Improve PPOCR example

examples/vision/ocr/PP-OCRv3/cpp/CMakeLists.txt

@@ -12,3 +12,7 @@ include_directories(${FASTDEPLOY_INCS})
 add_executable(infer_demo ${PROJECT_SOURCE_DIR}/infer.cc)
 # 添加FastDeploy库依赖
 target_link_libraries(infer_demo ${FASTDEPLOY_LIBS})
+
+add_executable(infer_static_shape_demo ${PROJECT_SOURCE_DIR}/infer_static_shape.cc)
+# 添加FastDeploy库依赖
+target_link_libraries(infer_static_shape_demo ${FASTDEPLOY_LIBS})

examples/vision/ocr/PP-OCRv3/cpp/README.md

@@ -43,13 +43,16 @@ wget https://gitee.com/paddlepaddle/PaddleOCR/raw/release/2.6/ppocr/utils/ppocr_
 ./infer_demo ./ch_PP-OCRv3_det_infer ./ch_ppocr_mobile_v2.0_cls_infer ./ch_PP-OCRv3_rec_infer ./ppocr_keys_v1.txt ./12.jpg 3
 # 昆仑芯XPU推理
 ./infer_demo ./ch_PP-OCRv3_det_infer ./ch_ppocr_mobile_v2.0_cls_infer ./ch_PP-OCRv3_rec_infer ./ppocr_keys_v1.txt ./12.jpg 4
-# 华为昇腾推理, 请用户在代码里正确开启Rec模型的静态shape推理，并设置分类模型和识别模型的推理batch size为1.
-./infer_demo ./ch_PP-OCRv3_det_infer ./ch_ppocr_mobile_v2.0_cls_infer ./ch_PP-OCRv3_rec_infer ./ppocr_keys_v1.txt ./12.jpg 5
+# 华为昇腾推理,需要使用静态shape的demo, 若用户需要连续地预测图片, 输入图片尺寸需要准备为统一尺寸
+./infer_static_shape_demo ./ch_PP-OCRv3_det_infer ./ch_ppocr_mobile_v2.0_cls_infer ./ch_PP-OCRv3_rec_infer ./ppocr_keys_v1.txt ./12.jpg 1
 ```
 
 以上命令只适用于Linux或MacOS, Windows下SDK的使用方式请参考:  
 - [如何在Windows中使用FastDeploy C++ SDK](../../../../../docs/cn/faq/use_sdk_on_windows.md)
 
+如果用户使用华为昇腾NPU部署, 请参考以下方式在部署前初始化部署环境:
+- [如何使用华为昇腾NPU部署](../../../../../docs/cn/faq/use_sdk_on_ascend.md)
+
 运行完成可视化结果如下图所示
 
 <img width="640" src="https://user-images.githubusercontent.com/109218879/185826024-f7593a0c-1bd2-4a60-b76c-15588484fa08.jpg">

examples/vision/ocr/PP-OCRv3/cpp/infer.cc

@@ -56,10 +56,6 @@ void InitAndInfer(const std::string& det_model_dir, const std::string& cls_model
   auto cls_model = fastdeploy::vision::ocr::Classifier(cls_model_file, cls_params_file, cls_option);
   auto rec_model = fastdeploy::vision::ocr::Recognizer(rec_model_file, rec_params_file, rec_label_file, rec_option);
 
-  // Users could enable static shape infer for rec model when deploy PP-OCR on hardware 
-  // which can not support dynamic shape infer well, like Huawei Ascend series. 
-  // rec_model.GetPreprocessor().SetStaticShapeInfer(true);
-
   assert(det_model.Initialized());
   assert(cls_model.Initialized());
   assert(rec_model.Initialized());
@@ -71,9 +67,6 @@ void InitAndInfer(const std::string& det_model_dir, const std::string& cls_model
   // Set inference batch size for cls model and rec model, the value could be -1 and 1 to positive infinity.
   // When inference batch size is set to -1, it means that the inference batch size 
   // of the cls and rec models will be the same as the number of boxes detected by the det model. 
-  // When users enable static shape infer for rec model, the batch size of cls and rec model needs to be set to 1.
-  // ppocr_v3.SetClsBatchSize(1);
-  // ppocr_v3.SetRecBatchSize(1); 
   ppocr_v3.SetClsBatchSize(cls_batch_size);
   ppocr_v3.SetRecBatchSize(rec_batch_size); 
 
@@ -130,8 +123,6 @@ int main(int argc, char* argv[]) {
     option.EnablePaddleToTrt();
   } else if (flag == 4) {
     option.UseKunlunXin();
-  } else if (flag == 5) {
-    option.UseAscend();
   }
 
   std::string det_model_dir = argv[1];

examples/vision/ocr/PP-OCRv3/cpp/infer_static_shape.cc

@@ -0,0 +1,107 @@
+// Copyright (c) 2022 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 "fastdeploy/vision.h"
+#ifdef WIN32
+const char sep = '\\';
+#else
+const char sep = '/';
+#endif
