(graph_fn, []) self.assertAllEqual(bbox_classes, tensor_dict[fields.InputDataFields.groundtruth_classes])
Example #28
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 #29
Source File: tf_example_decoder_test.py From models with Apache License 2.0 | 5 votes |
def testDecodeObjectIsCrowd(self): image_tensor = np.random.randint(256, size=(4, 5, 3)).astype(np.uint8) encoded_jpeg, _ = self._create_encoded_and_decoded_data( image_tensor, 'jpeg') object_is_crowd = [0, 1] def graph_fn(): example = tf.train.Example( features=tf.train.Features( feature={ 'image/encoded': dataset_util.bytes_feature(encoded_jpeg), 'image/format': dataset_util.bytes_feature(six.b('jpeg')), 'image/object/is_crowd': dataset_util.int64_list_feature(object_is_crowd), })).SerializeToString() example_decoder = tf_example_decoder.TfExampleDecoder() output = example_decoder.decode(tf.convert_to_tensor(example)) self.assertAllEqual((output[ fields.InputDataFields.groundtruth_is_crowd].get_shape().as_list()), [2]) return output tensor_dict = self.execute_cpu(graph_fn, []) self.assertAllEqual( [bool(item) for item in object_is_crowd], tensor_dict[fields.InputDataFields.groundtruth_is_crowd])
Example #30
Source File: tf_example_decoder_test.py From models with Apache License 2.0 | 5 votes |
def testDecodeObjectGroupOf(self): image_tensor = np.random.randint(256, size=(4, 5, 3)).astype(np.uint8) encoded_jpeg, _ = self._create_encoded_and_decoded_data( image_tensor, 'jpeg') object_group_of = [0, 1] def graph_fn(): example = tf.train.Example( features=tf.train.Features( feature={ 'image/encoded': dataset_util.bytes_feature(encoded_jpeg), 'image/format': dataset_util.bytes_feature(six.b('jpeg')), 'image/object/group_of': dataset_util.int64_list_feature(object_group_of), })).SerializeToString() example_decoder = tf_example_decoder.TfExampleDecoder() output = example_decoder.decode(tf.convert_to_tensor(example)) self.assertAllEqual((output[ fields.InputDataFields.groundtruth_group_of].get_shape().as_list()), [2]) return output tensor_dict = self.execute_cpu(graph_fn, []) self.assertAllEqual( [bool(item) for item in object_group_of], tensor_dict[fields.InputDataFields.groundtruth_group_of])