merge all

deploy/cpp_infer/CMakeLists.txt

-project(ocr_system CXX C)
+project(ppocr CXX C)
 
 option(WITH_MKL        "Compile demo with MKL/OpenBlas support, default use MKL."       ON)
 option(WITH_GPU        "Compile demo with GPU/CPU, default use CPU."                    OFF)
@@ -11,7 +11,7 @@ SET(CUDA_LIB "" CACHE PATH "Location of libraries")
 SET(CUDNN_LIB "" CACHE PATH "Location of libraries")
 SET(TENSORRT_DIR "" CACHE PATH "Compile demo with TensorRT")
 
-set(DEMO_NAME "ocr_system")
+set(DEMO_NAME "ppocr")
 
 
 macro(safe_set_static_flag)
@@ -206,7 +206,7 @@ endif()
 
 set(DEPS ${DEPS} ${OpenCV_LIBS})
 
-AUX_SOURCE_DIRECTORY(./src_system SRCS)
+AUX_SOURCE_DIRECTORY(./src SRCS)
 add_executable(${DEMO_NAME} ${SRCS})
 
 target_link_libraries(${DEMO_NAME} ${DEPS})

deploy/cpp_infer/include/clipper.h

@@ -31,6 +31,8 @@
 *                                                                              *
 *******************************************************************************/
 
+#pragma once
+
 #ifndef clipper_hpp
 #define clipper_hpp
 

deploy/cpp_infer/include/ocr_cls.h

@@ -12,6 +12,8 @@
 // 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"

deploy/cpp_infer/include/ocr_rec.h

@@ -12,6 +12,8 @@
 // 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"

deploy/cpp_infer/src_system/main.cpp → deploy/cpp_infer/src/main.cpp

@@ -29,6 +29,7 @@
 
 #include <glog/logging.h>
 #include <include/ocr_det.h>
+#include <include/ocr_cls.h>
 #include <include/ocr_rec.h>
 #include <sys/stat.h>
 
@@ -39,7 +40,9 @@ 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_math_library_num_threads, 10, "Num of threads with CPU.");
 DEFINE_bool(use_mkldnn, false, "Whether use mkldnn with CPU.");
-
+DEFINE_bool(use_tensorrt, false, "Whether use tensorrt.");
+DEFINE_bool(use_fp16, false, "Whether use fp16 when use tensorrt.");
+// detection related
 DEFINE_string(image_dir, "", "Dir of input image.");
 DEFINE_string(det_model_dir, "", "Path of det inference model.");
 DEFINE_int32(max_side_len, 960, "max_side_len of input image.");
@@ -48,16 +51,14 @@ DEFINE_double(det_db_box_thresh, 0.5, "Threshold of det_db_box_thresh.");
 DEFINE_double(det_db_unclip_ratio, 1.6, "Threshold of det_db_unclip_ratio.");
 DEFINE_bool(use_polygon_score, false, "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.");
-
+// recognition related
 DEFINE_string(rec_model_dir, "", "Path of rec inference model.");
 DEFINE_string(char_list_file, "../../ppocr/utils/ppocr_keys_v1.txt", "Path of dictionary.");
 
-DEFINE_bool(use_tensorrt, false, "Whether use tensorrt.");
-DEFINE_bool(use_fp16, false, "Whether use fp16 when use tensorrt.");
 
 using namespace std;
 using namespace cv;
@@ -131,83 +132,205 @@ cv::Mat GetRotateCropImage(const cv::Mat &srcimage,
 }
 
 
-int main(int argc, char **argv) {
-  // Parsing command-line
-  google::ParseCommandLineFlags(&argc, &argv, true);
-  if ((FLAGS_det_model_dir.empty() || FLAGS_rec_model_dir.empty() || FLAGS_image_dir.empty()) ||
-     (FLAGS_use_angle_cls && FLAGS_cls_model_dir.empty())) {
-    std::cout << "Usage[default]: ./ocr_system --det_model_dir=/PATH/TO/DET_INFERENCE_MODEL/ "
-                << "--rec_model_dir=/PATH/TO/REC_INFERENCE_MODEL/ "
-                << "--image_dir=/PATH/TO/INPUT/IMAGE/" << std::endl;
-    std::cout << "Usage[use angle cls]: ./ocr_system --det_model_dir=/PATH/TO/DET_INFERENCE_MODEL/ "
-                << "--use_angle_cls=true "
-                << "--cls_model_dir=/PATH/TO/CLS_INFERENCE_MODEL/ "
-                << "--rec_model_dir=/PATH/TO/REC_INFERENCE_MODEL/ "
-                << "--image_dir=/PATH/TO/INPUT/IMAGE/" << std::endl;
-    return -1;
-  }
+int main_det(int argc, char **argv) {
+    // Parsing command-line
+    google::ParseCommandLineFlags(&argc, &argv, true);
+    if (FLAGS_det_model_dir.empty() || FLAGS_image_dir.empty()) {
+        std::cout << "Usage[det]: ./ppocr --det_model_dir=/PATH/TO/DET_INFERENCE_MODEL/ "
+                  << "--image_dir=/PATH/TO/INPUT/IMAGE/" << std::endl;      
+        exit(1);      
+    }  
+    if (!PathExists(FLAGS_image_dir)) {
+        std::cerr << "[ERROR] image path not exist! image_dir: " << FLAGS_image_dir << endl;
+        exit(1);      
+    }
+    
+    std::vector<cv::String> cv_all_img_names;
+    cv::glob(FLAGS_image_dir, cv_all_img_names);
+    std::cout << "total images num: " << cv_all_img_names.size() << endl;
+    
+    DBDetector det(FLAGS_det_model_dir, FLAGS_use_gpu, FLAGS_gpu_id,
+                   FLAGS_gpu_mem, FLAGS_cpu_math_library_num_threads, 
+                   FLAGS_use_mkldnn, FLAGS_max_side_len, FLAGS_det_db_thresh,
+                   FLAGS_det_db_box_thresh, FLAGS_det_db_unclip_ratio,
+                   FLAGS_use_polygon_score, FLAGS_visualize,
+                   FLAGS_use_tensorrt, FLAGS_use_fp16);
+
+    auto start = std::chrono::system_clock::now();
+
+    for (int i = 0; i < cv_all_img_names.size(); ++i) {
+      LOG(INFO) << "The predict img: " << cv_all_img_names[i];
+
+      cv::Mat srcimg = cv::imread(cv_all_img_names[i], cv::IMREAD_COLOR);
+      if (!srcimg.data) {
+        std::cerr << "[ERROR] image read failed! image path: " << cv_all_img_names[i] << endl;
+        exit(1);
+      }
+      std::vector<std::vector<std::vector<int>>> boxes;
+
+      det.Run(srcimg, boxes);
+
+      auto end = std::chrono::system_clock::now();
+      auto duration =
+          std::chrono::duration_cast<std::chrono::microseconds>(end - start);
+      std::cout << "Cost  "
+                << double(duration.count()) *
+                       std::chrono::microseconds::period::num /
+                       std::chrono::microseconds::period::den
+                << "s" << std::endl;
+    }
+    
+    return 0;
+}
 
