inverse_segfault.py 文件源码

def get_mnist_images():
  import gzip
  from tensorflow.contrib.learn.python.learn.datasets import base
  import numpy

  def extract_images(f):
    """Extract the images into a 4D uint8 numpy array [index, y, x, depth].
    Args:
      f: A file object that can be passed into a gzip reader.
    Returns:
      data: A 4D uint8 numpy array [index, y, x, depth].
    Raises:
      ValueError: If the bytestream does not start with 2051.
    """
    print('Extracting', f.name)
    with gzip.GzipFile(fileobj=f) as bytestream:
      magic = _read32(bytestream)
      if magic != 2051:
        raise ValueError('Invalid magic number %d in MNIST image file: %s' %
                         (magic, f.name))
      num_images = _read32(bytestream)
      rows = _read32(bytestream)
      cols = _read32(bytestream)
      buf = bytestream.read(rows * cols * num_images)
      data = numpy.frombuffer(buf, dtype=numpy.uint8)
      data = data.reshape(num_images, rows, cols, 1)
      return data

  def _read32(bytestream):
    dt = numpy.dtype(numpy.uint32).newbyteorder('>')
    return numpy.frombuffer(bytestream.read(4), dtype=dt)[0]

  TRAIN_IMAGES = 'train-images-idx3-ubyte.gz'
  source_url = 'https://storage.googleapis.com/cvdf-datasets/mnist/'
  local_file = base.maybe_download(TRAIN_IMAGES, '/tmp',
                                     source_url + TRAIN_IMAGES)
  train_images = extract_images(open(local_file, 'rb'))
  train_images = train_images.reshape(60000, 28**2).T.astype(np.float64)/255
  return train_images

# helper utilities