Merge pull request #5648 from WenmuZhou/fix_cpp_lite_android

update db postprocess params

deploy/cpp_infer/include/ocr_det.h

@@ -45,8 +45,9 @@ public:
                       const double &det_db_thresh,
                       const double &det_db_box_thresh,
                       const double &det_db_unclip_ratio,
-                      const bool &use_polygon_score, const bool &visualize,
-                      const bool &use_tensorrt, const std::string &precision) {
+                      const bool &use_polygon_score, const bool &use_dilation,
+                      const bool &visualize, const bool &use_tensorrt,
+                      const std::string &precision) {
     this->use_gpu_ = use_gpu;
     this->gpu_id_ = gpu_id;
     this->gpu_mem_ = gpu_mem;
@@ -59,6 +60,7 @@ public:
     this->det_db_box_thresh_ = det_db_box_thresh;
     this->det_db_unclip_ratio_ = det_db_unclip_ratio;
     this->use_polygon_score_ = use_polygon_score;
+    this->use_dilation_ = use_dilation;
 
     this->visualize_ = visualize;
     this->use_tensorrt_ = use_tensorrt;
@@ -71,7 +73,8 @@ public:
   void LoadModel(const std::string &model_dir);
 
   // Run predictor
-  void Run(cv::Mat &img, std::vector<std::vector<std::vector<int>>> &boxes, std::vector<double> *times);
+  void Run(cv::Mat &img, std::vector<std::vector<std::vector<int>>> &boxes,
+           std::vector<double> *times);
 
 private:
   std::shared_ptr<Predictor> predictor_;
@@ -88,6 +91,7 @@ private:
   double det_db_box_thresh_ = 0.5;
   double det_db_unclip_ratio_ = 2.0;
   bool use_polygon_score_ = false;
+  bool use_dilation_ = false;
 
   bool visualize_ = true;
   bool use_tensorrt_ = false;

deploy/cpp_infer/readme.md

@@ -4,16 +4,20 @@
 C++在性能计算上优于python，因此，在大多数CPU、GPU部署场景，多采用C++的部署方式，本节将介绍如何在Linux\Windows (CPU\GPU)环境下配置C++环境并完成
 PaddleOCR模型部署。
 
-* [1. 准备环境](#1)
-  + [1.0 运行准备](#10)
-  + [1.1 编译opencv库](#11)
-  + [1.2 下载或者编译Paddle预测库](#12)
-    - [1.2.1 直接下载安装](#121)
-    - [1.2.2 预测库源码编译](#122)
-* [2 开始运行](#2)
-  + [2.1 将模型导出为inference model](#21)
-  + [2.2 编译PaddleOCR C++预测demo](#22)
-  + [2.3运行demo](#23)
+- [服务器端C++预测](#服务器端c预测)
+  - [1. 准备环境](#1-准备环境)
+    - [1.0 运行准备](#10-运行准备)
+    - [1.1 编译opencv库](#11-编译opencv库)
+    - [1.2 下载或者编译Paddle预测库](#12-下载或者编译paddle预测库)
+      - [1.2.1 直接下载安装](#121-直接下载安装)
+      - [1.2.2 预测库源码编译](#122-预测库源码编译)
+  - [2 开始运行](#2-开始运行)
+    - [2.1 将模型导出为inference model](#21-将模型导出为inference-model)
+    - [2.2 编译PaddleOCR C++预测demo](#22-编译paddleocr-c预测demo)
+    - [2.3 运行demo](#23-运行demo)
+        - [1. 只调用检测：](#1-只调用检测)
+        - [2. 只调用识别：](#2-只调用识别)
+        - [3. 调用串联：](#3-调用串联)
 
 <a name="1"></a>
 
@@ -103,7 +107,7 @@ opencv3/
 
 #### 1.2.1 直接下载安装
 
-* [Paddle预测库官网](https://paddle-inference.readthedocs.io/en/latest/user_guides/download_lib.html) 上提供了不同cuda版本的Linux预测库，可以在官网查看并选择合适的预测库版本（*建议选择paddle版本>=2.0.1版本的预测库* ）。
+* [Paddle预测库官网](https://paddleinference.paddlepaddle.org.cn/user_guides/download_lib.html#linux) 上提供了不同cuda版本的Linux预测库，可以在官网查看并选择合适的预测库版本（*建议选择paddle版本>=2.0.1版本的预测库* ）。
 