-  if (!PathExists(FLAGS_image_dir)) {
-      std::cerr << "[ERROR] image path not exist! image_dir: " << FLAGS_image_dir << endl;
-      exit(1);      
-  }
-  std::vector<cv::String> cv_all_img_names;
-  cv::glob(FLAGS_image_dir, cv_all_img_names);
-  std::cout << "total images num: " << cv_all_img_names.size() << endl;
-
-  DBDetector det(FLAGS_det_model_dir, FLAGS_use_gpu, FLAGS_gpu_id,
-                 FLAGS_gpu_mem, FLAGS_cpu_math_library_num_threads, 
-                 FLAGS_use_mkldnn, FLAGS_max_side_len, FLAGS_det_db_thresh,
-                 FLAGS_det_db_box_thresh, FLAGS_det_db_unclip_ratio,
-                 FLAGS_use_polygon_score, FLAGS_visualize,
-                 FLAGS_use_tensorrt, FLAGS_use_fp16);
-
-  Classifier *cls = nullptr;
-  if (FLAGS_use_angle_cls) {
-    cls = new Classifier(FLAGS_cls_model_dir, FLAGS_use_gpu, FLAGS_gpu_id,
-                         FLAGS_gpu_mem, FLAGS_cpu_math_library_num_threads,
-                         FLAGS_use_mkldnn, FLAGS_cls_thresh,
-                         FLAGS_use_tensorrt, FLAGS_use_fp16);
-  }
 
-  CRNNRecognizer rec(FLAGS_rec_model_dir, FLAGS_use_gpu, FLAGS_gpu_id,
-                     FLAGS_gpu_mem, FLAGS_cpu_math_library_num_threads,
-                     FLAGS_use_mkldnn, FLAGS_char_list_file,
-                     FLAGS_use_tensorrt, FLAGS_use_fp16);
+int main_rec(int argc, char **argv) {
+    // Parsing command-line
+    google::ParseCommandLineFlags(&argc, &argv, true);
+    if (FLAGS_rec_model_dir.empty() || FLAGS_image_dir.empty()) {
+        std::cout << "Usage[rec]: ./ppocr --rec_model_dir=/PATH/TO/REC_INFERENCE_MODEL/ "
+                  << "--image_dir=/PATH/TO/INPUT/IMAGE/" << std::endl;      
+        exit(1);      
+    }
+    if (!PathExists(FLAGS_image_dir)) {
+        std::cerr << "[ERROR] image path not exist! image_dir: " << FLAGS_image_dir << endl;
+        exit(1);      
+    }
+    
+    std::vector<cv::String> cv_all_img_names;
+    cv::glob(FLAGS_image_dir, cv_all_img_names);
+    std::cout << "total images num: " << cv_all_img_names.size() << endl;
+    
+    CRNNRecognizer rec(FLAGS_rec_model_dir, FLAGS_use_gpu, FLAGS_gpu_id,
+                       FLAGS_gpu_mem, FLAGS_cpu_math_library_num_threads,
+                       FLAGS_use_mkldnn, FLAGS_char_list_file,
+                       FLAGS_use_tensorrt, FLAGS_use_fp16);
+
+    auto start = std::chrono::system_clock::now();
+
+    for (int i = 0; i < cv_all_img_names.size(); ++i) {
+      LOG(INFO) << "The predict img: " << cv_all_img_names[i];
+
+      cv::Mat srcimg = cv::imread(cv_all_img_names[i], cv::IMREAD_COLOR);
+      if (!srcimg.data) {
+        std::cerr << "[ERROR] image read failed! image path: " << cv_all_img_names[i] << endl;
+        exit(1);
+      }
 
