ValueError: All bounding boxes should have positive height and width. Found invaid box

问题

运行faster rcnn时出现该错误时，需要的bounding boxes格式为：[xmin, ymin, xmax, ymax]，但数据集导入时格式可能为[xmin, ymin, width, height]，就会出现这种错误。

解决方法

torchvision.ops.boxes.box_convert提供了一个bounding boxes的转换函数，其用法

 def box_convert(boxes: Tensor, in_fmt: str, out_fmt: str) -> Tensor: 
     """ 
     Converts boxes from given in_fmt to out_fmt. 
     Supported in_fmt and out_fmt are: 
  
     'xyxy': boxes are represented via corners, x1, y1 being top left and x2, y2 being bottom right. 
  
     'xywh' : boxes are represented via corner, width and height, x1, y2 being top left, w, h being width and height. 
  
     'cxcywh' : boxes are represented via centre, width and height, cx, cy being center of box, w, h 
     being width and height. 
  
     Arguments: 
         boxes (Tensor[N, 4]): boxes which will be converted. 
         in_fmt (str): Input format of given boxes. Supported formats are ['xyxy', 'xywh', 'cxcywh']. 
         out_fmt (str): Output format of given boxes. Supported formats are ['xyxy', 'xywh', 'cxcywh'] 
  
     Returns: 
         boxes (Tensor[N, 4]): Boxes into converted format. 
     """ 

案例：

from torchvision.ops.boxes import box_convert

"""
... 数据导入部分省略
"""


boxes = box_convert(boxes=torch.tensor(boxes), in_fmt='xywh', out_fmt='xyxy')

源自：https://github.com/pytorch/vision/issues/2740