TypeError: __init__() got an unexpected keyword argument 'label_smoothing'

[silencessss]

Anyone meet this problem??? I could not deal with it.
Detail:
→ TypeError: init() got an unexpected keyword argument 'label_smoothing'

in main.py line 546 → criterion = create_loss_fn(args)
and
in utils.py line 32 → criterion = nn.CrossEntropyLoss(label_smoothing=args.label_smoothing)

Thanks!

[silencessss]

I had been deal with it!!

My torch vision is 1.9.0. Hence, the nn.CrossEntropyLoss() is like → torch.nn.CrossEntropyLoss(weight=None, size_average=None, ignore_index=-100, reduce=None, reduction='mean').

However, the nn.CrossEntropyLoss() in troch vision 1.11.0 is like → torch.nn.CrossEntropyLoss(weight=None, size_average=None, ignore_index=- 100, reduce=None, reduction='mean', label_smoothing=0.0) .