-  auto start = std::chrono::system_clock::now();
+      rec.Run(srcimg);
+        
+      auto end = std::chrono::system_clock::now();
+      auto duration =
+          std::chrono::duration_cast<std::chrono::microseconds>(end - start);
+      std::cout << "Cost  "
+                << double(duration.count()) *
+                       std::chrono::microseconds::period::num /
+                       std::chrono::microseconds::period::den
+                << "s" << std::endl;
+    }
+    
+    return 0;
+}
 
-  for (int i = 0; i < cv_all_img_names.size(); ++i) {
-    LOG(INFO) << "The predict img: " << cv_all_img_names[i];
 
-    cv::Mat srcimg = cv::imread(FLAGS_image_dir, cv::IMREAD_COLOR);
-    if (!srcimg.data) {
-      std::cerr << "[ERROR] image read failed! image path: " << cv_all_img_names[i] << endl;
-      exit(1);
+int main_system(int argc, char **argv) {
+    // Parsing command-line
+    google::ParseCommandLineFlags(&argc, &argv, true);
+    if ((FLAGS_det_model_dir.empty() || FLAGS_rec_model_dir.empty() || FLAGS_image_dir.empty()) ||
+       (FLAGS_use_angle_cls && FLAGS_cls_model_dir.empty())) {
+        std::cout << "Usage[system without angle cls]: ./ppocr --det_model_dir=/PATH/TO/DET_INFERENCE_MODEL/ "
+                    << "--rec_model_dir=/PATH/TO/REC_INFERENCE_MODEL/ "
+                    << "--image_dir=/PATH/TO/INPUT/IMAGE/" << std::endl;
+        std::cout << "Usage[system with angle cls]: ./ppocr --det_model_dir=/PATH/TO/DET_INFERENCE_MODEL/ "
+                    << "--use_angle_cls=true "
+                    << "--cls_model_dir=/PATH/TO/CLS_INFERENCE_MODEL/ "
+                    << "--rec_model_dir=/PATH/TO/REC_INFERENCE_MODEL/ "
+                    << "--image_dir=/PATH/TO/INPUT/IMAGE/" << std::endl;
+        exit(1);      
     }
-    std::vector<std::vector<std::vector<int>>> boxes;
+    if (!PathExists(FLAGS_image_dir)) {
+        std::cerr << "[ERROR] image path not exist! image_dir: " << FLAGS_image_dir << endl;
+        exit(1);      
+    }
+    
+    std::vector<cv::String> cv_all_img_names;
+    cv::glob(FLAGS_image_dir, cv_all_img_names);
+    std::cout << "total images num: " << cv_all_img_names.size() << endl;
+    
+    DBDetector det(FLAGS_det_model_dir, FLAGS_use_gpu, FLAGS_gpu_id,
+                   FLAGS_gpu_mem, FLAGS_cpu_math_library_num_threads, 
+                   FLAGS_use_mkldnn, FLAGS_max_side_len, FLAGS_det_db_thresh,
+                   FLAGS_det_db_box_thresh, FLAGS_det_db_unclip_ratio,
+                   FLAGS_use_polygon_score, FLAGS_visualize,
+                   FLAGS_use_tensorrt, FLAGS_use_fp16);
+
+    Classifier *cls = nullptr;
+    if (FLAGS_use_angle_cls) {
+      cls = new Classifier(FLAGS_cls_model_dir, FLAGS_use_gpu, FLAGS_gpu_id,
+                           FLAGS_gpu_mem, FLAGS_cpu_math_library_num_threads,
+                           FLAGS_use_mkldnn, FLAGS_cls_thresh,
+                           FLAGS_use_tensorrt, FLAGS_use_fp16);
+    }
+
+    CRNNRecognizer rec(FLAGS_rec_model_dir, FLAGS_use_gpu, FLAGS_gpu_id,
+                       FLAGS_gpu_mem, FLAGS_cpu_math_library_num_threads,
+                       FLAGS_use_mkldnn, FLAGS_char_list_file,
+                       FLAGS_use_tensorrt, FLAGS_use_fp16);
+
+    auto start = std::chrono::system_clock::now();
 
-    det.Run(srcimg, boxes);
-  
-    cv::Mat crop_img;
-    for (int j = 0; j < boxes.size(); j++) {
-      crop_img = GetRotateCropImage(srcimg, boxes[j]);
+    for (int i = 0; i < cv_all_img_names.size(); ++i) {
+      LOG(INFO) << "The predict img: " << cv_all_img_names[i];
 
-      if (cls != nullptr) {
-        crop_img = cls->Run(crop_img);
+      cv::Mat srcimg = cv::imread(FLAGS_image_dir, cv::IMREAD_COLOR);
+      if (!srcimg.data) {
+        std::cerr << "[ERROR] image read failed! image path: " << cv_all_img_names[i] << endl;
+        exit(1);
       }
-      rec.Run(crop_img);
+      std::vector<std::vector<std::vector<int>>> boxes;
+
+      det.Run(srcimg, boxes);
+    
+      cv::Mat crop_img;
+      for (int j = 0; j < boxes.size(); j++) {
+        crop_img = GetRotateCropImage(srcimg, boxes[j]);
+
+        if (cls != nullptr) {
+          crop_img = cls->Run(crop_img);
+        }
+        rec.Run(crop_img);
+      }
+        
+      auto end = std::chrono::system_clock::now();
+      auto duration =
+          std::chrono::duration_cast<std::chrono::microseconds>(end - start);
+      std::cout << "Cost  "
+                << double(duration.count()) *
+                       std::chrono::microseconds::period::num /
+                       std::chrono::microseconds::period::den
+                << "s" << std::endl;
     }
       
