Solved the problem that wandb could not display masks_pred in the multi-category segmentation problem.If we do not modify it, we may encounter the following error message:mode, rawmode = _fromarray_typemap[typekey] KeyError: ((1, 1, 15), '|u1').ps:15 is the number of categories.

Former-commit-id: ff0c2ffa33c945a491e85ef44e89891e9a7c435d

train.py

@@ -130,7 +130,7 @@ def train_net(net,
                             'images': wandb.Image(images[0].cpu()),
                             'masks': {
                                 'true': wandb.Image(true_masks[0].float().cpu()),
-                                'pred': wandb.Image(torch.softmax(masks_pred, dim=1)[0].float().cpu()),
+                                'pred': wandb.Image(torch.softmax(masks_pred, dim=1).argmax(dim=1)[0].float().cpu()),
                             },
                             'step': global_step,
                             'epoch': epoch,