module.py 4.2 KB
Newer Older
文幕地方's avatar
文幕地方 已提交
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31
# -*- coding:utf-8 -*-
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

import os
import sys
sys.path.insert(0, ".")
import copy

import time
import paddlehub
from paddlehub.common.logger import logger
from paddlehub.module.module import moduleinfo, runnable, serving
import cv2
import numpy as np
import paddlehub as hub

from tools.infer.utility import base64_to_cv2
from ppstructure.table.predict_table import TableSystem as _TableSystem
from ppstructure.predict_system import save_structure_res
from ppstructure.utility import parse_args
from deploy.hubserving.structure_table.params import read_params


@moduleinfo(
    name="structure_table",
    version="1.0.0",
    summary="PP-Structure table service",
    author="paddle-dev",
    author_email="paddle-dev@baidu.com",
文幕地方's avatar
文幕地方 已提交
32
    type="cv/structure_table")
文幕地方's avatar
文幕地方 已提交
33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111
class TableSystem(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.table_sys = _TableSystem(cfg)

    def merge_configs(self):
        # deafult 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 chinese texts in the predicted images.
        Args:
            images (list(numpy.ndarray)): images data, shape of each is [H, W, C]. If images not paths
            paths (list[str]): The paths of images. If paths not images
        Returns:
            res (list): The result of chinese texts and save path of images.
        """

        if images != [] and isinstance(images, list) and paths == []:
            predicted_data = images
        elif images == [] and isinstance(paths, list) and paths != []:
            predicted_data = self.read_images(paths)
        else:
            raise TypeError("The input data is inconsistent with expectations.")

        assert predicted_data != [], "There is not any image to be predicted. Please check the input data."

        all_results = []
        for img in predicted_data:
            if img is None:
                logger.info("error in loading image")
                all_results.append([])
                continue
            starttime = time.time()
            pred_html = self.table_sys(img)
            elapse = time.time() - starttime
            logger.info("Predict time: {}".format(elapse))

文幕地方's avatar
文幕地方 已提交
112
            all_results.append({'html': pred_html})
文幕地方's avatar
文幕地方 已提交
113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130
        return all_results

    @serving
    def serving_method(self, images, **kwargs):
        """
        Run as a service.
        """
        images_decode = [base64_to_cv2(image) for image in images]
        results = self.predict(images_decode, **kwargs)
        return results


if __name__ == '__main__':
    table_system = TableSystem()
    table_system._initialize()
    image_path = ['./doc/table/table.jpg']
    res = table_system.predict(paths=image_path)
    print(res)