目录
接上这一篇
基于VS2019的paddle-ocr编译、测试和代码精简_Jieeeee`的博客-CSDN博客
接下来,生成一个DLL文件给其他工程调用
修改代码,解决返回值问题
首先修改上文中的代码,因为paddle-ocr源码会将每幅图里的字符串分开,标上坐标
但是对我的应用来说,我只需要读取当前的全部字符即可,不需要用到两维的向量,而且二维的向量也不利于函数返回
// 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.
#include "opencv2/core.hpp"
#include "opencv2/imgcodecs.hpp"
#include "opencv2/imgproc.hpp"
#include <iostream>
#include <vector>
#include <include/args.h>
#include <include/paddleocr.h>
#include <include/paddlestructure.h>
#include <chrono>
using namespace std::chrono;
using namespace PaddleOCR;
using namespace std;
string return_result(const vector<OCRPredictResult>& ocr_result) {
std::string rec_result;
for (int i = 0; i < ocr_result.size(); i++) {
//这里的ocr_result.size()是单张图片内识别的多个字符串
if (ocr_result[i].score != -1.0) {
rec_result += ocr_result[i].text;
}
}
//cout << "rec text: " << rec_result;
//cout << std::endl;
return rec_result;
}
vector<string> ocr(vector<cv::Mat> img_list) {
PPOCR ocr = PPOCR();
vector<string> result;
std::vector<std::vector<OCRPredictResult>> ocr_results =
ocr.ocr(img_list, FLAGS_det, FLAGS_rec, FLAGS_cls);
for (int i = 0; i < img_list.size(); ++i) {
//Utility::print_result(ocr_results[i]);
result.push_back(return_result(ocr_results[i]));
}
return result;
}
int main(int argc, char** argv) {
vector<string> result;
high_resolution_clock::time_point startTime, endTime;
cv::Mat image1 = cv::imread("./img/test1.png");
cv::Mat image2 = cv::imread("./img/test2.png");
cv::Mat image3 = cv::imread("./img/test3.png");
cv::Mat image4 = cv::imread("./img/test4.png");
cv::Mat image5 = cv::imread("./img/test5.png");
vector<cv::Mat> img_list;
img_list.push_back(image1);
img_list.push_back(image2);
img_list.push_back(image3);
img_list.push_back(image4);
img_list.push_back(image5);
startTime = high_resolution_clock::now();
result = ocr(img_list);
endTime = high_resolution_clock::now();
long interval_time = (duration_cast<milliseconds>(endTime - startTime).count());
printf("\r\ntime = %d ", interval_time);
for (int i = 0; i < result.size(); i++)
{
cout << result[i] << "\r\n";
}
cout << std::endl;
}
测试没错,开始生成DLL的过程,参考博客
Win10 + C++ + Paddle编译成DLL C++调用OCR文字识别_paddleocr c++如何使用_weixin_45052870的博客-CSDN博客
生成DLL文件
修改一下args.cpp 将能放在一起的外部文件都放在release文件夹下
// 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.
#include <gflags/gflags.h>
// common args
DEFINE_bool(use_gpu, true, "Infering with GPU or CPU.");
DEFINE_bool(use_tensorrt, false, "Whether use tensorrt.");
DEFINE_int32(gpu_id, 0, "Device id of GPU to execute.");
DEFINE_int32(gpu_mem, 4000, "GPU id when infering with GPU.");
DEFINE_int32(cpu_threads, 10, "Num of threads with CPU.");
DEFINE_bool(enable_mkldnn, false, "Whether use mkldnn with CPU.");
DEFINE_string(precision, "fp32", "Precision be one of fp32/fp16/int8");
DEFINE_bool(benchmark, false, "Whether use benchmark.");
DEFINE_string(output, "./output/", "Save benchmark log path.");
DEFINE_string(image_dir, "./img", "Dir of input image.");
DEFINE_string(
type, "ocr",
"Perform ocr or structure, the value is selected in ['ocr','structure'].");
// detection related
DEFINE_string(det_model_dir, "det", "Path of det inference model.");
DEFINE_string(limit_type, "max", "limit_type of input image.");
DEFINE_int32(limit_side_len, 960, "limit_side_len of input image.");
DEFINE_double(det_db_thresh, 0.3, "Threshold of det_db_thresh.");
DEFINE_double(det_db_box_thresh, 0.6, "Threshold of det_db_box_thresh.");
DEFINE_double(det_db_unclip_ratio, 1.5, "Threshold of det_db_unclip_ratio.");
DEFINE_bool(use_dilation, false, "Whether use the dilation on output map.");
DEFINE_string(det_db_score_mode, "slow", "Whether use polygon score.");
DEFINE_bool(visualize, true, "Whether show the detection results.");
// classification related
DEFINE_bool(use_angle_cls, false, "Whether use use_angle_cls.");