 * 下载之后使用下面的方法解压。
 
@@ -249,7 +253,7 @@ CUDNN_LIB_DIR=/your_cudnn_lib_dir
 |gpu_id|int|0|GPU id，使用GPU时有效|
 |gpu_mem|int|4000|申请的GPU内存|
 |cpu_math_library_num_threads|int|10|CPU预测时的线程数，在机器核数充足的情况下，该值越大，预测速度越快|
-|use_mkldnn|bool|true|是否使用mkldnn库|
+|enable_mkldnn|bool|true|是否使用mkldnn库|
 
 - 检测模型相关
 

deploy/cpp_infer/readme_en.md

@@ -78,7 +78,7 @@ opencv3/
 
 #### 1.2.1 Direct download and installation
 
-[Paddle inference library official website](https://paddle-inference.readthedocs.io/en/latest/user_guides/download_lib.html). You can review and select the appropriate version of the inference library on the official website.
+[Paddle inference library official website](https://paddleinference.paddlepaddle.org.cn/user_guides/download_lib.html#linux). You can review and select the appropriate version of the inference library on the official website.
 
 
 * After downloading, use the following command to extract files.
@@ -231,7 +231,7 @@ More parameters are as follows,
 |gpu_id|int|0|GPU id when use_gpu is true|
 |gpu_mem|int|4000|GPU memory requested|
 |cpu_math_library_num_threads|int|10|Number of threads when using CPU inference. When machine cores is enough, the large the value, the faster the inference speed|
-|use_mkldnn|bool|true|Whether to use mkdlnn library|
+|enable_mkldnn|bool|true|Whether to use mkdlnn library|
 
 - Detection related parameters
 

deploy/cpp_infer/src/ocr_det.cpp

@@ -14,7 +14,6 @@
 
 #include <include/ocr_det.h>
 
-
 namespace PaddleOCR {
 
 void DBDetector::LoadModel(const std::string &model_dir) {
@@ -30,13 +29,10 @@ void DBDetector::LoadModel(const std::string &model_dir) {
       if (this->precision_ == "fp16") {
         precision = paddle_infer::Config::Precision::kHalf;
       }
-     if (this->precision_ == "int8") {
+      if (this->precision_ == "int8") {
         precision = paddle_infer::Config::Precision::kInt8;
-      } 
-      config.EnableTensorRtEngine(
-          1 << 20, 10, 3,
-          precision,
-          false, false);
+      }
+      config.EnableTensorRtEngine(1 << 20, 10, 3, precision, 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}},
@@ -105,7 +101,7 @@ void DBDetector::Run(cv::Mat &img,
   cv::Mat srcimg;
   cv::Mat resize_img;
   img.copyTo(srcimg);
-  
+
   auto preprocess_start = std::chrono::steady_clock::now();
   this->resize_op_.Run(img, resize_img, this->max_side_len_, ratio_h, ratio_w,
                        this->use_tensorrt_);
@@ -116,16 +112,16 @@ void DBDetector::Run(cv::Mat &img,
   std::vector<float> input(1 * 3 * resize_img.rows * resize_img.cols, 0.0f);
   this->permute_op_.Run(&resize_img, input.data());
   auto preprocess_end = std::chrono::steady_clock::now();
-    
+
   // 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});
   auto inference_start = std::chrono::steady_clock::now();
   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]);
@@ -136,7 +132,7 @@ void DBDetector::Run(cv::Mat &img,
   out_data.resize(out_num);
   output_t->CopyToCpu(out_data.data());
   auto inference_end = std::chrono::steady_clock::now();
-  
+
   auto postprocess_start = std::chrono::steady_clock::now();
   int n2 = output_shape[2];
   int n3 = output_shape[3];
@@ -157,24 +153,29 @@ void DBDetector::Run(cv::Mat &img,
   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);
+  if (this->use_dilation_) {
+    cv::Mat dila_ele =
+        cv::getStructuringElement(cv::MORPH_RECT, cv::Size(2, 2));
+    cv::dilate(bit_map, bit_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_);
+      pred_map, bit_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);
   auto postprocess_end = std::chrono::steady_clock::now();
   std::cout << "Detected boxes num: " << boxes.size() << endl;
 
-  std::chrono::duration<float> preprocess_diff = preprocess_end - preprocess_start;
+  std::chrono::duration<float> preprocess_diff =
+      preprocess_end - preprocess_start;
   times->push_back(double(preprocess_diff.count() * 1000));
   std::chrono::duration<float> inference_diff = inference_end - inference_start;
   times->push_back(double(inference_diff.count() * 1000));
-  std::chrono::duration<float> postprocess_diff = postprocess_end - postprocess_start;
+  std::chrono::duration<float> postprocess_diff =
+      postprocess_end - postprocess_start;
   times->push_back(double(postprocess_diff.count() * 1000));
-    
+
   //// visualization
   if (this->visualize_) {
     Utility::VisualizeBboxes(srcimg, boxes);