Question on nan

Hi there,
This is a great work and many thanks for releasing the code. When I look into the code, I find some places where nan is handled, like

Lines 366 to 367 in 34a4767

    
           output = torch.nan_to_num(output) 
        
           mask = torch.nan_to_num(mask)

and

Lines 336 to 337 in 34a4767

    
           loss_cls = torch.nan_to_num(loss_cls) 
        
           loss_bbox = torch.nan_to_num(loss_bbox)

I wonder in which cases nan would occur? It might help me better understand the model. Any advice would be very much appreciated!

	output = torch.nan_to_num(output)
	mask = torch.nan_to_num(mask)

	loss_cls = torch.nan_to_num(loss_cls)
	loss_bbox = torch.nan_to_num(loss_bbox)