diff --git a/deploy/cpp_infer/include/ocr_det.h b/deploy/cpp_infer/include/ocr_det.h index 6e4086fbaa6945b9f685e6844b7e701283de2dae..24392495348c8d85350e6b34725a33c76f0415f1 100644 --- a/deploy/cpp_infer/include/ocr_det.h +++ b/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 &use_dilation, - const bool &use_tensorrt, const std::string &precision) { + const std::string &det_db_score_mode, + const bool &use_dilation, const bool &use_tensorrt, + const std::string &precision) { this->use_gpu_ = use_gpu; this->gpu_id_ = gpu_id; this->gpu_mem_ = gpu_mem; @@ -58,7 +59,7 @@ public: this->det_db_thresh_ = det_db_thresh; 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->det_db_score_mode_ = det_db_score_mode; this->use_dilation_ = use_dilation; this->use_tensorrt_ = use_tensorrt; @@ -88,7 +89,7 @@ private: double det_db_thresh_ = 0.3; double det_db_box_thresh_ = 0.5; double det_db_unclip_ratio_ = 2.0; - bool use_polygon_score_ = false; + std::string det_db_score_mode_ = "slow"; bool use_dilation_ = false; bool visualize_ = true; diff --git a/deploy/cpp_infer/include/postprocess_op.h b/deploy/cpp_infer/include/postprocess_op.h index b384b79b3041bfcb96f042c6450d3c6e54f00498..4a98b151bdcc53e2ab3fbda1dca55dd9746bd86c 100644 --- a/deploy/cpp_infer/include/postprocess_op.h +++ b/deploy/cpp_infer/include/postprocess_op.h @@ -56,7 +56,7 @@ public: std::vector>> BoxesFromBitmap(const cv::Mat pred, const cv::Mat bitmap, const float &box_thresh, const float &det_db_unclip_ratio, - const bool &use_polygon_score); + const std::string &det_db_score_mode); std::vector>> FilterTagDetRes(std::vector>> boxes, diff --git a/deploy/cpp_infer/readme.md b/deploy/cpp_infer/readme.md index e7104881027b111de6821af8244ea2a6092fc14b..d269cc9e8fdfd68700e32c14816dc3b313bfad23 100644 --- a/deploy/cpp_infer/readme.md +++ b/deploy/cpp_infer/readme.md @@ -267,7 +267,7 @@ CUDNN_LIB_DIR=/your_cudnn_lib_dir |det_db_thresh|float|0.3|用于过滤DB预测的二值化图像，设置为0.-0.3对结果影响不明显| |det_db_box_thresh|float|0.5|DB后处理过滤box的阈值，如果检测存在漏框情况，可酌情减小| |det_db_unclip_ratio|float|1.6|表示文本框的紧致程度，越小则文本框更靠近文本| -|use_polygon_score|bool|false|是否使用多边形框计算bbox score，false表示使用矩形框计算。矩形框计算速度更快，多边形框对弯曲文本区域计算更准确。| +|det_db_score_mode|string|slow|slow:使用多边形框计算bbox score，fast:使用矩形框计算。矩形框计算速度更快，多边形框对弯曲文本区域计算更准确。| |visualize|bool|true|是否对结果进行可视化，为1时，预测结果会保存在`output`字段指定的文件夹下和输入图像同名的图像上。| - 方向分类器相关 diff --git a/deploy/cpp_infer/readme_en.md b/deploy/cpp_infer/readme_en.md index 61d65095394a9f5b7323bf8eb7324cd1e91b1346..b7687a9f6530976655a99690e9be02a04bbce6d3 100644 --- a/deploy/cpp_infer/readme_en.md +++ b/deploy/cpp_infer/readme_en.md @@ -260,7 +260,7 @@ More parameters are as follows, |det_db_thresh|float|0.3|Used to filter the binarized image of DB prediction, setting 0.-0.3 has no obvious effect on the result| |det_db_box_thresh|float|0.5|DB post-processing filter box threshold, if there is a missing box detected, it can be reduced as appropriate| |det_db_unclip_ratio|float|1.6|Indicates the compactness of the text box, the smaller the value, the closer the text box to the text| -|use_polygon_score|bool|false|Whether to use polygon box to calculate bbox score, false means to use rectangle box to calculate. Use rectangular box to calculate faster, and polygonal box more accurate for curved text area.