-    auto end = std::chrono::system_clock::now();
-    auto duration =
-        std::chrono::duration_cast<std::chrono::microseconds>(end - start);
-    std::cout << "Cost  "
-              << double(duration.count()) *
-                     std::chrono::microseconds::period::num /
-                     std::chrono::microseconds::period::den
-              << "s" << std::endl;
-  }
+    return 0;
+}
+
 
-  return 0;
+int main(int argc, char **argv) {
+  if (strcmp(argv[1], "det")!=0 && strcmp(argv[1], "rec")!=0 && strcmp(argv[1], "system")!=0) {
+      std::cout << "Please choose one mode of [det, rec, system] !" << std::endl;
+      return -1;
+  }
+  std::cout << "mode: " << argv[1] << endl;
+      
+  if (strcmp(argv[1], "det")==0) {
+      return main_det(argc, argv);
+  }
+  if (strcmp(argv[1], "rec")==0) {
+      return main_rec(argc, argv);
+  }    
+  if (strcmp(argv[1], "system")==0) {
+      return main_system(argc, argv);
+  } 
+    
+//   return 0;
 }

deploy/cpp_infer/src_det/ocr_det.cpp → deploy/cpp_infer/src/ocr_det.cpp

@@ -13,8 +13,7 @@
 // limitations under the License.
 
 #include <include/ocr_det.h>
-#include <include/preprocess_op.cpp>
-#include <include/postprocess_op.cpp>
+
 
 namespace PaddleOCR {
 

deploy/cpp_infer/src_det/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 "glog/logging.h"
-#include "omp.h"
-#include "opencv2/core.hpp"
-#include "opencv2/imgcodecs.hpp"
-#include "opencv2/imgproc.hpp"
-#include <chrono>
-#include <iomanip>
-#include <iostream>
-#include <ostream>
-#include <vector>
-
-#include <cstring>
-#include <fstream>
-#include <numeric>
-
-#include <glog/logging.h>
-#include <include/ocr_det.h>
-#include <sys/stat.h>
-
-#include <gflags/gflags.h>
-
-DEFINE_bool(use_gpu, false, "Infering with GPU or CPU.");
-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_math_library_num_threads, 10, "Num of threads with CPU.");
-DEFINE_bool(use_mkldnn, false, "Whether use mkldnn with CPU.");
-
-DEFINE_string(image_dir, "", "Dir of input image.");
-DEFINE_string(det_model_dir, "", "Path of det inference model.");
-DEFINE_int32(max_side_len, 960, "max_side_len of input image.");
-DEFINE_double(det_db_thresh, 0.3, "Threshold of det_db_thresh.");
-DEFINE_double(det_db_box_thresh, 0.5, "Threshold of det_db_box_thresh.");
-DEFINE_double(det_db_unclip_ratio, 1.6, "Threshold of det_db_unclip_ratio.");
-DEFINE_bool(use_polygon_score, false, "Whether use polygon score.");
-DEFINE_bool(visualize, true, "Whether show the detection results.");
-
-DEFINE_bool(use_tensorrt, false, "Whether use tensorrt.");
-DEFINE_bool(use_fp16, false, "Whether use fp16 when use tensorrt.");
-
-
-using namespace std;
-using namespace cv;
-using namespace PaddleOCR;
-
-
-static bool PathExists(const std::string& path){
-#ifdef _WIN32
-  struct _stat buffer;
-  return (_stat(path.c_str(), &buffer) == 0);
-#else
-  struct stat buffer;
-  return (stat(path.c_str(), &buffer) == 0);
-#endif  // !_WIN32
-}
-
-
-int main(int argc, char **argv) {
-  // Parsing command-line
-  google::ParseCommandLineFlags(&argc, &argv, true);
-  if (FLAGS_det_model_dir.empty() || FLAGS_image_dir.empty()) {
-    std::cout << "Usage: ./ocr_det --det_model_dir=/PATH/TO/INFERENCE_MODEL/ "
-                << "--image_dir=/PATH/TO/INPUT/IMAGE/" << std::endl;
-    return -1;
-  }
-
-  if (!PathExists(FLAGS_image_dir)) {
-      std::cerr << "[ERROR] image path not exist! image_dir: " << FLAGS_image_dir << endl;
-      exit(1);      
-  }
-  std::vector<cv::String> cv_all_img_names;
-  cv::glob(FLAGS_image_dir, cv_all_img_names);
-  std::cout << "total images num: " << cv_all_img_names.size() << endl;
-      
-  DBDetector det(FLAGS_det_model_dir, FLAGS_use_gpu, FLAGS_gpu_id,
-                 FLAGS_gpu_mem, FLAGS_cpu_math_library_num_threads, 
-                 FLAGS_use_mkldnn, FLAGS_max_side_len, FLAGS_det_db_thresh,
-                 FLAGS_det_db_box_thresh, FLAGS_det_db_unclip_ratio,
-                 FLAGS_use_polygon_score, FLAGS_visualize,
-                 FLAGS_use_tensorrt, FLAGS_use_fp16);
-
-  auto start = std::chrono::system_clock::now();
-
-  for (int i = 0; i < cv_all_img_names.size(); ++i) {
-    LOG(INFO) << "The predict img: " << cv_all_img_names[i];
-
-    cv::Mat srcimg = cv::imread(cv_all_img_names[i], cv::IMREAD_COLOR);
-    if (!srcimg.data) {
-      std::cerr << "[ERROR] image read failed! image path: " << cv_all_img_names[i] << endl;
-      exit(1);
-    }
-    std::vector<std::vector<std::vector<int>>> boxes;
-
-    det.Run(srcimg, boxes);
-
-    auto end = std::chrono::system_clock::now();
-    auto duration =
-        std::chrono::duration_cast<std::chrono::microseconds>(end - start);
-    std::cout << "Cost  "
-              << double(duration.count()) *
-                     std::chrono::microseconds::period::num /
-                     std::chrono::microseconds::period::den
-              << "s" << std::endl;
-  }
-    
-  return 0;
-}