DEFINE_string(cls_model_dir, "", "Path of cls inference model.");
DEFINE_double(cls_thresh, 0.9, "Threshold of cls_thresh.");
DEFINE_int32(cls_batch_num, 1, "cls_batch_num.");
// recognition related
DEFINE_string(rec_model_dir, "rec", "Path of rec inference model.");
DEFINE_int32(rec_batch_num, 6, "rec_batch_num.");
DEFINE_string(rec_char_dict_path, "ppocr_keys_v1.txt",
"Path of dictionary.");
DEFINE_int32(rec_img_h, 48, "rec image height");
DEFINE_int32(rec_img_w, 320, "rec image width");
// layout model related
DEFINE_string(layout_model_dir, "", "Path of table layout inference model.");
DEFINE_string(layout_dict_path,
"../../ppocr/utils/dict/layout_dict/layout_publaynet_dict.txt",
"Path of dictionary.");
DEFINE_double(layout_score_threshold, 0.5, "Threshold of score.");
DEFINE_double(layout_nms_threshold, 0.5, "Threshold of nms.");
// structure model related
DEFINE_string(table_model_dir, "", "Path of table struture inference model.");
DEFINE_int32(table_max_len, 488, "max len size of input image.");
DEFINE_int32(table_batch_num, 1, "table_batch_num.");
DEFINE_bool(merge_no_span_structure, true,
"Whether merge <td> and </td> to <td></td>");
DEFINE_string(table_char_dict_path,
"../../ppocr/utils/dict/table_structure_dict_ch.txt",
"Path of dictionary.");
// ocr forward related
DEFINE_bool(det, true, "Whether use det in forward.");
DEFINE_bool(rec, true, "Whether use rec in forward.");
DEFINE_bool(cls, false, "Whether use cls in forward.");
DEFINE_bool(table, false, "Whether use table structure in forward.");
DEFINE_bool(layout, false, "Whether use layout analysis in forward.");
然后修改代码main.cpp
// 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.
#include "opencv2/core.hpp"
#include "opencv2/imgcodecs.hpp"
#include "opencv2/imgproc.hpp"
#include <iostream>
#include <vector>
#include <include/args.h>
#include <include/paddleocr.h>
#include <include/paddlestructure.h>
#include <chrono>
#include "include/ppocr.h"
using namespace std::chrono;
using namespace PaddleOCR;
using namespace std;
string return_result(const vector<OCRPredictResult>& ocr_result) {
std::string rec_result;
for (int i = 0; i < ocr_result.size(); i++) {
//这里的ocr_result.size()是单张图片内识别的多个字符串
if (ocr_result[i].score != -1.0) {
rec_result += ocr_result[i].text;
}
}
//cout << "rec text: " << rec_result;
//cout << std::endl;
return rec_result;
}
__declspec(dllexport) vector<string> ocr(vector<cv::Mat> img_list) {
PPOCR ocr = PPOCR();
vector<string> result;
std::vector<std::vector<OCRPredictResult>> ocr_results =
ocr.ocr(img_list, FLAGS_det, FLAGS_rec, FLAGS_cls);
for (int i = 0; i < img_list.size(); ++i) {
//Utility::print_result(ocr_results[i]);
result.push_back(return_result(ocr_results[i]));
}
return result;
}
新建ppocr.h文件
#pragma once
///c+ +
#pragma once
#ifndef IMAGE_API
#define IMAGE_API
#include "opencv2/core.hpp"
#include "opencv2/imgcodecs.hpp"
#include "opencv2/imgproc.hpp"
#include <iostream>
#include <vector>
#include <include/args.h>
#include <include/paddleocr.h>
#include <include/paddlestructure.h>
using namespace std::chrono;
using namespace PaddleOCR;
using namespace std;
extern "C"
{
// 图像推理
__declspec(dllexport) vector<string> ocr(vector<cv::Mat> img_list);
}
#endif
///
然后编译出ppocr.dll
新建另一个工程进行测试
随便新建一个带命令行的工程,将上述工程中的全部文件拷贝到工程目录下(这一步是为了能使用调试器)
然后修改该工程代码 读取DLL并且调用函数
HMODULE dllHandle = LoadLibrary(L"ppocr.dll");
if (!dllHandle) {
std::cerr << "Error loading ppocr.dll" << std::endl;
return 1;
}
// 获取 ocr 函数的地址
OcrFunction ocrFunc = reinterpret_cast<OcrFunction>(GetProcAddress(dllHandle, "ocr"));
if (!ocrFunc) {
std::cerr << "Error getting ocr function address" << std::endl;
return 1;
}
// 调用 ocr 函数
std::vector<std::string> result = ocrFunc(imgList);
然后调试器运行得到结果
如果需要在release里直接运行exe 需要把所有模型和dll依赖都放到releas里
再测试一下,运行正常