换了OTALoss，训练报了错（i changed to use OTALoss, and when starting training, the errors occur）

[oldg00se]

Traceback (most recent call last):
File "e:\yolov5-6.1-ota\train-ota.py", line 655, in
main(opt)
File "e:\yolov5-6.1-ota\train-ota.py", line 551, in main
train(opt.hyp, opt, device, callbacks)
File "e:\yolov5-6.1-ota\train-ota.py", line 342, in train
loss, loss_items = compute_loss(pred, targets.to(device), imgs) # loss scaled by batch_size
File "E:\anaconda\envs\yolov5\lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "E:\anaconda\envs\yolov5\lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
File "e:\yolov5-6.1-ota\utils\ota.py", line 147, in forward
return self.get_losses(
File "e:\yolov5-6.1-ota\utils\ota.py", line 337, in get_losses
reg_target = gt_bboxes_per_image[matched_gt_inds]
RuntimeError: indices should be either on cpu or on the same device as the indexed tensor (cpu)