TF学习之DeepLabv3+代码阅读3（input_preprocess）

DeepLabv3+代码阅读之input_preprocess.py

一、preprocess_image_and_label

对图片和标签处理
返回：
	original_image： 原始图片
	processed_image： 处理后图片
	label： 处理后ground truth

def preprocess_image_and_label(image,# 输入图片
                               label,# Ground truth
                               crop_height,# 裁剪image和label的尺寸
                               crop_width,
                               min_resize_value=None,# 要求的resize最小的短边
                               max_resize_value=None,# 允许的resize的最大长边
                               resize_factor=None,
                               min_scale_factor=1.,
                               max_scale_factor=1.,
                               scale_factor_step_size=0,
                               ignore_label=255,
                               is_training=True,
                               model_variant=None):

  if is_training and label is None:
    raise ValueError('During training, label must be provided.')
  if model_variant is None:
    tf.logging.warning('Default mean-subtraction is performed. Please specify '
                       'a model_variant. See feature_extractor.network_map for '
                       'supported model variants.')

  # Keep reference to original image.
  original_image = image

  processed_image = tf.cast(image, tf.float32)

  if label is not None:
    label = tf.cast(label, tf.int32)

  # Resize image and label to the desired range.
  if min_resize_value or max_resize_value:
    [processed_image, label] = (
        preprocess_utils.resize_to_range(
            image=processed_image,
            label=label,
            min_size=min_resize_value,
            max_size=max_resize_value,
            factor=resize_factor,
            align_corners=True))
    # The `original_image` becomes the resized image.
    original_image = tf.identity(processed_image)

  # Data augmentation by randomly scaling the inputs.
  if is_training:
    scale = preprocess_utils.get_random_scale(
        min_scale_factor, max_scale_factor, scale_factor_step_size)
    processed_image, label = preprocess_utils.randomly_scale_image_and_label(
        processed_image, label, scale)
    processed_image.set_shape([None, None, 3])

  # Pad image and label to have dimensions >= [crop_height, crop_width]
  image_shape = tf.shape(processed_image)
  image_height = image_shape[0]
  image_width = image_shape[1]

  target_height = image_height + tf.maximum(crop_height - image_height, 0)
  target_width = image_width + tf.maximum(crop_width - image_width, 0)

  # Pad image with mean pixel value.
  mean_pixel = tf.reshape(
      feature_extractor.mean_pixel(model_variant), [1, 1, 3])
  processed_image = preprocess_utils.pad_to_bounding_box(
      processed_image, 0, 0, target_height, target_width, mean_pixel)

  if label is not None:
    label = preprocess_utils.pad_to_bounding_box(
        label, 0, 0, target_height, target_width, ignore_label)

  # Randomly crop the image and label.
  if is_training and label is not None:
    processed_image, label = preprocess_utils.random_crop(
        [processed_image, label], crop_height, crop_width)

  processed_image.set_shape([crop_height, crop_width, 3])

  if label is not None:
    label.set_shape([crop_height, crop_width, 1])

  if is_training:
    # Randomly left-right flip the image and label.
    processed_image, label, _ = preprocess_utils.flip_dim(
        [processed_image, label], _PROB_OF_FLIP, dim=1)

  return original_image, processed_image, label