Weight parameter of DiceLoss

[NastaranVB]

Hello,
I have used loss function as below:
lloss_function=DiceLoss(include_background=False, to_onehot_y=True, softmax=True, reduction='mean', smooth_nr=0, smooth_dr=1e-5, weight=[2, 10])
In past days it was working but now I get the below error:

TypeError Traceback (most recent call last)
/tmp/ipykernel_1144963/2523664510.py in
11 model=unet,
12 learning_rate=1e-3,
---> 13 loss_function=DiceLoss(include_background=False, to_onehot_y=True, softmax=True, reduction='mean', smooth_nr=0, smooth_dr=1e-5, weight=[2, 10]),
14 optimizer_name=torch.optim.AdamW,
15 scheduler_name=torch.optim.lr_scheduler.ExponentialLR,

TypeError: init() got an unexpected keyword argument 'weight'

[KumoLiu]

Hi @NastaranVB, please check the type of DiceLoss. Thanks.

[NastaranVB]

Hi @KumoLiu thanks for coming back to me so quickly. What do you mean from the type of DiceLoss?
I have used it as loss function in multi class segmentation which includes 3 class including background.
'DiceLoss
class monai.losses.DiceLoss(include_background=True, to_onehot_y=False, sigmoid=False, softmax=False, other_act=None, squared_pred=False, jaccard=False, reduction=LossReduction.MEAN, smooth_nr=1e-05, smooth_dr=1e-05, batch=False, weight=None)'

[KumoLiu]

Can you check your MONAI version? weight args is added after 1.2. Thanks.

[NastaranVB]

Thank you very much. The version was the reason.