deploy/cpp_infer/src_rec/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 "glog/logging.h"
-#include "omp.h"
-#include "opencv2/core.hpp"
-#include "opencv2/imgcodecs.hpp"
-#include "opencv2/imgproc.hpp"
-#include <chrono>
-#include <iomanip>
-#include <iostream>
-#include <ostream>
-#include <vector>
-
-#include <cstring>
-#include <fstream>
-#include <numeric>
-
-#include <glog/logging.h>
-#include <include/ocr_rec.h>
-#include <sys/stat.h>
-
-#include <gflags/gflags.h>
-
-DEFINE_bool(use_gpu, false, "Infering with GPU or CPU.");
-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_math_library_num_threads, 10, "Num of threads with CPU.");
-DEFINE_bool(use_mkldnn, false, "Whether use mkldnn with CPU.");
-
-DEFINE_string(image_dir, "", "Dir of input image.");
-DEFINE_string(rec_model_dir, "", "Path of rec inference model.");
-DEFINE_string(char_list_file, "../../ppocr/utils/ppocr_keys_v1.txt", "Path of dictionary.");
-
-DEFINE_bool(use_tensorrt, false, "Whether use tensorrt.");
-DEFINE_bool(use_fp16, false, "Whether use fp16 when use tensorrt.");
-
-
-using namespace std;
-using namespace cv;
-using namespace PaddleOCR;
-
-
-static bool PathExists(const std::string& path){
-#ifdef _WIN32
-  struct _stat buffer;
-  return (_stat(path.c_str(), &buffer) == 0);
-#else
-  struct stat buffer;
-  return (stat(path.c_str(), &buffer) == 0);
-#endif  // !_WIN32
-}
-
-
-int main(int argc, char **argv) {
-  // Parsing command-line
-  google::ParseCommandLineFlags(&argc, &argv, true);
-  if (FLAGS_rec_model_dir.empty() || FLAGS_image_dir.empty()) {
-    std::cout << "Usage: ./ocr_rec --rec_model_dir=/PATH/TO/INFERENCE_MODEL/ "
-                << "--image_dir=/PATH/TO/INPUT/IMAGE/" << std::endl;
-    return -1;
-  }
-
-  if (!PathExists(FLAGS_image_dir)) {
-      std::cerr << "[ERROR] image path not exist! image_dir: " << FLAGS_image_dir << endl;
-      exit(1);      
-  }
-  std::vector<cv::String> cv_all_img_names;
-  cv::glob(FLAGS_image_dir, cv_all_img_names);
-  std::cout << "total images num: " << cv_all_img_names.size() << endl;
-
-  CRNNRecognizer rec(FLAGS_rec_model_dir, FLAGS_use_gpu, FLAGS_gpu_id,
-                     FLAGS_gpu_mem, FLAGS_cpu_math_library_num_threads,
-                     FLAGS_use_mkldnn, FLAGS_char_list_file,
-                     FLAGS_use_tensorrt, FLAGS_use_fp16);
-
-  auto start = std::chrono::system_clock::now();
-
-  for (int i = 0; i < cv_all_img_names.size(); ++i) {
-    LOG(INFO) << "The predict img: " << cv_all_img_names[i];
-
-    cv::Mat srcimg = cv::imread(cv_all_img_names[i], cv::IMREAD_COLOR);
-    if (!srcimg.data) {
-      std::cerr << "[ERROR] image read failed! image path: " << cv_all_img_names[i] << endl;
-      exit(1);
-    }
-
-    rec.Run(srcimg);
-      
-    auto end = std::chrono::system_clock::now();
-    auto duration =
-        std::chrono::duration_cast<std::chrono::microseconds>(end - start);
-    std::cout << "Cost  "
-              << double(duration.count()) *
-                     std::chrono::microseconds::period::num /
-                     std::chrono::microseconds::period::den
-              << "s" << std::endl;
-  }
-
-  return 0;
-}

