// 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. #pragma once #include "opencv2/core.hpp" #include "opencv2/imgcodecs.hpp" #include "opencv2/imgproc.hpp" #include "paddle_api.h" #include "paddle_inference_api.h" #include #include #include #include #include #include #include #include #include #include #include using namespace paddle_infer; namespace PaddleOCR { class StructureLayoutRecognizer { public: explicit StructureLayoutRecognizer( const std::string &model_dir, const bool &use_gpu, const int &gpu_id, const int &gpu_mem, const int &cpu_math_library_num_threads, const bool &use_mkldnn, const string &label_path, const bool &use_tensorrt, const std::string &precision, const double &layout_score_threshold, const double &layout_nms_threshold) { this->use_gpu_ = use_gpu; this->gpu_id_ = gpu_id; this->gpu_mem_ = gpu_mem; this->cpu_math_library_num_threads_ = cpu_math_library_num_threads; this->use_mkldnn_ = use_mkldnn; this->use_tensorrt_ = use_tensorrt; this->precision_ = precision; this->post_processor_.init(label_path, layout_score_threshold, layout_nms_threshold); LoadModel(model_dir); } // Load Paddle inference model void LoadModel(const std::string &model_dir); void Run(cv::Mat img, std::vector &result, std::vector ×); private: std::shared_ptr predictor_; bool use_gpu_ = false; int gpu_id_ = 0; int gpu_mem_ = 4000; int cpu_math_library_num_threads_ = 4; bool use_mkldnn_ = false; std::vector mean_ = {0.485f, 0.456f, 0.406f}; std::vector scale_ = {1 / 0.229f, 1 / 0.224f, 1 / 0.225f}; bool is_scale_ = true; bool use_tensorrt_ = false; std::string precision_ = "fp32"; // pre-process Resize resize_op_; Normalize normalize_op_; Permute permute_op_; // post-process PicodetPostProcessor post_processor_; }; } // namespace PaddleOCR