tao▌

Pose classification using ST-GCN (Spatial Temporal Graph Convolutional Network). Classifies skeleton sequences

Sparse4D for multi-camera temporal 3D object detection and tracking. Uses sparse queries with deformable

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

Standard single-step train/eval/export workflow for any TAO model. Use when training a TAO model on a dataset

OneFormer for universal image segmentation. Unifies panoptic, instance, and semantic segmentation with a

Visual ChangeNet for binary image classification and segmentation in AOI defect detection. Use when training,

OCRNet for scene text recognition. Recognizes text content from cropped text-region images and supports CTC

Optical Inspection for defect detection using Siamese networks. Compares image pairs to detect manufacturing

Person re-identification (ReID). Learns discriminative embeddings to match the same person across different

RT-DETR (Real-Time DEtection TRansformer) for 2D object detection. Designed for real-time inference with