AttributeError: 'BboxLoss' object has no attribute 'dfl_loss'

[1343464520]

训练时出现这个问题，不知道是啥原因。请帮忙看看，谢谢！

Plotting labels to runs\detect\pruning_task_2\step_0_finetune\labels.jpg...
optimizer: 'optimizer=auto' found, ignoring 'lr0=0.01' and 'momentum=0.937' and determining best 'optimizer', 'lr0' and 'momentum' automatically...
optimizer: AdamW(lr=0.001429, momentum=0.9) with parameter groups 65 weight(decay=0.0), 72 weight(decay=0.0005), 71 bias(decay=0.0)
Image sizes 640 train, 640 val
Using 8 dataloader workers
Logging results to runs\detect\pruning_task_2\step_0_finetune
Starting training for 60 epochs...

  Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size

0%| | 0/216 [00:00<?, ?it/s]
Traceback (most recent call last):
File "D:\Model_Pruning\Torch-Pruning\examples\yolov8\yolov8_pruning.py", line 422, in
prune(args)
File "D:\Model_Pruning\Torch-Pruning\examples\yolov8\yolov8_pruning.py", line 373, in prune
model.train_v2(pruning=True, **pruning_cfg)
File "D:\Model_Pruning\Torch-Pruning\examples\yolov8\yolov8_pruning.py", line 270, in train_v2
self.trainer.train()
File "D:\software\anaconda\envs\pruning\Lib\site-packages\ultralytics\engine\trainer.py", line 207, in train
self._do_train(world_size)
File "D:\software\anaconda\envs\pruning\Lib\site-packages\ultralytics\engine\trainer.py", line 380, in _do_train
self.loss, self.loss_items = self.model(batch)
^^^^^^^^^^^^^^^^^
File "D:\software\anaconda\envs\pruning\Lib\site-packages\torch\nn\modules\module.py", line 1736, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\software\anaconda\envs\pruning\Lib\site-packages\torch\nn\modules\module.py", line 1747, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\software\anaconda\envs\pruning\Lib\site-packages\ultralytics\nn\tasks.py", line 111, in forward
return self.loss(x, *args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\software\anaconda\envs\pruning\Lib\site-packages\ultralytics\nn\tasks.py", line 293, in loss
return self.criterion(preds, batch)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\software\anaconda\envs\pruning\Lib\site-packages\ultralytics\utils\loss.py", line 255, in call
loss[0], loss[2] = self.bbox_loss(
^^^^^^^^^^^^^^^
File "D:\software\anaconda\envs\pruning\Lib\site-packages\torch\nn\modules\module.py", line 1736, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\software\anaconda\envs\pruning\Lib\site-packages\torch\nn\modules\module.py", line 1747, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\software\anaconda\envs\pruning\Lib\site-packages\ultralytics\utils\loss.py", line 106, in forward
if self.dfl_loss:
^^^^^^^^^^^^^
File "D:\software\anaconda\envs\pruning\Lib\site-packages\torch\nn\modules\module.py", line 1931, in getattr
raise AttributeError(
AttributeError: 'BboxLoss' object has no attribute 'dfl_loss'