YOLOV5/V7 实现图片、视频、摄像头 标签数量统计

本文主要是在推理detect阶段，预测的图片或视频中没有标签的数量统计

在 detect.py中的第171行（大家看自己位置，我这里是大概位置）加入这行代码

cv2.putText(im0, f"{n} " + 'person', (5, 50), cv2.FONT_HERSHEY_SIMPLEX, 1.2, (0, 0, 255), 2)

修改后的 11行和28行29行

            if len(det):
                # Rescale boxes from img_size to im0 size
                det[:, :4] = scale_coords(im.shape[2:], det[:, :4], im0.shape).round()

                # Print results
                for c in det[:, -1].unique():
                    n = (det[:, -1] == c).sum()  # detections per class
                    print(n)
                    s += f"{n} {names[int(c)]}{'s' * (n > 1)}, "  # add to string

                    cv2.putText(im0, f"{n} " + 'person', (5, 50), cv2.FONT_HERSHEY_SIMPLEX, 1.2, (0, 0, 255), 2)

                # Write results
                for *xyxy, conf, cls in reversed(det):
                    if save_txt:  # Write to file
                        xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist()  # normalized xywh
                        line = (cls, *xywh, conf) if save_conf else (cls, *xywh)  # label format
                        with open(txt_path + '.txt', 'a') as f:
                            f.write(('%g ' * len(line)).rstrip() % line + '\n')

                    if save_img or save_crop or view_img:  # Add bbox to image
                        c = int(cls)  # integer class
                        label = None if hide_labels else (names[c] if hide_conf else f'{names[c]} {conf:.2f}')
                        annotator.box_label(xyxy, label, color=colors(c, True))
                        if save_crop:
                            save_one_box(xyxy, imc, file=save_dir / 'crops' / names[c] / f'{p.stem}.jpg', BGR=True)
            # 注释 这里加入else 是为了输出预测框为0时的结果
            else:
                cv2.putText(im0,  '0 person', (5, 50), cv2.FONT_HERSHEY_SIMPLEX, 1.2, (0, 0, 255), 2)

如果想要 根据预测框的数量 来进行分等级 加入6-15行

  # Print results
                for c in det[:, -1].unique():
                    n = (det[:, -1] == c).sum()  # detections per class
                    s += f"{n} {names[int(c)]}{'s' * (n > 1)}, "  # add to string
                    
                    # 根据预测框数量进行等级分类
                    if (int(f"{n}") < 10):
                        strr = "111" # 小于10个框等级111
                    elif (int(f"{n}") > 10 and int(f"{n}") < 20):
                        strr = "222" # 小于20个小于10个  等级222
                    else:
                        strr = "333" # 大于20个  等级333

                    cv2.putText(im0,   f"{n} " + 'person' + strr +  (10, 30), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 0, 255), 2)
                    print(s)