Merge branch 'PaddlePaddle:dygraph' into dygraph

deploy/cpp_infer/readme_en.md

-# Server-side C++ inference
+# Server-side C++ Inference
 
 This chapter introduces the C++ deployment method of the PaddleOCR model, and the corresponding python predictive deployment method refers to [document](../../doc/doc_ch/inference.md).
 C++ is better than python in terms of performance calculation. Therefore, in most CPU and GPU deployment scenarios, C++ deployment is mostly used.
@@ -6,14 +6,14 @@ This section will introduce how to configure the C++ environment and complete it
 PaddleOCR model deployment.
 
 
-## 1. Prepare the environment
+## 1. Prepare the Environment
 
 ### Environment
 
 - Linux, docker is recommended.
 
 
-### 1.1 Compile opencv
+### 1.1 Compile OpenCV
 
 * First of all, you need to download the source code compiled package in the Linux environment from the opencv official website. Taking opencv3.4.7 as an example, the download command is as follows.
 
@@ -73,7 +73,7 @@ opencv3/
 |-- share
 ```
 
-### 1.2 Compile or download or  the Paddle inference library
+### 1.2 Compile or Download or the Paddle Inference Library
 
 * There are 2 ways to obtain the Paddle inference library, described in detail below.
 
@@ -136,7 +136,7 @@ build/paddle_inference_install_dir/
 Among them, `paddle` is the Paddle library required for C++ prediction later, and `version.txt` contains the version information of the current inference library.
 
 
-## 2. Compile and run the demo
+## 2. Compile and Run the Demo
 
 ### 2.1 Export the inference model
 
@@ -183,7 +183,7 @@ or the generated Paddle inference library path (`build/paddle_inference_install_
 Execute the built executable file:  
 ```shell
 ./build/ppocr <mode> [--param1] [--param2] [...]
-```  
+```
 Here, `mode` is a required parameter，and the value range is ['det', 'rec', 'system'], representing using detection only, using recognition only and using the end-to-end system respectively. Specifically,
 
 ##### 1. run det demo:

deploy/cpp_infer/src/main.cpp

@@ -35,15 +35,16 @@
 #include <sys/stat.h>
 
 #include <gflags/gflags.h>
+#include "auto_log/autolog.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_int32(cpu_threads, 10, "Num of threads with CPU.");
+DEFINE_bool(enable_mkldnn, false, "Whether use mkldnn with CPU.");
 DEFINE_bool(use_tensorrt, false, "Whether use tensorrt.");
 DEFINE_string(precision, "fp32", "Precision be one of fp32/fp16/int8");
-DEFINE_bool(benchmark, true, "Whether use benchmark.");
+DEFINE_bool(benchmark, false, "Whether use benchmark.");
 DEFINE_string(save_log_path, "./log_output/", "Save benchmark log path.");
 // detection related
 DEFINE_string(image_dir, "", "Dir of input image.");
@@ -60,6 +61,7 @@ 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_int32(rec_batch_num, 1, "rec_batch_num.");
 DEFINE_string(char_list_file, "../../ppocr/utils/ppocr_keys_v1.txt", "Path of dictionary.");
 
 
@@ -68,34 +70,6 @@ using namespace cv;
 using namespace PaddleOCR;
 
