ocr_det.h 2.7 KB
Newer Older
littletomatodonkey's avatar
littletomatodonkey 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 32 33 34 35 36 37 38
// Copyright (c) 2020 PaddlePaddle Authors. All Rights Reserved.
//
// 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.

#pragma once

#include "opencv2/core.hpp"
#include "opencv2/imgcodecs.hpp"
#include "opencv2/imgproc.hpp"
#include "paddle_api.h"
#include "paddle_inference_api.h"
#include <chrono>
#include <iomanip>
#include <iostream>
#include <ostream>
#include <vector>

#include <cstring>
#include <fstream>
#include <numeric>

#include <include/postprocess_op.h>
#include <include/preprocess_op.h>

namespace PaddleOCR {

class DBDetector {
public:
littletomatodonkey's avatar
littletomatodonkey 已提交
39 40 41 42 43 44 45
  explicit DBDetector(const std::string &model_dir, const bool &use_gpu,
                      const int &gpu_id, const int &gpu_mem,
                      const int &cpu_math_library_num_threads,
                      const int &max_side_len, const double &det_db_thresh,
                      const double &det_db_box_thresh,
                      const double &det_db_unclip_ratio,
                      const bool &visualize) {
littletomatodonkey's avatar
littletomatodonkey 已提交
46 47 48 49 50
    this->use_gpu_ = use_gpu;
    this->gpu_id_ = gpu_id;
    this->gpu_mem_ = gpu_mem;
    this->cpu_math_library_num_threads_ = cpu_math_library_num_threads;

littletomatodonkey's avatar
littletomatodonkey 已提交
51
    this->max_side_len_ = max_side_len;
littletomatodonkey's avatar
littletomatodonkey 已提交
52 53 54 55

    this->det_db_thresh_ = det_db_thresh;
    this->det_db_box_thresh_ = det_db_box_thresh;
    this->det_db_unclip_ratio_ = det_db_unclip_ratio;
littletomatodonkey's avatar
littletomatodonkey 已提交
56 57

    this->visualize_ = visualize;
littletomatodonkey's avatar
littletomatodonkey 已提交
58 59

    LoadModel(model_dir);
littletomatodonkey's avatar
littletomatodonkey 已提交
60 61 62
  }

  // Load Paddle inference model
littletomatodonkey's avatar
littletomatodonkey 已提交
63
  void LoadModel(const std::string &model_dir);
littletomatodonkey's avatar
littletomatodonkey 已提交
64 65 66 67 68 69 70

  // Run predictor
  void Run(cv::Mat &img, std::vector<std::vector<std::vector<int>>> &boxes);

private:
  std::shared_ptr<PaddlePredictor> predictor_;

littletomatodonkey's avatar
littletomatodonkey 已提交
71 72 73 74 75
  bool use_gpu_ = false;
  int gpu_id_ = 0;
  int gpu_mem_ = 4000;
  int cpu_math_library_num_threads_ = 4;

littletomatodonkey's avatar
littletomatodonkey 已提交
76 77
  int max_side_len_ = 960;

littletomatodonkey's avatar
littletomatodonkey 已提交
78 79 80 81
  double det_db_thresh_ = 0.3;
  double det_db_box_thresh_ = 0.5;
  double det_db_unclip_ratio_ = 2.0;

littletomatodonkey's avatar
littletomatodonkey 已提交
82 83
  bool visualize_ = true;

littletomatodonkey's avatar
littletomatodonkey 已提交
84 85 86 87 88 89 90 91 92 93 94 95 96 97
  std::vector<float> mean_ = {0.485f, 0.456f, 0.406f};
  std::vector<float> scale_ = {1 / 0.229f, 1 / 0.224f, 1 / 0.225f};
  bool is_scale_ = true;

  // pre-process
  ResizeImgType0 resize_op_;
  Normalize normalize_op_;
  Permute permute_op_;

  // post-process
  PostProcessor post_processor_;
};

} // namespace PaddleOCR