Results for “dataplane-v2”

Trains vision transformers via self-distillation without labels for self-supervised visual representation learning, and supports export and inference of NVDINOv2 backbones.

Finetune the NV-Generate-CTMR MAISI VAE/autoencoder on user-supplied CT or MRI NIfTI volumes using a staged config and datalist workflow.

Guides machine learning development with experiment tracking, hyperparameter optimization, model registry, and MLOps pipeline integration.