deploy/cpp_infer/src_rec/ocr_rec.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 <include/ocr_rec.h>
-#include <include/preprocess_op.cpp>
-
-namespace PaddleOCR {
-
-void CRNNRecognizer::Run(cv::Mat &img) {
-  cv::Mat srcimg;
-  img.copyTo(srcimg);
-  cv::Mat resize_img;
-
-  float wh_ratio = float(srcimg.cols) / float(srcimg.rows);
-
-  this->resize_op_.Run(srcimg, resize_img, wh_ratio, this->use_tensorrt_);
-
-  this->normalize_op_.Run(&resize_img, this->mean_, this->scale_,
-                          this->is_scale_);
-
-  std::vector<float> input(1 * 3 * resize_img.rows * resize_img.cols, 0.0f);
-
-  this->permute_op_.Run(&resize_img, input.data());
-
-  // Inference.
-  auto input_names = this->predictor_->GetInputNames();
-  auto input_t = this->predictor_->GetInputHandle(input_names[0]);
-  input_t->Reshape({1, 3, resize_img.rows, resize_img.cols});
-  input_t->CopyFromCpu(input.data());
-  this->predictor_->Run();
-
-  std::vector<float> predict_batch;
-  auto output_names = this->predictor_->GetOutputNames();
-  auto output_t = this->predictor_->GetOutputHandle(output_names[0]);
-  auto predict_shape = output_t->shape();
-
-  int out_num = std::accumulate(predict_shape.begin(), predict_shape.end(), 1,
-                                std::multiplies<int>());
-  predict_batch.resize(out_num);
-
-  output_t->CopyToCpu(predict_batch.data());
-
-  // ctc decode
-  std::vector<std::string> str_res;
-  int argmax_idx;
-  int last_index = 0;
-  float score = 0.f;
-  int count = 0;
-  float max_value = 0.0f;
-
-  for (int n = 0; n < predict_shape[1]; n++) {
-    argmax_idx =
-        int(Utility::argmax(&predict_batch[n * predict_shape[2]],
-                            &predict_batch[(n + 1) * predict_shape[2]]));
-    max_value =
-        float(*std::max_element(&predict_batch[n * predict_shape[2]],
-                                &predict_batch[(n + 1) * predict_shape[2]]));
-
-    if (argmax_idx > 0 && (!(n > 0 && argmax_idx == last_index))) {
-      score += max_value;
-      count += 1;
-      str_res.push_back(label_list_[argmax_idx]);
-    }
-    last_index = argmax_idx;
-  }
-  score /= count;
-  for (int i = 0; i < str_res.size(); i++) {
-    std::cout << str_res[i];
-  }
-  std::cout << "\tscore: " << score << std::endl;
-}
-
-void CRNNRecognizer::LoadModel(const std::string &model_dir) {
-  //   AnalysisConfig config;
-  paddle_infer::Config config;
-  config.SetModel(model_dir + "/inference.pdmodel",
-                  model_dir + "/inference.pdiparams");
-
-  if (this->use_gpu_) {
-    config.EnableUseGpu(this->gpu_mem_, this->gpu_id_);
-    if (this->use_tensorrt_) {
-      config.EnableTensorRtEngine(
-          1 << 20, 10, 3,
-          this->use_fp16_ ? paddle_infer::Config::Precision::kHalf
-                          : paddle_infer::Config::Precision::kFloat32,
-          false, false);
-      std::map<std::string, std::vector<int>> min_input_shape = {
-          {"x", {1, 3, 32, 10}}};
-      std::map<std::string, std::vector<int>> max_input_shape = {
-          {"x", {1, 3, 32, 2000}}};
-      std::map<std::string, std::vector<int>> opt_input_shape = {
-          {"x", {1, 3, 32, 320}}};
-
-      config.SetTRTDynamicShapeInfo(min_input_shape, max_input_shape,
-                                    opt_input_shape);
-    }
-  } else {
-    config.DisableGpu();
-    if (this->use_mkldnn_) {
-      config.EnableMKLDNN();
-      // cache 10 different shapes for mkldnn to avoid memory leak
-      config.SetMkldnnCacheCapacity(10);
-    }
-    config.SetCpuMathLibraryNumThreads(this->cpu_math_library_num_threads_);
-  }
-
-  config.SwitchUseFeedFetchOps(false);
-  // true for multiple input
-  config.SwitchSpecifyInputNames(true);
-
-  config.SwitchIrOptim(true);
-
-  config.EnableMemoryOptim();
-  config.DisableGlogInfo();
-
-  this->predictor_ = CreatePredictor(config);
-}
-
-cv::Mat CRNNRecognizer::GetRotateCropImage(const cv::Mat &srcimage,
-                                           std::vector<std::vector<int>> box) {
-  cv::Mat image;
-  srcimage.copyTo(image);
-  std::vector<std::vector<int>> points = box;
-
-  int x_collect[4] = {box[0][0], box[1][0], box[2][0], box[3][0]};
-  int y_collect[4] = {box[0][1], box[1][1], box[2][1], box[3][1]};
-  int left = int(*std::min_element(x_collect, x_collect + 4));
-  int right = int(*std::max_element(x_collect, x_collect + 4));
-  int top = int(*std::min_element(y_collect, y_collect + 4));
-  int bottom = int(*std::max_element(y_collect, y_collect + 4));
-
-  cv::Mat img_crop;
-  image(cv::Rect(left, top, right - left, bottom - top)).copyTo(img_crop);
-
-  for (int i = 0; i < points.size(); i++) {
-    points[i][0] -= left;
-    points[i][1] -= top;
-  }
-
-  int img_crop_width = int(sqrt(pow(points[0][0] - points[1][0], 2) +
-                                pow(points[0][1] - points[1][1], 2)));
-  int img_crop_height = int(sqrt(pow(points[0][0] - points[3][0], 2) +
-                                 pow(points[0][1] - points[3][1], 2)));
-
-  cv::Point2f pts_std[4];
-  pts_std[0] = cv::Point2f(0., 0.);
-  pts_std[1] = cv::Point2f(img_crop_width, 0.);
-  pts_std[2] = cv::Point2f(img_crop_width, img_crop_height);
-  pts_std[3] = cv::Point2f(0.f, img_crop_height);
-
-  cv::Point2f pointsf[4];
-  pointsf[0] = cv::Point2f(points[0][0], points[0][1]);
-  pointsf[1] = cv::Point2f(points[1][0], points[1][1]);
-  pointsf[2] = cv::Point2f(points[2][0], points[2][1]);
-  pointsf[3] = cv::Point2f(points[3][0], points[3][1]);
-
-  cv::Mat M = cv::getPerspectiveTransform(pointsf, pts_std);
-
-  cv::Mat dst_img;
-  cv::warpPerspective(img_crop, dst_img, M,
-                      cv::Size(img_crop_width, img_crop_height),
-                      cv::BORDER_REPLICATE);
-
-  if (float(dst_img.rows) >= float(dst_img.cols) * 1.5) {
-    cv::Mat srcCopy = cv::Mat(dst_img.rows, dst_img.cols, dst_img.depth());
-    cv::transpose(dst_img, srcCopy);
-    cv::flip(srcCopy, srcCopy, 0);
-    return srcCopy;
-  } else {
-    return dst_img;
-  }
-}
-
-} // namespace PaddleOCR

