PASCALVOC2012Localization.py 文件源码

def _read_image_and_box(self, bboxes_csv):
        """Extract the filename from the queue, read the image and
        produce a single box
        Returns:
            image, [y_min, x_min, y_max, x_max, label]
        """

        reader = tf.TextLineReader(skip_header_lines=True)
        _, row = reader.read(bboxes_csv)
        # file ,y_min, x_min, y_max, x_max, label
        record_defaults = [[""], [0.], [0.], [0.], [0.], [0.]]
        # eg:
        # 2008_000033,0.1831831831831832,0.208,0.7717717717717718,0.952,0
        filename, y_min, x_min, y_max, x_max, label = tf.decode_csv(
            row, record_defaults)
        image_path = os.path.join(self._data_dir, 'VOCdevkit', 'VOC2012',
                                  'JPEGImages') + "/" + filename + ".jpg"

        # image is normalized in [-1,1]
        image = read_image_jpg(image_path)
        return image, tf.stack([y_min, x_min, y_max, x_max, label])