PaddleX/paddlex/inference/pipelines/ocr.py

# copyright (c) 2024 PaddlePaddle Authors. All Rights Reserve.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#    http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

from .base import BasePipeline
from ..components import CropByPolys
from ..results import OCRResult


class OCRPipeline(BasePipeline):
    """OCR Pipeline"""

    entities = "ocr"

    def __init__(
        self, det_model, rec_model, rec_batch_size, predictor_kwargs=None, is_curve=False, **kwargs
    ):
        super().__init__(predictor_kwargs)
        self._det_predict = self._create_predictor(det_model)
        self._rec_predict = self._create_predictor(rec_model, batch_size=rec_batch_size)
        # TODO: foo
        if is_curve:
            det_box_type = 'poly'
        else:
            det_box_type = 'quad'
        self._crop_by_polys = CropByPolys(det_box_type=det_box_type)

    def predict(self, x):
        for det_res in self._det_predict(x):
            single_img_res = det_res
            single_img_res["rec_text"] = []
            single_img_res["rec_score"] = []
            if len(single_img_res["dt_polys"]) > 0:
                all_subs_of_img = list(self._crop_by_polys(single_img_res))
                for rec_res in self._rec_predict(all_subs_of_img):
                    single_img_res["rec_text"].append(rec_res["rec_text"])
                    single_img_res["rec_score"].append(rec_res["rec_score"])
            yield single_img_res