deploy/cpp_infer/src_system/ocr_det.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 <include/ocr_det.h>
-#include <include/preprocess_op.cpp>
-#include <include/postprocess_op.cpp>
-
-namespace PaddleOCR {
-
-void DBDetector::LoadModel(const std::string &model_dir) {
-  //   AnalysisConfig config;
-  paddle_infer::Config config;
-  config.SetModel(model_dir + "/inference.pdmodel",
-                  model_dir + "/inference.pdiparams");
-
-  if (this->use_gpu_) {
-    config.EnableUseGpu(this->gpu_mem_, this->gpu_id_);
-    if (this->use_tensorrt_) {
-      config.EnableTensorRtEngine(
-          1 << 20, 10, 3,
-          this->use_fp16_ ? paddle_infer::Config::Precision::kHalf
-                          : paddle_infer::Config::Precision::kFloat32,
-          false, false);
-      std::map<std::string, std::vector<int>> min_input_shape = {
-          {"x", {1, 3, 50, 50}},
-          {"conv2d_92.tmp_0", {1, 96, 20, 20}},
-          {"conv2d_91.tmp_0", {1, 96, 10, 10}},
-          {"nearest_interp_v2_1.tmp_0", {1, 96, 10, 10}},
-          {"nearest_interp_v2_2.tmp_0", {1, 96, 20, 20}},
-          {"nearest_interp_v2_3.tmp_0", {1, 24, 20, 20}},
-          {"nearest_interp_v2_4.tmp_0", {1, 24, 20, 20}},
-          {"nearest_interp_v2_5.tmp_0", {1, 24, 20, 20}},
-          {"elementwise_add_7", {1, 56, 2, 2}},
-          {"nearest_interp_v2_0.tmp_0", {1, 96, 2, 2}}};
-      std::map<std::string, std::vector<int>> max_input_shape = {
-          {"x", {1, 3, this->max_side_len_, this->max_side_len_}},
-          {"conv2d_92.tmp_0", {1, 96, 400, 400}},
-          {"conv2d_91.tmp_0", {1, 96, 200, 200}},
-          {"nearest_interp_v2_1.tmp_0", {1, 96, 200, 200}},
-          {"nearest_interp_v2_2.tmp_0", {1, 96, 400, 400}},
-          {"nearest_interp_v2_3.tmp_0", {1, 24, 400, 400}},
-          {"nearest_interp_v2_4.tmp_0", {1, 24, 400, 400}},
-          {"nearest_interp_v2_5.tmp_0", {1, 24, 400, 400}},
-          {"elementwise_add_7", {1, 56, 400, 400}},
-          {"nearest_interp_v2_0.tmp_0", {1, 96, 400, 400}}};
-      std::map<std::string, std::vector<int>> opt_input_shape = {
-          {"x", {1, 3, 640, 640}},
-          {"conv2d_92.tmp_0", {1, 96, 160, 160}},
-          {"conv2d_91.tmp_0", {1, 96, 80, 80}},
-          {"nearest_interp_v2_1.tmp_0", {1, 96, 80, 80}},
-          {"nearest_interp_v2_2.tmp_0", {1, 96, 160, 160}},
-          {"nearest_interp_v2_3.tmp_0", {1, 24, 160, 160}},
-          {"nearest_interp_v2_4.tmp_0", {1, 24, 160, 160}},
-          {"nearest_interp_v2_5.tmp_0", {1, 24, 160, 160}},
-          {"elementwise_add_7", {1, 56, 40, 40}},
-          {"nearest_interp_v2_0.tmp_0", {1, 96, 40, 40}}};
-
-      config.SetTRTDynamicShapeInfo(min_input_shape, max_input_shape,
-                                    opt_input_shape);
-    }
-  } else {
-    config.DisableGpu();
-    if (this->use_mkldnn_) {
-      config.EnableMKLDNN();
-      // cache 10 different shapes for mkldnn to avoid memory leak
-      config.SetMkldnnCacheCapacity(10);
-    }
-    config.SetCpuMathLibraryNumThreads(this->cpu_math_library_num_threads_);
-  }
-  // use zero_copy_run as default
-  config.SwitchUseFeedFetchOps(false);
-  // true for multiple input
-  config.SwitchSpecifyInputNames(true);
-
-  config.SwitchIrOptim(true);
-
-  config.EnableMemoryOptim();
-  // config.DisableGlogInfo();
-
-  this->predictor_ = CreatePredictor(config);
-}
-
-void DBDetector::Run(cv::Mat &img,
-                     std::vector<std::vector<std::vector<int>>> &boxes) {
-  float ratio_h{};
-  float ratio_w{};
-
-  cv::Mat srcimg;
-  cv::Mat resize_img;
-  img.copyTo(srcimg);
-  this->resize_op_.Run(img, resize_img, this->max_side_len_, ratio_h, ratio_w,
-                       this->use_tensorrt_);
-
-  this->normalize_op_.Run(&resize_img, this->mean_, this->scale_,
-                          this->is_scale_);
-
-  std::vector<float> input(1 * 3 * resize_img.rows * resize_img.cols, 0.0f);
-  this->permute_op_.Run(&resize_img, input.data());
-
-  // Inference.
-  auto input_names = this->predictor_->GetInputNames();
-  auto input_t = this->predictor_->GetInputHandle(input_names[0]);
-  input_t->Reshape({1, 3, resize_img.rows, resize_img.cols});
-  input_t->CopyFromCpu(input.data());
-  this->predictor_->Run();
-
-  std::vector<float> out_data;
-  auto output_names = this->predictor_->GetOutputNames();
-  auto output_t = this->predictor_->GetOutputHandle(output_names[0]);
-  std::vector<int> output_shape = output_t->shape();
-  int out_num = std::accumulate(output_shape.begin(), output_shape.end(), 1,
-                                std::multiplies<int>());
-
-  out_data.resize(out_num);
-  output_t->CopyToCpu(out_data.data());
-
-  int n2 = output_shape[2];
-  int n3 = output_shape[3];
-  int n = n2 * n3;
-
-  std::vector<float> pred(n, 0.0);
-  std::vector<unsigned char> cbuf(n, ' ');
-
-  for (int i = 0; i < n; i++) {
-    pred[i] = float(out_data[i]);
-    cbuf[i] = (unsigned char)((out_data[i]) * 255);
-  }
-
-  cv::Mat cbuf_map(n2, n3, CV_8UC1, (unsigned char *)cbuf.data());
-  cv::Mat pred_map(n2, n3, CV_32F, (float *)pred.data());
-
-  const double threshold = this->det_db_thresh_ * 255;
-  const double maxvalue = 255;
-  cv::Mat bit_map;
-  cv::threshold(cbuf_map, bit_map, threshold, maxvalue, cv::THRESH_BINARY);
-  cv::Mat dilation_map;
-  cv::Mat dila_ele = cv::getStructuringElement(cv::MORPH_RECT, cv::Size(2, 2));
-  cv::dilate(bit_map, dilation_map, dila_ele);
-  boxes = post_processor_.BoxesFromBitmap(
-      pred_map, dilation_map, this->det_db_box_thresh_,
-      this->det_db_unclip_ratio_, this->use_polygon_score_);
-
-  boxes = post_processor_.FilterTagDetRes(boxes, ratio_h, ratio_w, srcimg);
-  std::cout << "Detected boxes num: " << boxes.size() << endl;
-    
-  //// visualization
-  if (this->visualize_) {
-    Utility::VisualizeBboxes(srcimg, boxes);
-  }
-}
-
-} // namespace PaddleOCR

