Python object_detection.utils.dataset_util.int64_feature() Examples

The following are 30 code examples of object_detection.utils.dataset_util.int64_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 vehicle_counting_tensorflow with MIT License 6 votes vote down vote up 
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 g-tensorflow-models with Apache License 2.0 6 votes vote down vote up 
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 multilabel-image-classification-tensorflow with MIT License 6 votes vote down vote up 
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 Live-feed-object-device-identification-using-Tensorflow-and-OpenCV with Apache License 2.0 6 votes vote down vote up 
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_tf1_test.py    From models with Apache License 2.0 6 votes vote down vote up 
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 Live-feed-object-device-identification-using-Tensorflow-and-OpenCV with Apache License 2.0 6 votes vote down vote up 
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: input_reader_builder_test.py    From MAX-Object-Detector with Apache License 2.0 6 votes vote down vote up 
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 #8
Source File: create_kitti_tf_record.py    From motion-rcnn with MIT License 6 votes vote down vote up 
def _create_tfexample(label_map_dict,
                      image_id, encoded_image, encoded_next_image,
                      disparity_image, next_disparity_image, flow):
  #camera_intrinsics = np.array([982.529, 690.0, 233.1966])
  camera_intrinsics = np.array([725.0, 620.5, 187.0], dtype=np.float32)
  f, x0, y0 = camera_intrinsics
  depth = _depth_from_disparity_image(disparity_image, f)
  next_depth = _depth_from_disparity_image(next_disparity_image, f)

  key = hashlib.sha256(encoded_image).hexdigest()
  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(image_id.encode('utf8')),
    'image/source_id': dataset_util.bytes_feature(image_id.encode('utf8')),
    'image/encoded': dataset_util.bytes_feature(encoded_image),
    'next_image/encoded': dataset_util.bytes_feature(encoded_next_image),
    'image/format': dataset_util.bytes_feature('png'.encode('utf8')),
    'image/key/sha256': dataset_util.bytes_feature(key.encode('utf8')),
    'image/depth': dataset_util.float_list_feature(depth.ravel().tolist()),
    'next_image/depth': dataset_util.float_list_feature(next_depth.ravel().tolist()),
    'image/flow': dataset_util.float_list_feature(example_flow.ravel().tolist()),
    'image/camera/intrinsics': dataset_util.float_list_feature(camera_intrinsics.tolist())
  }))
  return example, num_instances
Example #9
Source File: dataset_builder_test.py    From MAX-Object-Detector with Apache License 2.0 5 votes vote down vote up 
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 #10
Source File: gen_tfrecord.py    From DeepLogo with MIT License 5 votes vote down vote up 
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 #11
Source File: input_reader_builder_tf1_test.py    From models with Apache License 2.0 5 votes vote down vote up 
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 #12
Source File: tf_example_decoder_test.py    From MAX-Object-Detector with Apache License 2.0 5 votes vote down vote up 
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 #13
Source File: tf_example_decoder_test.py    From vehicle_counting_tensorflow with MIT License 5 votes vote down vote up 
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 #14
Source File: tf_example_decoder_test.py    From MAX-Object-Detector with Apache License 2.0 5 votes vote down vote up 
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: dataset_builder_test.py    From multilabel-image-classification-tensorflow with MIT License 5 votes vote down vote up 
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 #16
Source File: tf_example_decoder_test.py    From g-tensorflow-models with Apache License 2.0 5 votes vote down vote up 
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 #17
Source File: tf_example_decoder_test.py    From g-tensorflow-models with Apache License 2.0 5 votes vote down vote up 
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 #18
Source File: dataset_builder_test.py    From g-tensorflow-models with Apache License 2.0 5 votes vote down vote up 
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 #19
Source File: tf_example_decoder_test.py    From models with Apache License 2.0 5 votes vote down vote up 
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 #20
Source File: tf_example_decoder_test.py    From models with Apache License 2.0 5 votes vote down vote up 
def testContextFeaturesNotAvailableByDefault(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_ymins = [0.0, 4.0]
    bbox_xmins = [1.0, 5.0]
    bbox_ymaxs = [2.0, 6.0]
    bbox_xmaxs = [3.0, 7.0]
    num_features = 10
    context_feature_length = 10
    context_features = np.random.random(num_features*context_feature_length)

    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/context_features':
                      dataset_util.float_list_feature(context_features),
                  'image/context_feature_length':
                      dataset_util.int64_feature(context_feature_length),
                  'image/object/bbox/ymin':
                      dataset_util.float_list_feature(bbox_ymins),
                  'image/object/bbox/xmin':
                      dataset_util.float_list_feature(bbox_xmins),
                  'image/object/bbox/ymax':
                      dataset_util.float_list_feature(bbox_ymaxs),
                  'image/object/bbox/xmax':
                      dataset_util.float_list_feature(bbox_xmaxs),
              })).SerializeToString()

      example_decoder = tf_example_decoder.TfExampleDecoder()
      return example_decoder.decode(tf.convert_to_tensor(example))

    tensor_dict = self.execute_cpu(graph_fn, [])
    self.assertNotIn(fields.InputDataFields.context_features,
                     tensor_dict)
Example #21
Source File: gen_tfrecord_logos32plus.py    From DeepLogo with MIT License 5 votes vote down vote up 
def create_tf_example(img_fname, logo_name, bbox, img_dir, logo_names):
    x1, y1, w, h = list(map(int, bbox))
    x2, y2 = x1 + w, y1 + h
    cls_idx = logo_names[logo_name]
    cls_text = logo_name.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 #22
Source File: dataset_builder_test.py    From Live-feed-object-device-identification-using-Tensorflow-and-OpenCV with Apache License 2.0 5 votes vote down vote up 
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 #23
Source File: dataset_builder_test.py    From Live-feed-object-device-identification-using-Tensorflow-and-OpenCV with Apache License 2.0 5 votes vote down vote up 
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: Generate_tfrecord.py    From Live-feed-object-device-identification-using-Tensorflow-and-OpenCV with Apache License 2.0 5 votes vote down vote up 
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 #25
Source File: generate_tfrecord.py    From TensorFlow-Object-Detection-API-Tutorial-Train-Multiple-Objects-Windows-10 with Apache License 2.0 5 votes vote down vote up 
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 #26
Source File: tf_example_decoder_test.py    From multilabel-image-classification-tensorflow with MIT License 5 votes vote down vote up 
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: generate_tfrecord.py    From Tensorflow-Object-Detection-API-Train-Model with MIT License 5 votes vote down vote up 
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 #28
Source File: tf_example_decoder_test.py    From multilabel-image-classification-tensorflow with MIT License 5 votes vote down vote up 
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 #29
Source File: generate_tf_records.py    From Emojinator with MIT License 5 votes vote down vote up 
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 #30
Source File: dataset_builder_test.py    From vehicle_counting_tensorflow with MIT License 5 votes vote down vote up 
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