Class OCRDet

deploy/hubserving/ocr_det/module.py:46–144

    type="cv/text_detection",
)
class OCRDet(hub.Module):
    def _initialize(self, use_gpu=False, enable_mkldnn=False):
        """
        initialize with the necessary elements
        """
        cfg = self.merge_configs()

        cfg.use_gpu = use_gpu
        if use_gpu:
            try:
                _places = os.environ["CUDA_VISIBLE_DEVICES"]
                int(_places[0])
                print("use gpu: ", use_gpu)
                print("CUDA_VISIBLE_DEVICES: ", _places)
                cfg.gpu_mem = 8000
            except:
                raise RuntimeError(
                    "Environment Variable CUDA_VISIBLE_DEVICES is not set correctly. If you wanna use gpu, please set CUDA_VISIBLE_DEVICES via export CUDA_VISIBLE_DEVICES=cuda_device_id."
                )
        cfg.ir_optim = True
        cfg.enable_mkldnn = enable_mkldnn

        self.text_detector = TextDetector(cfg)

    def merge_configs(
        self,
    ):
        # default cfg
        backup_argv = copy.deepcopy(sys.argv)
        sys.argv = sys.argv[:1]
        cfg = parse_args()

        update_cfg_map = vars(read_params())

        for key in update_cfg_map:
            cfg.__setattr__(key, update_cfg_map[key])

        sys.argv = copy.deepcopy(backup_argv)
        return cfg

    def read_images(self, paths=[]):
        images = []
        for img_path in paths:
            assert os.path.isfile(img_path), "The {} isn't a valid file.".format(
                img_path
            )
            img = cv2.imread(img_path)
            if img is None:
                logger.info("error in loading image:{}".format(img_path))
                continue
            images.append(img)
        return images

    def predict(self, images=[], paths=[]):
        """
        Get the text box in the predicted images.
        Args:
            images (list(numpy.ndarray)): images data, shape of each is [H, W, C]. If images not paths