如何检测 Yolo 模型中的特定检测对象

Question

我正在使用 Yolor 检测多个对象，然后裁剪检测到的特定对象并存储在单独的文件夹中。我能够裁剪每个检测到的对象，但我对如何仅裁剪特定检测到的对象感到困惑。

下面是裁剪检测到的图像的代码： save_obj 函数保存裁剪后的图像。

           # Write results
            k = 0 
            for *xyxy, conf, cls in det:
                if save_txt:  # Write to file
                    xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist()  # normalized xywh
                    with open(txt_path + '.txt', 'a') as f:
                        f.write(('%g ' * 5 + '\n') % (cls, *xywh))  # label format

                if save_img or view_img:  # Add bbox to image
                    label = '%s %.2f' % (names[int(cls)], conf)
                    plot_one_box(xyxy, im0, label=label, color=colors[int(cls)], line_thickness=3)
                

                if save_obj:  
                    x,y,w,h=int(xyxy[0]), int(xyxy[1]), int(xyxy[2] - xyxy[0]), int(xyxy[3] - xyxy[1])                   
                    img_ = im1.astype(np.uint8)
                    crop_img=img_[y:y+ h, x:x + w]                          
                        
                    #!!rescale image !!!
                    filename=p.name
                    filename_no_extesion=filename.split('.')[0]
                    extension=filename.split('.')[1]
                    new_filename=str(filename_no_extesion) + '_' + str(k) + '.' + str(extension) 
                    dir_path=os.path.join('/mydrive/yolor/','cropped')
                    filepath=os.path.join(dir_path, new_filename)
                    print(filepath)
                    cv2.imwrite(filepath, crop_img)
                    k=k+1

Answer 1

希望对您有所帮助

           # Write results
        k = 0 
        for *xyxy, conf, cls in det:
            if save_txt:  # Write to file
                xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist()  # normalized xywh
                with open(txt_path + '.txt', 'a') as f:
                    f.write(('%g ' * 5 + '\n') % (cls, *xywh))  # label format

            if save_img or view_img:  # Add bbox to image
                label = '%s %.2f' % (names[int(cls)], conf)
                plot_one_box(xyxy, im0, label=label, color=colors[int(cls)], line_thickness=3)
            

            if save_obj and names[int(cls)]=='xyz_class':  
                x,y,w,h=int(xyxy[0]), int(xyxy[1]), int(xyxy[2] - xyxy[0]), int(xyxy[3] - xyxy[1])                   
                img_ = im1.astype(np.uint8)
                crop_img=img_[y:y+ h, x:x + w]                          
                    
                #!!rescale image !!!
                filename=p.name
                filename_no_extesion=filename.split('.')[0]
                extension=filename.split('.')[1]
                new_filename=str(filename_no_extesion) + '_' + str(k) + '.' + str(extension) 
                dir_path=os.path.join('/mydrive/yolor/','cropped')
                filepath=os.path.join(dir_path, new_filename)
                print(filepath)
                cv2.imwrite(filepath, crop_img)
                k=k+1

如何检测 Yolo 模型中的特定检测对象

how to detect a particular detected object in Yolo model

python

deep-learning

yolo

yolov5