point_cloud_classification.ipynb: AttributeError: 'dict' object has no attribute 'view'

[msieb1]

Running the cell

engine = ClassificationEngine(PointNet(num_classes=len(categories)),
                              train_loader, val_loader)
engine.fit()

gives

    224 
    225             for idx, batch in enumerate(self.train_loader):
--> 226                 loss, accuracy = self.train_batch(batch)
    227                 self.optimize_batch(loss)
    228                 self.print_train_stats()

/opt/conda/envs/lab42/lib/python3.7/site-packages/kaolin-0.1.0-py3.7-linux-x86_64.egg/kaolin/engine/classification.py in train_batch(self, batch)
    174         data, label = batch
    175         pred = self.model(data)
--> 176         loss = self.criterion(pred, label.view(-1))
    177         self.train_loss_cur_epoch += loss.item()
    178         predlabel = torch.argmax(pred, dim=1)

AttributeError: 'dict' object has no attribute 'view'

Downloaded the ModelNet10 dataset as instructed. Seems like category is nested within the attributes key of the KaolinDatasetItem.