| +|det_db_score_mode|string|slow| slow: use polygon box to calculate bbox score, fast: use rectangle box to calculate. Use rectangular box to calculate faster, and polygonal box more accurate for curved text area.| |visualize|bool|true|Whether to visualize the results，when it is set as true, the prediction results will be saved in the folder specified by the `output` field on an image with the same name as the input image.| - Classifier related parameters diff --git a/deploy/cpp_infer/include/clipper.cpp b/deploy/cpp_infer/src/clipper.cpp similarity index 100% rename from deploy/cpp_infer/include/clipper.cpp rename to deploy/cpp_infer/src/clipper.cpp diff --git a/deploy/cpp_infer/src/main.cpp b/deploy/cpp_infer/src/main.cpp index efc1e50ce929b4f68dff3437faa05b9ac46c2aa0..046a68a9692c6bbaf582924c688249b0bc366b97 100644 --- a/deploy/cpp_infer/src/main.cpp +++ b/deploy/cpp_infer/src/main.cpp @@ -36,25 +36,26 @@ #include "auto_log/autolog.h" #include +// common args DEFINE_bool(use_gpu, false, "Infering with GPU or CPU."); +DEFINE_bool(use_tensorrt, false, "Whether use tensorrt."); 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_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, false, "Whether use benchmark."); DEFINE_string(output, "./output/", "Save benchmark log path."); -// detection related DEFINE_string(image_dir, "", "Dir of input image."); +DEFINE_bool(visualize, true, "Whether show the detection results."); +// detection related 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, 0.6, "Threshold of det_db_box_thresh."); DEFINE_double(det_db_unclip_ratio, 1.5, "Threshold of det_db_unclip_ratio."); -DEFINE_bool(use_polygon_score, false, "Whether use polygon score."); DEFINE_bool(use_dilation, false, "Whether use the dilation on output map."); -DEFINE_bool(visualize, true, "Whether show the detection results."); +DEFINE_string(det_db_score_mode, "slow", "Whether use polygon score."); // classification related DEFINE_bool(use_angle_cls, false, "Whether use use_angle_cls."); DEFINE_string(cls_model_dir, "", "Path of cls inference model."); @@ -85,7 +86,7 @@ int main_det(std::vector cv_all_img_names) { 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_use_dilation, + FLAGS_det_db_score_mode, FLAGS_use_dilation, FLAGS_use_tensorrt, FLAGS_precision); if (!PathExists(FLAGS_output)) { @@ -117,13 +118,21 @@ int main_det(std::vector cv_all_img_names) { time_info[2] += det_times[2]; if (FLAGS_benchmark) { - cout << cv_all_img_names[i] << '\t'; + cout << cv_all_img_names[i] << "\t["; for (int n = 0; n < boxes.size(); n++) { + cout << '['; for (int m = 0; m < boxes[n].size(); m++) { - cout << boxes[n][m][0] << ' ' << boxes[n][m][1] << ' '; + cout << '[' << boxes[n][m][0] << ',' << boxes[n][m][1] << "]"; + if (m != boxes[n].size() - 1) { + cout << ','; + } + } + cout << ']'; + if (n != boxes.size() - 1) { + cout << ','; } } - cout << endl; + cout << ']' << endl; } } @@ -140,8 +149,6 @@ int main_rec(std::vector cv_all_img_names) { std::vector time_info = {0, 0, 0}; std::string rec_char_dict_path = FLAGS_rec_char_dict_path; - if (FLAGS_benchmark) - rec_char_dict_path = FLAGS_rec_char_dict_path.substr(6); cout << "label file: " << rec_char_dict_path << endl; CRNNRecognizer rec(FLAGS_rec_model_dir, FLAGS_use_gpu, FLAGS_gpu_id, @@ -194,7 +201,7 @@ int main_system(std::vector cv_all_img_names) { 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_use_dilation, + FLAGS_det_db_score_mode, FLAGS_use_dilation, FLAGS_use_tensorrt, FLAGS_precision); Classifier *cls = nullptr; @@ -205,8 +212,6 @@ int main_system(std::vector cv_all_img_names) { } std::string rec_char_dict_path = FLAGS_rec_char_dict_path; - if (FLAGS_benchmark) - rec_char_dict_path = FLAGS_rec_char_dict_path.substr(6); cout << "label file: " << rec_char_dict_path << endl; CRNNRecognizer rec(FLAGS_rec_model_dir, FLAGS_use_gpu, FLAGS_gpu_id, diff --git a/deploy/cpp_infer/src/ocr_det.cpp b/deploy/cpp_infer/src/ocr_det.cpp index d72dc40cddb0845c370f5ad4bb9b6e2f6fe0bf2f..ff7164ca24bec74e1334ed9237dd33d813470c94 100644 --- a/deploy/cpp_infer/src/ocr_det.cpp +++ b/deploy/cpp_infer/src/ocr_det.cpp @@ -161,7 +161,7 @@ void DBDetector::Run(cv::Mat &img, boxes = post_processor_.BoxesFromBitmap( pred_map, bit_map, this->det_db_box_thresh_, this->det_db_unclip_ratio_, - this->use_polygon_score_); + this->det_db_score_mode_); boxes = post_processor_.FilterTagDetRes(boxes, ratio_h, ratio_w, srcimg); auto postprocess_end = std::chrono::steady_clock::now(); diff --git a/deploy/cpp_infer/src/postprocess_op.cpp b/deploy/cpp_infer/src/postprocess_op.cpp index c3985572048155cf5aca57c95f1d8a816658ef13..5374fb1a4eba68d8055a52ec91d97c290832aa9d 100644 --- a/deploy/cpp_infer/src/postprocess_op.cpp +++ b/deploy/cpp_infer/src/postprocess_op.cpp @@ -12,8 +12,8 @@ // See the License for the specific language governing permissions and // limitations under the License. +#include #include -#include namespace PaddleOCR { @@ -187,23 +187,22 @@ float PostProcessor::PolygonScoreAcc(std::vector contour, cv::Mat mask; mask = cv::Mat::zeros(ymax - ymin + 1, xmax - xmin + 1, CV_8UC1); + cv::Point *rook_point = new cv::Point[contour.size()]; - cv::Point* rook_point = new cv::Point[contour.size()]; - for (int i = 0; i < contour.size(); ++i) { rook_point[i] = cv::Point(int(box_x[i]) - xmin, int(box_y[i]) - ymin); } const cv::Point *ppt[1] = {rook_point}; int npt[] = {int(contour.size())}; - cv::fillPoly(mask, ppt, npt, 1, cv::Scalar(1)); cv::Mat croppedImg; - pred(cv::Rect(xmin, ymin, xmax - xmin + 1, ymax - ymin + 1)).copyTo(croppedImg); + pred(cv::Rect(xmin, ymin, xmax - xmin + 1, ymax - ymin + 1)) + .copyTo(croppedImg); float score = cv::mean(croppedImg, mask)[0]; - delete []rook_point; + delete[] rook_point; return score; } @@ -247,7 +246,7 @@ float PostProcessor::BoxScoreFast(std::vector> box_array, std::vector>> PostProcessor::BoxesFromBitmap( const cv::Mat pred, const cv::Mat bitmap, const float &box_thresh, - const float &det_db_unclip_ratio, const bool &use_polygon_score) { + const float &det_db_unclip_ratio, const std::string &det_db_score_mode) { const int min_size = 3; const int max_candidates = 1000; @@ -281,7 +280,7 @@ std::vector>> PostProcessor::BoxesFromBitmap( } float score; - if (use_polygon_score) + if (det_db_score_mode == "slow") /* compute using polygon*/ score = PolygonScoreAcc(contours[_i], pred); else