TypeError: 'NoneType' object is not subscriptable

### Checklist

- [X] I have searched for [similar issues](https://github.com/isl-org/Open3D-ML/issues).
- [X] I have tested with the [latest development wheel](http://www.open3d.org/docs/latest/getting_started.html#development-version-pip).
- [X] I have checked the [release documentation](http://www.open3d.org/docs/release/) and the [latest documentation](http://www.open3d.org/docs/latest/) (for `master` branch).

### My Question

Hi

When I do pipeline_run_test with the trained model, I get an error. Can you help?

test 0/1: 100%|█████████▉| 2901299/2901742 [02:29<00:01, 319.36it/s]

test 0/1: 100%|██████████| 2901742/2901742 [02:30<00:00, 385.56it/s]

test 0/1: 100%|██████████| 2901742/2901742 [02:40<00:00, 385.56it/s]INFO - 2022-06-27 21:50:11,355 - parislille3d - Saved ajaccio_2 in ./test/ParisLille3D/ajaccio_2.txt.
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
[](https://localhost:8080/#) in ()
28
29 # evaluate performance on the test set; this will write logs to './logs'.
---> 30 pipeline.run_test()

[/usr/local/lib/python3.7/dist-packages/open3d/_ml3d/torch/pipelines/semantic_segmentation.py](https://localhost:8080/#) in run_test(self)
259 results, inputs['data'], 0, save_gt=False)
260 log.info(
--> 261 f"Overall Testing Accuracy : {self.metric_test.acc()[-1]}, mIoU : {self.metric_test.iou()[-1]}"
262 )
263

TypeError: 'NoneType' object is not subscriptable