98 lines
2.7 KiB
C++
98 lines
2.7 KiB
C++
// 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:
|
|
explicit DBDetector(const std::string &model_dir, const bool &use_gpu = false,
|
|
const int &gpu_id = 0, const int &gpu_mem = 4000,
|
|
const int &cpu_math_library_num_threads = 4,
|
|
const int &max_side_len = 960,
|
|
const double &det_db_thresh = 0.3,
|
|
const double &det_db_box_thresh = 0.5,
|
|
const double &det_db_unclip_ratio = 2.0,
|
|
const bool &visualize = true) {
|
|
LoadModel(model_dir);
|
|
|
|
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;
|
|
|
|
this->max_side_len_ = max_side_len;
|
|
|
|
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;
|
|
|
|
this->visualize_ = visualize;
|
|
}
|
|
|
|
// Load Paddle inference model
|
|
void LoadModel(const std::string &model_dir);
|
|
|
|
// Run predictor
|
|
void Run(cv::Mat &img, std::vector<std::vector<std::vector<int>>> &boxes);
|
|
|
|
private:
|
|
std::shared_ptr<PaddlePredictor> predictor_;
|
|
|
|
bool use_gpu_ = false;
|
|
int gpu_id_ = 0;
|
|
int gpu_mem_ = 4000;
|
|
int cpu_math_library_num_threads_ = 4;
|
|
|
|
int max_side_len_ = 960;
|
|
|
|
double det_db_thresh_ = 0.3;
|
|
double det_db_box_thresh_ = 0.5;
|
|
double det_db_unclip_ratio_ = 2.0;
|
|
|
|
bool visualize_ = true;
|
|
|
|
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
|