preprocess.py 文件源码

def load_letter(letter_dir, min_num_images):
    """Load the data for a single letter label."""
    image_files = os.listdir(letter_dir)
    # (num image, image width, image height)
    dataset = np.ndarray(shape=(len(image_files), image_size, image_size),
                         dtype=np.float32)
    image_index = 0
    print(letter_dir)
    for image in image_files:
        image_file = os.path.join(letter_dir, image)
        try:
            # normalize image to [-0.5, 0.5]
            image_data = (ndimage.imread(image_file).astype(float) -
                          pixel_depth / 2) / pixel_depth
            if image_data.shape != (image_size, image_size):
                raise Exception('Unexpected image shape: %s' % str(image_data.shape))
            dataset[image_index, :, :] = image_data
            image_index += 1
        except IOError as e:
            print('Could not read:', image_file, ':', e, "- it's ok, skipping.")

    num_images = image_index
    dataset = dataset[0:num_images, :, :]
    if num_images < min_num_images:
        raise Exception('Many fewer images than expected: %d < %d'
                        % (num_images, min_num_images))

    print('Full dataset tensor:', dataset.shape)
    print('Mean:', np.mean(dataset))
    print('Standard deviation:', np.std(dataset))
    return dataset