 
-void PrintBenchmarkLog(std::string model_name, 
-                       int batch_size, 
-                       std::string input_shape,
-                       std::vector<double> time_info,
-                       int img_num){
-  LOG(INFO) << "----------------------- Config info -----------------------";
-  LOG(INFO) << "runtime_device: " << (FLAGS_use_gpu ? "gpu" : "cpu");
-  LOG(INFO) << "ir_optim: " << "True";
-  LOG(INFO) << "enable_memory_optim: " << "True";
-  LOG(INFO) << "enable_tensorrt: " << FLAGS_use_tensorrt;
-  LOG(INFO) << "enable_mkldnn: " << (FLAGS_use_mkldnn ? "True" : "False");
-  LOG(INFO) << "cpu_math_library_num_threads: " << FLAGS_cpu_math_library_num_threads;
-  LOG(INFO) << "----------------------- Data info -----------------------";
-  LOG(INFO) << "batch_size: " << batch_size;
-  LOG(INFO) << "input_shape: " << input_shape;
-  LOG(INFO) << "data_num: " << img_num;
-  LOG(INFO) << "----------------------- Model info -----------------------";
-  LOG(INFO) << "model_name: " << model_name;
-  LOG(INFO) << "precision: " << FLAGS_precision;
-  LOG(INFO) << "----------------------- Perf info ------------------------";
-  LOG(INFO) << "Total time spent(ms): "
-            << std::accumulate(time_info.begin(), time_info.end(), 0);
-  LOG(INFO) << "preprocess_time(ms): " << time_info[0] / img_num
-            << ", inference_time(ms): " << time_info[1] / img_num
-            << ", postprocess_time(ms): " << time_info[2] / img_num;
-}
-
-
 static bool PathExists(const std::string& path){
 #ifdef _WIN32
   struct _stat buffer;
@@ -110,14 +84,14 @@ static bool PathExists(const std::string& path){
 int main_det(std::vector<cv::String> cv_all_img_names) {
     std::vector<double> time_info = {0, 0, 0};
     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_gpu_mem, FLAGS_cpu_threads, 
+                   FLAGS_enable_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_precision);
     
     for (int i = 0; i < cv_all_img_names.size(); ++i) {
-      LOG(INFO) << "The predict img: " << cv_all_img_names[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) {
@@ -132,10 +106,30 @@ int main_det(std::vector<cv::String> cv_all_img_names) {
       time_info[0] += det_times[0];
       time_info[1] += det_times[1];
       time_info[2] += det_times[2];
+    
+      if (FLAGS_benchmark) {
+          cout << cv_all_img_names[i] << '\t';
+          for (int n = 0; n < boxes.size(); n++) {
+            for (int m = 0; m < boxes[n].size(); m++) {
+              cout << boxes[n][m][0] << ' ' << boxes[n][m][1] << ' ';
+            }
+          }
+          cout << endl;
+      }        
     }
     
     if (FLAGS_benchmark) {
-        PrintBenchmarkLog("det", 1, "dynamic", time_info, cv_all_img_names.size());
+        AutoLogger autolog("ocr_det", 
+                           FLAGS_use_gpu,
+                           FLAGS_use_tensorrt,
+                           FLAGS_enable_mkldnn,
+                           FLAGS_cpu_threads,
+                           1, 
+                           "dynamic", 
+                           FLAGS_precision, 
+                           time_info, 
+                           cv_all_img_names.size());
+        autolog.report();
     }
     return 0;
 }
@@ -143,9 +137,15 @@ int main_det(std::vector<cv::String> cv_all_img_names) {
 
 int main_rec(std::vector<cv::String> cv_all_img_names) {
     std::vector<double> time_info = {0, 0, 0};
+    
+    std::string char_list_file = FLAGS_char_list_file;
+    if (FLAGS_benchmark) 
+        char_list_file = FLAGS_char_list_file.substr(6);
+    cout << "label file: " << char_list_file << 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_gpu_mem, FLAGS_cpu_threads,
+                       FLAGS_enable_mkldnn, char_list_file,
                        FLAGS_use_tensorrt, FLAGS_precision);
 
     for (int i = 0; i < cv_all_img_names.size(); ++i) {
@@ -164,19 +164,31 @@ int main_rec(std::vector<cv::String> cv_all_img_names) {
       time_info[1] += rec_times[1];
       time_info[2] += rec_times[2];
     }
-    
+        
     if (FLAGS_benchmark) {
-        PrintBenchmarkLog("rec", 1, "dynamic", time_info, cv_all_img_names.size());
+        AutoLogger autolog("ocr_rec", 
+                           FLAGS_use_gpu,
+                           FLAGS_use_tensorrt,
+                           FLAGS_enable_mkldnn,
+                           FLAGS_cpu_threads,
+                           1, 
+                           "dynamic", 
+                           FLAGS_precision, 
+                           time_info, 
+                           cv_all_img_names.size());
+        autolog.report();
     }
-    
     return 0;
 }
 
