基于yolov8的面部七种表情识别C++部署工程

#include "FacialEmotion.h" static float fast_exp(float x) { union { uint32_t i; float f; } v{}; v.i = (1 << 23) * (1.4426950409 * x + 126.93490512f); return v.f; } static inline float sigmoid(float x) { return 1.0f / (1.0f + fast_exp(-x)); } static float intersection_area(const Object& a, const Object& b) { cv::Rect_<float> inter = a.rect & b.rect; return inter.area(); } static void qsort_descent_inplace(std::vector<Object>& faceobjects, int left, int right) { int i = left; int j = right; float p = faceobjects[(left + right) / 2].prob; while (i <= j) { while (faceobjects[i].prob > p) i++; while (faceobjects[j].prob < p) j--; if (i <= j) { // swap std::swap(faceobjects[i], faceobjects[j]); i++; j--; } } // #pragma omp parallel sections { // #pragma omp section { if (left < j) qsort_descent_inplace(faceobjects, left, j); } // #pragma omp section { if (i < right) qsort_descent_inplace(faceobjects, i, right); } } } static void qsort_descent_inplace(std::vector<Object>& faceobjects) { if (faceobjects.empty()) return; qsort_descent_inplace(faceobjects, 0, faceobjects.size() - 1); } static void nms_sorted_bboxes(const std::vector<Object>& faceobjects, std::vector<int>& picked, float nms_threshold) { picked.clear(); const int n = faceobjects.size(); std::vector<float> areas(n); for (int i = 0; i < n; i++) { areas[i] = faceobjects[i].rect.width * faceobjects[i].rect.height; } for (int i = 0; i < n; i++) { const Object& a = faceobjects[i]; int keep = 1; for (int j = 0; j < (int)picked.size(); j++) { const Object& b = faceobjects[picked[j]]; // intersection over union float inter_area = intersection_area(a, b); float union_area = areas[i] + areas[picked[j]] - inter_area; // float IoU = inter_area / union_area if (inter_area / union_area > nms_threshold) keep = 0; } if (keep) picked.push_back(i); } } static void generate_grids_and_stride(const int target_w, const int target_h, std::vector<int>& strides, std::vector<GridAndStride>& grid_strides) { for (int i = 0; i < (int)strides.size(); i++) { int stride = strides[i]; int num_grid_w = target_w / stride; int num_grid_h = target_h / stride; for (int g1 = 0; g1 < num_grid_h; g1++) { for (int g0 = 0; g0 < num_grid_w; g0++) { GridAndStride gs; gs.grid0 = g0; gs.grid1 = g1; gs.stride = stride; grid_strides.push_back(gs); } } } } static void generate_proposals(std::vector<GridAndStride> grid_strides, const ncnn::Mat& pred, float prob_threshold, std::vector<Object>& objects) { const int num_points = grid_strides.size(); const int num_class = 7; const int reg_max_1 = 16; for (int i = 0; i < num_points; i++) //out.h { const float* scores = pred.row(i) + 4 * reg_max_1; // find label with max score int label = -1; float score = -FLT_MAX; for (int k = 0; k < num_class; k++) { float confidence = scores[k]; if (confidence > score) { label = k; score = confidence; } } float box_prob = sigmoid(score); if (box_prob >= prob_threshold) { ncnn::Mat bbox_pred(reg_max_1, 4, (void*)pred.row(i)); { ncnn::Layer* softmax = ncnn::create_layer(ncnn::layer_to_index("Softmax")); // ncnn::layer_to_index("Softmax") ncnn::ParamDict pd; pd.set(0, 1); // axis // pd.set(1, 1); softmax->load_param(pd); ncnn::Option opt; opt.num_threads = 1; opt.use_packing_layout = false; softmax->create_pipeline(opt); softmax->forward_inplace(bbox_pred, opt); softmax->destroy_pipeline(opt); delete softmax; } float pred_ltrb[4]; for (int k = 0; k < 4; k++) { float dis = 0.f; const float* dis_after_sm = bbox_pred.row(k); for (int l = 0; l < reg_max_1; l++) { dis += l * dis_after_sm[l]; } pred_ltrb[k] = dis * grid_strides[i].stride; } float pb_cx = (grid_strides[i].grid0 + 0.5f) * grid_strides[i].stride; float pb_cy = (grid_strides[i].grid1 + 0.5f) * grid_strides[i].stride; float x0 = pb_cx - pred_ltrb[0]; float y0 = pb_cy - pred_ltrb[1]; float x1 = pb_cx + pred_ltrb[2]; float y1 = pb_cy + pred_ltrb[3]; Object obj; obj.rect.x = x0; obj.rect.y = y0; obj.rect.width = x1 - x0; obj.rect.height = y1 - y0; obj.label = label; obj.prob = box_prob; objects.push_back(obj); } } } //调用ncnn转置操作 static void transpose(const ncnn::Mat& in, ncnn::Mat& out) { ncnn::Option opt; opt.num_threads = 1; opt.use_fp16_storage = false; opt.use_packing_layout = true; ncnn::Layer* op = ncnn::create_layer("Permute"); // set param ncnn::ParamDict pd; pd.set(0, 1);// order_type=1 op->load_param(pd); op->create_pipeline(opt); op->forward(in,out, opt); op->destroy_pipeline(opt); delete op; } FacialEmotion::FacialEmotion() { blob_pool_allocator.set_size_compare_ratio(0.f); workspace_pool_allocator.set_size_compare_ratio(0.f); } int FacialEmotion::load(std::string parma_path,std::string bin_path,int _target_size,bool use_gpu) { yolo.clear(); blob_pool_allocator.clear(); workspace_pool_allocator.clear(); ncnn::set_cpu_powersave(2); ncnn::set_omp_num_threads(ncnn::get_big_cpu_count()); yolo.opt = ncnn::Option(); #if NCNN_VULKAN yolo.opt.use_vulkan_compute = use_gpu; #endif yolo.opt.num_threads = 2; yolo.opt.blob_allocator = &blob_pool_allocator; yolo.opt.workspace_allocator = &workspace_pool_allocator; yolo.load_param(parma_path.c_str()); yolo.load_model(bin_path.c_str()); target_size = _target_size; return 0; } int FacialEmotion::detect(const cv::Mat& rgb, std::vector<Object>& objects, float prob_threshold, float nms_threshold) { int width = rgb.cols; int height = rgb.rows; // pad to multiple of 32 int w = width; int h = height; float scale = 1.f; if (w > h) { scale = (float)target_size / w; w = target_size; h = h * scale; } else { scale = (float)target_size / h; h = target_size; w = w * scale; } ncnn::Mat in = ncnn::Mat::from_pixels_resize(rgb.data, ncnn::Mat::PIXEL_BGR, width, height, w, h); // pad to target_size rectangle int wpad = (w + 31) / 32 * 32 - w; int hpad = (h + 31) / 32 * 32 - h; ncnn::Mat in_pad; ncnn::copy_make_border(in, in_pad, hpad / 2, hpad - hpad / 2, wpad / 2, wpad - wpad / 2, ncnn::BORDER_CONSTANT, 0.f); in_pad.substract_mean_normalize(0, norm_vals); ncnn::Extractor ex = yolo.create_extractor(); ex.input("images", in_pad); std::vector<Object> proposals; ncnn::Mat out; ex.extract("/model.22/Concat_3_output_0", out); ncnn::Mat out1; transpose(out, out1); std::vector<int> strides = {8, 16, 32}; // might have stride=64 s