utils.py 文件源码

def prepare_label(input_batch, new_size, num_classes, one_hot=True):
    """Resize masks and perform one-hot encoding.

    Args:
      input_batch: input tensor of shape [batch_size H W 1].
      new_size: a tensor with new height and width.
      num_classes: number of classes to predict (including background).
      one_hot: whether perform one-hot encoding.

    Returns:
      Outputs a tensor of shape [batch_size h w 21]
      with last dimension comprised of 0's and 1's only.
    """
    with tf.name_scope('label_encode'):
        input_batch = tf.image.resize_nearest_neighbor(input_batch, new_size) # as labels are integer numbers, need to use NN interp.
        input_batch = tf.squeeze(input_batch, squeeze_dims=[3]) # reducing the channel dimension.
        if one_hot:
            input_batch = tf.one_hot(input_batch, depth=num_classes)
    return input_batch