 
 int main_system(std::vector<cv::String> cv_all_img_names) {
+    std::vector<double> time_info_det = {0, 0, 0};
+    std::vector<double> time_info_rec = {0, 0, 0};
+
     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_gpu_mem, FLAGS_cpu_threads, 
+                   FLAGS_enable_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_precision);
@@ -184,22 +196,25 @@ int main_system(std::vector<cv::String> cv_all_img_names) {
     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_gpu_mem, FLAGS_cpu_threads,
+                           FLAGS_enable_mkldnn, FLAGS_cls_thresh,
                            FLAGS_use_tensorrt, FLAGS_precision);
     }
 
+    std::string char_list_file = FLAGS_char_list_file;
+    if (FLAGS_benchmark) 
+        char_list_file = FLAGS_char_list_file.substr(6);
+    cout << "label file: " << char_list_file << 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_gpu_mem, FLAGS_cpu_threads,
+                       FLAGS_enable_mkldnn, char_list_file,
                        FLAGS_use_tensorrt, FLAGS_precision);
 
-    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(FLAGS_image_dir, cv::IMREAD_COLOR);
+      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);
@@ -209,7 +224,10 @@ int main_system(std::vector<cv::String> cv_all_img_names) {
       std::vector<double> rec_times;
         
       det.Run(srcimg, boxes, &det_times);
-    
+      time_info_det[0] += det_times[0];
+      time_info_det[1] += det_times[1];
+      time_info_det[2] += det_times[2];
+        
       cv::Mat crop_img;
       for (int j = 0; j < boxes.size(); j++) {
         crop_img = Utility::GetRotateCropImage(srcimg, boxes[j]);
@@ -218,18 +236,36 @@ int main_system(std::vector<cv::String> cv_all_img_names) {
           crop_img = cls->Run(crop_img);
         }
         rec.Run(crop_img, &rec_times);
+        time_info_rec[0] += rec_times[0];
+        time_info_rec[1] += rec_times[1];
+        time_info_rec[2] += rec_times[2];
       }
-        
-      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;
     }
-      
+    if (FLAGS_benchmark) {
+        AutoLogger autolog_det("ocr_det", 
+                            FLAGS_use_gpu,
+                            FLAGS_use_tensorrt,
+                            FLAGS_enable_mkldnn,
+                            FLAGS_cpu_threads,
+                            1, 
+                            "dynamic", 
+                            FLAGS_precision, 
+                            time_info_det, 
+                            cv_all_img_names.size());
+        AutoLogger autolog_rec("ocr_rec", 
+                            FLAGS_use_gpu,
+                            FLAGS_use_tensorrt,
+                            FLAGS_enable_mkldnn,
+                            FLAGS_cpu_threads,
+                            1, 
+                            "dynamic", 
+                            FLAGS_precision, 
+                            time_info_rec, 
+                            cv_all_img_names.size());
+        autolog_det.report();
+        std::cout << endl;
+        autolog_rec.report();
+    }  
     return 0;
 }
 

deploy/cpp_infer/src/ocr_rec.cpp

@@ -112,12 +112,16 @@ void CRNNRecognizer::LoadModel(const std::string &model_dir) {
           1 << 20, 10, 3,
           precision,
           false, false);
+
       std::map<std::string, std::vector<int>> min_input_shape = {
-          {"x", {1, 3, 32, 10}}};
+          {"x", {1, 3, 32, 10}},
+          {"lstm_0.tmp_0", {10, 1, 96}}};
       std::map<std::string, std::vector<int>> max_input_shape = {
-          {"x", {1, 3, 32, 2000}}};
+          {"x", {1, 3, 32, 2000}},
+          {"lstm_0.tmp_0", {1000, 1, 96}}};
       std::map<std::string, std::vector<int>> opt_input_shape = {
-          {"x", {1, 3, 32, 320}}};
+          {"x", {1, 3, 32, 320}},
+          {"lstm_0.tmp_0", {25, 1, 96}}};
 
       config.SetTRTDynamicShapeInfo(min_input_shape, max_input_shape,
                                     opt_input_shape);
@@ -139,7 +143,7 @@ void CRNNRecognizer::LoadModel(const std::string &model_dir) {
   config.SwitchIrOptim(true);
 
   config.EnableMemoryOptim();
-  config.DisableGlogInfo();
+//   config.DisableGlogInfo();
 
   this->predictor_ = CreatePredictor(config);
 }

deploy/hubserving/ocr_det/params.py

@@ -13,7 +13,7 @@ def read_params():
 
