
Trains, evaluates, exports and runs TAO models that classify actions in video clips
- Open source
- 4K GitHub stars
- Computer vision


Trains, evaluates, exports and runs TAO models that classify actions in video clips

Runs container-backed hyperparameter search for NVIDIA TAO networks via AutoMLRunner

Gates TAO model launches behind preflight checks, image confirmation and a review step

Trains, evaluates, exports and runs NVIDIA TAO Deformable DETR object detectors

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

Trains, evaluates and exports TAO Sparse4D multi-camera 3D detection and tracking models

Trains, evaluates, exports and runs DINO 2D object detectors via TAO in Docker

Runs InternVideo2-CLIP video-text retrieval, fine-tuning, ONNX export and TensorRT deploy

Guides an agent to port a HuggingFace vision model into the NVIDIA TAO Toolkit

Runs an iterative retrain-and-evaluate loop to improve NVIDIA TAO CLIP image-text

Fine-tunes and runs NVIDIA CLIP models for image-text retrieval and zero-shot

Chains AutoML tuning, a DEFT data-improvement loop and a final AutoML pass for PCB AOI
The closest alternatives to Tao train single step are Tao train action recognition, Tao run automl, Tao launch workflow, Tao train deformable detr and Tao train rtdetr.
Yes. Tao train action recognition, Tao run automl, Tao launch workflow have a free or open-source option.