data.py 文件源码

def __read_cifar(filenames, shuffle=True, cifar100=False):
  """Reads and parses examples from CIFAR data files.
  """
  # Dimensions of the images in the CIFAR-10 dataset.
  # See http://www.cs.toronto.edu/~kriz/cifar.html for a description of the
  # input format.
  filename_queue = tf.train.string_input_producer(filenames, shuffle=shuffle,num_epochs=None)

  label_bytes = 1  # 2 for CIFAR-100
  if cifar100:
      label_bytes = 2
  height = 32
  width = 32
  depth = 3
  image_bytes = height * width * depth
  # Every record consists of a label followed by the image, with a
  # fixed number of bytes for each.
  record_bytes = label_bytes + image_bytes

  # Read a record, getting filenames from the filename_queue.  No
  # header or footer in the CIFAR-10 format, so we leave header_bytes
  # and footer_bytes at their default of 0.
  reader = tf.FixedLengthRecordReader(record_bytes=record_bytes)
  key, value = reader.read(filename_queue)

  # Convert from a string to a vector of uint8 that is record_bytes long.
  record_bytes = tf.decode_raw(value, tf.uint8)

  # The first bytes represent the label, which we convert from uint8->int32.
  label = tf.cast(
      tf.slice(record_bytes, [0], [label_bytes]), tf.int32)

  # The remaining bytes after the label represent the image, which we reshape
  # from [depth * height * width] to [depth, height, width].
  depth_major = tf.reshape(tf.slice(record_bytes, [label_bytes], [image_bytes]),
                           [depth, height, width])
  # Convert from [depth, height, width] to [height, width, depth].
  image = tf.transpose(depth_major, [1, 2, 0])

  return tf.cast(image, tf.float32), label