CASIA.py 文件源码

def load_gnt_file(filename):
        """
        Load characters and images from a given GNT file.
        :param filename: The file path to load.
        :return: (image: Pillow.Image.Image, character) tuples
        """

        # Thanks to nhatch for the code to read the GNT file, available at https://github.com/nhatch/casia
        with open(filename, "rb") as f:
            while True:
                packed_length = f.read(4)
                if packed_length == b'':
                    break

                length = struct.unpack("<I", packed_length)[0]
                raw_label = struct.unpack(">cc", f.read(2))
                width = struct.unpack("<H", f.read(2))[0]
                height = struct.unpack("<H", f.read(2))[0]
                photo_bytes = struct.unpack("{}B".format(height * width), f.read(height * width))

                # Comes out as a tuple of chars. Need to be combined. Encoded as gb2312, gotta convert to unicode.
                label = decode(raw_label[0] + raw_label[1], encoding="gb2312")
                # Create an array of bytes for the image, match it to the proper dimensions, and turn it into an image.
                image = toimage(np.array(photo_bytes).reshape(height, width))

                yield image, label