image_reader.py 文件源码

def read_images_from_disk(input_queue, input_size, random_scale): 
    """Read one image and its corresponding mask with optional pre-processing.

    Args:
      input_queue: tf queue with paths to the image and its mask.
      input_size: a tuple with (height, width) values.
                  If not given, return images of original size.
      random_scale: whether to randomly scale the images prior
                    to random crop.

    Returns:
      Two tensors: the decoded image and its mask.
    """
    img_contents = tf.read_file(input_queue[0])
    label_contents = tf.read_file(input_queue[1])
    shape = input_queue[2]

    img = tf.image.decode_jpeg(img_contents, channels=3)
    label = tf.image.decode_png(label_contents, channels=1)
    if input_size is not None:
        h, w = input_size
        if random_scale:
            scale = tf.random_uniform([1], minval=0.75, maxval=1.25, dtype=tf.float32, seed=None)
            h_new = tf.to_int32(tf.multiply(tf.to_float(tf.shape(img)[0]), scale))
            w_new = tf.to_int32(tf.multiply(tf.to_float(tf.shape(img)[1]), scale))
            new_shape = tf.squeeze(tf.stack([h_new, w_new]), axis=[1])
            img = tf.image.resize_images(img, new_shape)
            label = tf.image.resize_nearest_neighbor(tf.expand_dims(label, 0), new_shape)
            label = tf.squeeze(label, axis=[0]) # resize_image_with_crop_or_pad accepts 3D-tensor.
        img = tf.image.resize_image_with_crop_or_pad(img, h, w)
        label = tf.image.resize_image_with_crop_or_pad(label, h, w)
    # RGB -> BGR.
    img_r, img_g, img_b = tf.split(axis=2, num_or_size_splits=3, value=img)
    img = tf.cast(tf.concat(axis=2, values=[img_b, img_g, img_r]), dtype=tf.float32)
    # Extract mean.
    img -= IMG_MEAN

    return img, label, shape