yolov5s.engine 推理得到的 bbox 和 pytorch 不一样 about tensorrtx

[wang-xinyu]

用最终drow_bbox里面的结果是否就可以？

tensorrtx/yolov5/yolov5_det.cpp

Line 204 in 62050de

draw_bbox(img_batch, res_batch);

参考下drow_bbox里面get_rect的实现

tensorrtx/yolov5/src/postprocess.cpp

Line 87 in 62050de

cv::Rect r = get_rect(img, res[j].bbox);

[Zhang-Wen-chao]

`std::tuple<float, float, float, float> get_rect_values(cv::Mat& img, float bbox[4]) {
float l, r, t, b;
float r_w = kInputW / (img.cols * 1.0);
float r_h = kInputH / (img.rows * 1.0);
if (r_h > r_w) {
l = bbox[0] - bbox[2] / 2.f;
r = bbox[0] + bbox[2] / 2.f;
t = bbox[1] - bbox[3] / 2.f - (kInputH - r_w * img.rows) / 2;
b = bbox[1] + bbox[3] / 2.f - (kInputH - r_w * img.rows) / 2;
l = l / r_w;
r = r / r_w;
t = t / r_w;
b = b / r_w;
} else {
l = bbox[0] - bbox[2] / 2.f - (kInputW - r_h * img.cols) / 2;
r = bbox[0] + bbox[2] / 2.f - (kInputW - r_h * img.cols) / 2;
t = bbox[1] - bbox[3] / 2.f;
b = bbox[1] + bbox[3] / 2.f;
l = l / r_h;
r = r / r_h;
t = t / r_h;
b = b / r_h;
}

return std::make_tuple(l, t, r - l, b - t);

}`

谢谢大佬！这个函数返回了bbox在原图上的xywh。