     #params for text detector
     cfg.det_algorithm = "DB"
-    cfg.det_model_dir = "./inference/ch_ppocr_mobile_v2.0_det_infer/"
+    cfg.det_model_dir = "./inference/ch_PP-OCRv2_det_infer/"
     cfg.det_limit_side_len = 960
     cfg.det_limit_type = 'max'
 

deploy/hubserving/ocr_rec/params.py

@@ -13,7 +13,7 @@ def read_params():
 
     #params for text recognizer
     cfg.rec_algorithm = "CRNN"
-    cfg.rec_model_dir = "./inference/ch_ppocr_mobile_v2.0_rec_infer/"
+    cfg.rec_model_dir = "./inference/ch_PP-OCRv2_rec_infer/"
 
     cfg.rec_image_shape = "3, 32, 320"
     cfg.rec_char_type = 'ch'

deploy/hubserving/ocr_system/params.py

@@ -13,7 +13,7 @@ def read_params():
 
     #params for text detector
     cfg.det_algorithm = "DB"
-    cfg.det_model_dir = "./inference/ch_ppocr_mobile_v2.0_det_infer/"
+    cfg.det_model_dir = "./inference/ch_PP-OCRv2_det_infer/"
     cfg.det_limit_side_len = 960
     cfg.det_limit_type = 'max'
 
@@ -31,7 +31,7 @@ def read_params():
 
     #params for text recognizer
     cfg.rec_algorithm = "CRNN"
-    cfg.rec_model_dir = "./inference/ch_ppocr_mobile_v2.0_rec_infer/"
+    cfg.rec_model_dir = "./inference/ch_PP-OCRv2_rec_infer/"
 
     cfg.rec_image_shape = "3, 32, 320"
     cfg.rec_char_type = 'ch'

deploy/hubserving/readme.md

@@ -34,10 +34,10 @@ pip3 install paddlehub==2.1.0 --upgrade -i https://pypi.tuna.tsinghua.edu.cn/sim
 ```
 
 ### 2. 下载推理模型
-安装服务模块前，需要准备推理模型并放到正确路径。默认使用的是v2.0版的超轻量模型，默认模型路径为：
+安装服务模块前，需要准备推理模型并放到正确路径。默认使用的是PP-OCRv2模型，默认模型路径为：
 ```
-检测模型：./inference/ch_ppocr_mobile_v2.0_det_infer/
-识别模型：./inference/ch_ppocr_mobile_v2.0_rec_infer/
+检测模型：./inference/ch_PP-OCRv2_det_infer/
+识别模型：./inference/ch_PP-OCRv2_rec_infer/
 方向分类器：./inference/ch_ppocr_mobile_v2.0_cls_infer/
 ```  
 

deploy/hubserving/readme_en.md

@@ -35,10 +35,10 @@ pip3 install paddlehub==2.1.0 --upgrade -i https://pypi.tuna.tsinghua.edu.cn/sim
 ```
 
 ### 2. Download inference model
-Before installing the service module, you need to prepare the inference model and put it in the correct path. By default, the ultra lightweight model of v2.0 is used, and the default model path is:  
+Before installing the service module, you need to prepare the inference model and put it in the correct path. By default, the PP-OCRv2 models are used, and the default model path is:  
 ```
-detection model: ./inference/ch_ppocr_mobile_v2.0_det_infer/
-recognition model: ./inference/ch_ppocr_mobile_v2.0_rec_infer/
+detection model: ./inference/ch_PP-OCRv2_det_infer/
+recognition model: ./inference/ch_PP-OCRv2_rec_infer/
 text direction classifier: ./inference/ch_ppocr_mobile_v2.0_cls_infer/
 ```