hsiangyuzhao / panet Goto Github PK

Hello, dear author. Thanks for replying to my last quetion. I tried different ways to run the code after that. Firstly, I rewrite the code like this "dice_et = dice_metric(y_pred=predictions[:, 1:2, ...], y=ground_truth[:, 1:2, ...]), dice_et, dice_et_not_nans = do_metric_reduction(dice_et, reduction = MetricReduction.None)". However all the dice and hd are non. Then I change the version of monai to 0.5, which can return two values. But all the dice and hd are still non. Can you help me fix this problem or tell me the version of monai you used? Thank you very much!

Hello, dear author. When I tried to run the code, I received an error. It said that the dice metric only had one return value, but we expected two, for example we want dice_et and dice_et_not_nan. Is there any way I can fix this problem? Thank you so much.

Hello, dear author. I have encountered some troubles when trying to implement the 2D multi-lesion segmentation. I want to get the code for 2D multi-lesion segmentation.If possible, can you send me the source code?

Dear author, I have Turned "get_not_nans" to " Ture like that:

dice_metric = DiceMetric(include_background=True, reduction='none', get_not_nans=True)
dice_et, dice_et_not_nan = dice_metric(y_pred=predictions[:, 1:2, ...], y=ground_truth[:, 1:2, ...])

However, I still got the following error:
"dice_et, dice_et_not_nan = dice_metric(y_pred=predictions[:, 1:2, ...], y=ground_truth[:, 1:2, ...])
ValueError: not enough values to unpack (expected 2, got 1)"

How can I fix it?
Looking forward to your help! Thanks!