
Guides an agent through training, evaluating and running FoundationStereo stereo depth
- Open source
- 4K GitHub stars
- Design and media

Guides an agent through training, evaluating and running FoundationStereo stereo depth

Trains, evaluates and exports Grounding DINO text-prompted object detectors via TAO

Trains, evaluates, distills and quantizes PyTorch image classifiers inside TAO containers

Pretrains and fine-tunes masked autoencoder vision backbones with NVIDIA TAO

Trains and runs ViT-MAE segmentation models from point or box annotations via Docker

Trains and runs NVIDIA TAO Mask Grounding DINO for text-prompted instance segmentation

Trains, evaluates and exports Mask2Former segmentation models through NVIDIA TAO

Trains and evaluates metric-learning embeddings for retrieval-based visual recognition

Trains vision transformers with self-supervised NVDINOv2 learning on unlabeled images

Trains, evaluates, exports and runs NVPanoptix3D models for 3D panoptic scene segmentation

Trains, evaluates and deploys OCDNet text detection models through TAO in Docker

Trains, evaluates and exports OCRNet scene text recognition models with TAO

Trains, evaluates and exports OneFormer universal segmentation models on TAO with Docker

Trains, evaluates and exports PointPillars 3D LiDAR object detection models with TAO

Trains, evaluates, exports and runs ST-GCN models that classify skeleton pose sequences

Trains, evaluates, exports and runs person re-identification models in Docker

Trains, distills, quantizes and runs RT-DETR real-time object detection models

Guides an agent through training, evaluating and exporting TAO SegFormer segmentation

Runs a standard TAO train, evaluate and export sequence without AutoML loops

Runs tao-daft validate to check NVIDIA TAO DAFT datasets for structure and schema errors

Guides an agent through adding a new cuTile GPU kernel operator to TileGym

Guides an agent through iterative profiling and tuning of cuTile GPU kernels in TileGym

Guides an agent to swap TileGym cuTile kernels into Hugging Face transformers models

Helps agents find and recommend NVIDIA skills from the live catalog before general answers

Launches the AutoMagicCalib microservice and web UI from NGC images with Docker Compose

Predicts biomolecular structures and ligand binding affinity via Boltz2 NIM

Runs masked-codon variant scoring with the public CodonFM Encodon models

Sets up the public CodonFM repo, dev container and Encodon checkpoint downloads

Adds and checks Proteina-Complexa design target definitions in YAML registries

Guides building equivariant tensor products and segmented polynomials with cuEquivariance