
Remote SLURM GPU cluster execution over SSH with sbatch/srun, Pyxis/Enroot containers, and Lustre-backed
- Open source
- 4K GitHub stars

Remote SLURM GPU cluster execution over SSH with sbatch/srun, Pyxis/Enroot containers, and Lustre-backed


BEVFusion for multi-sensor 3D object detection




Monocular depth estimation using Metric Depth Anything v2 or Relative Depth Anything architectures

DINO (DETR with Improved DeNoising Anchor Boxes) for 2D object detection


Real-time stereo depth estimation using FastFoundationStereo (FFS), the distilled bp2 commercial variant of

Stereo depth estimation using FoundationStereo


PyTorch-based TAO image classification

Masked Auto-Encoder (MAE) for self-supervised pretraining and fine-tuning

MAL (Mask Auto-Label) for weakly-supervised segmentation

Mask Grounding DINO for grounded instance segmentation

Mask2Former for universal image segmentation (panoptic, instance, and semantic)

Metric-learning recognition (ml-recog) for fine-grained visual recognition

NVDINOv2 for self-supervised visual representation learning

NVPanoptix3D for panoptic 3D scene reconstruction from posed RGB images




PointPillars for 3D object detection from LiDAR point clouds

Pose classification using ST-GCN (Spatial Temporal Graph Convolutional Network)


RT-DETR (Real-Time DEtection TRansformer) for 2D object detection


Standard single-step train/eval/export workflow for any TAO model

Run `tao-daft validate` to check NVIDIA TAO DAFT datasets for structure, schema, and cross-reference errors