+
+void InitAndInfer(const std::string& det_model_dir, const std::string& cls_model_dir, const std::string& rec_model_dir, const std::string& rec_label_file, const std::string& image_file, const fastdeploy::RuntimeOption& option) {
+  auto det_model_file = det_model_dir + sep + "inference.pdmodel";
+  auto det_params_file = det_model_dir + sep + "inference.pdiparams";
+
+  auto cls_model_file = cls_model_dir + sep + "inference.pdmodel";
+  auto cls_params_file = cls_model_dir + sep + "inference.pdiparams";
+
+  auto rec_model_file = rec_model_dir + sep + "inference.pdmodel";
+  auto rec_params_file = rec_model_dir + sep + "inference.pdiparams";
+
+  auto det_option = option;
+  auto cls_option = option;
+  auto rec_option = option;
+
+  auto det_model = fastdeploy::vision::ocr::DBDetector(det_model_file, det_params_file, det_option);
+  auto cls_model = fastdeploy::vision::ocr::Classifier(cls_model_file, cls_params_file, cls_option);
+  auto rec_model = fastdeploy::vision::ocr::Recognizer(rec_model_file, rec_params_file, rec_label_file, rec_option);
+
+  // Users could enable static shape infer for rec model when deploy PP-OCR on hardware 
+  // which can not support dynamic shape infer well, like Huawei Ascend series. 
+  rec_model.GetPreprocessor().SetStaticShapeInfer(true);
+
+  assert(det_model.Initialized());
+  assert(cls_model.Initialized());
+  assert(rec_model.Initialized());
+
+  // The classification model is optional, so the PP-OCR can also be connected in series as follows
+  // auto ppocr_v3 = fastdeploy::pipeline::PPOCRv3(&det_model, &rec_model);
+  auto ppocr_v3 = fastdeploy::pipeline::PPOCRv3(&det_model, &cls_model, &rec_model);
+
+  // When users enable static shape infer for rec model, the batch size of cls and rec model must to be set to 1.
+  ppocr_v3.SetClsBatchSize(1);
+  ppocr_v3.SetRecBatchSize(1); 
+
+  if(!ppocr_v3.Initialized()){
+    std::cerr << "Failed to initialize PP-OCR." << std::endl;
+    return;
+  }
+
+  auto im = cv::imread(image_file);
+  
+  fastdeploy::vision::OCRResult result;
+  if (!ppocr_v3.Predict(im, &result)) {
+    std::cerr << "Failed to predict." << std::endl;
+    return;
+  }
+
+  std::cout << result.Str() << std::endl;
+
+  auto vis_im = fastdeploy::vision::VisOcr(im, result);
+  cv::imwrite("vis_result.jpg", vis_im);
+  std::cout << "Visualized result saved in ./vis_result.jpg" << std::endl;
+}
+
+int main(int argc, char* argv[]) {
+  if (argc < 7) {
+    std::cout << "Usage: infer_demo path/to/det_model path/to/cls_model "
+                 "path/to/rec_model path/to/rec_label_file path/to/image "
+                 "run_option, "
+                 "e.g ./infer_demo ./ch_PP-OCRv3_det_infer "
+                 "./ch_ppocr_mobile_v2.0_cls_infer ./ch_PP-OCRv3_rec_infer "
+                 "./ppocr_keys_v1.txt ./12.jpg 0"
+              << std::endl;
+    std::cout << "The data type of run_option is int, 0: run with cpu; 1: run "
+                 "with ascend."
+              << std::endl;
+    return -1;
+  }
+
+  fastdeploy::RuntimeOption option;
+  int flag = std::atoi(argv[6]);
+
+  if (flag == 0) {
+    option.UseCpu(); 
+  } else if (flag == 1) {
+    option.UseAscend();
+  }
+
+  std::string det_model_dir = argv[1];
+  std::string cls_model_dir = argv[2];
+  std::string rec_model_dir = argv[3];
+  std::string rec_label_file = argv[4];
+  std::string test_image = argv[5];
+  InitAndInfer(det_model_dir, cls_model_dir, rec_model_dir, rec_label_file, test_image, option);
+  return 0;
+}