
Trains and runs ViT-MAE segmentation models from point or box annotations via Docker
- Open source
- 4K GitHub stars
- Computer vision

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

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

Guides an agent through setting up and running NVIDIA CDF auto-labeling pipelines

Guides an agent through building NVIDIA DeepStream video analytics pipelines in Python

Guides an agent through importing an object-detection model into NVIDIA DeepStream

Runs NVIDIA's DeepStream Multi-View 3D Tracking app on sample or custom multi-camera video

Installs and repairs the FoundationPose perception pipeline and builds its depth engines

Scores object detection predictions against ground truth to produce per-class mAP metrics

Finds the weakest VCN classify predictions and ranks them for augmentation via TAO

Calibrates multi-camera MP4 recordings through the AutoMagicCalib REST API