Running into some issues with training a new dataset with jetson-inference

I am trying to train a new dataset that I’ve created. I captured images of a mask as shown in the tutorial and they are saved under jetson-inference/python/training/classification/data/dataset/train/mask. Now, I want to train the data set. So i cd to jetson-inference/python/training/classification and run the command "python3 --model-dir=models/mask data/dataset/train/mask. I think I may be running the wrong command? Because terminal just returns this:

Use GPU: 0 for training
Traceback (most recent call last):
File “”, line 506, in
File “”, line 135, in main
main_worker(args.gpu, ngpus_per_node, args)
File “”, line 171, in main_worker
File “/usr/local/lib/python3.6/dist-packages/torchvision-0.7.0a0+78ed10c-py3.6-linux-aarch64.egg/torchvision/datasets/”, line 208, in init
File “/usr/local/lib/python3.6/dist-packages/torchvision-0.7.0a0+78ed10c-py3.6-linux-aarch64.egg/torchvision/datasets/”, line 94, in init
classes, class_to_idx = self._find_classes(self.root)
File “/usr/local/lib/python3.6/dist-packages/torchvision-0.7.0a0+78ed10c-py3.6-linux-aarch64.egg/torchvision/datasets/”, line 123, in _find_classes
classes = [ for d in os.scandir(dir) if d.is_dir()]
FileNotFoundError: [Errno 2] No such file or directory: ‘data/dataset/train/mask/train’

I think I get the same thing when I try to retrain the cat_dog dataset