deploy/cpp_infer/tools/build.sh

-set -o errexit
-
-if [ $# != 1 ] ; then
-echo "USAGE: $0 MODE (one of ['det', 'rec', 'system'])"
-echo " e.g.: $0 system"
-exit 1;
-fi
-
-# MODE be one of ['det', 'rec', 'system']
-MODE=$1
-cp CMakeLists_$MODE.txt CMakeLists.txt
-
-
 OPENCV_DIR=/paddle/git/new/PaddleOCR/deploy/cpp_infer/opencv-3.4.7/opencv3/
 LIB_DIR=/paddle/git/new/PaddleOCR/deploy/cpp_infer/paddle_inference/
 CUDA_LIB_DIR=/usr/local/cuda/lib64/

deploy/cpp_infer/tools/config.txt

-# model load config
-use_gpu 0
-gpu_id  0
-gpu_mem  4000
-cpu_math_library_num_threads  10
-use_mkldnn 0
-
-# det config
-max_side_len  960
-det_db_thresh  0.3
-det_db_box_thresh  0.5
-det_db_unclip_ratio  1.6
-use_polygon_score 1
-det_model_dir  ./inference/ch_ppocr_mobile_v2.0_det_infer/
-
-# cls config
-use_angle_cls 0
-cls_model_dir  ./inference/ch_ppocr_mobile_v2.0_cls_infer/
-cls_thresh  0.9
-
-# rec config
-rec_model_dir  ./inference/ch_ppocr_mobile_v2.0_rec_infer/
-char_list_file  ../../ppocr/utils/ppocr_keys_v1.txt
-
-# show the detection results
-visualize 0
-
-# use_tensorrt
-use_tensorrt 0
-use_fp16   0
-

deploy/cpp_infer/tools/run.sh

-
-./build/ocr_system ./tools/config.txt ../../doc/imgs/12.jpg