Open3DML training pipeline doesnt find labels -- where do I config this?

[runra]

HI All ML Gurus,

The crux of the question: How do I structure my data set so this code finds the training labels and the images?

I'm trying to use some of the example code to test out training with the semantickitti data set.
I've downloaded it, and got semantic segmentation to work.

However, when I try to run the following code, it cannot find the labels...(FileNotFoundError: Label file)
`import open3d.ml as _ml3d
import open3d.ml.torch as ml3d

cfg_file = "/home/uname/PycharmProjects/Open3DML-Clean3/Open3D-ML-master/ml3d/configs/randlanet_semantickitti.yml"
cfg = _ml3d.utils.Config.load_from_file(cfg_file)

#model = ml3d.models.RandLANet(**cfg.model)
cfg.dataset['dataset_path'] = "/media/uname/examplePCD/data_odometry_velodyne/"

use a cache for storing the results of the preprocessing (default path is './logs/cache')

dataset = ml3d.datasets.SemanticKITTI(dataset_path="/media/uname/examplePCD/data_odometry", use_cache=True)

create the model with random initialization.

#model = RandLANet()
model = ml3d.models.RandLANet()

pipeline = ml3d.pipelines.SemanticSegmentation(model=model, dataset=dataset, max_epoch=100)

prints training progress in the console.

pipeline.run_train()`

Now...the labels are in:
/media/uname/examplePCD/data_odometry_labels

How do I configure the pipeline and the above script to find both the labels and the training data?

Thanks for your help.

[AdityaPatel1068]

Hey , I want to know what config you used to run the open3d model, I am unable to find the correct version on windows 10