
Pretrains and fine-tunes masked autoencoder vision backbones with NVIDIA TAO
- Open source
- 4K GitHub stars
- Computer vision


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

Trains, evaluates and exports Mask2Former segmentation models through NVIDIA TAO

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

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

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

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

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

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

Trains, evaluates and exports TAO monocular depth models from single RGB images

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

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

Trains, evaluates and exports OCRNet scene text recognition models with TAO
The closest alternatives to Tao train mask auto label are Tao train mask auto encoder, Tao train mask2former, Tao train mask grounding dino, Tao train action recognition and Tao train segformer.
Yes. Tao train mask auto encoder, Tao train mask2former, Tao train mask grounding dino have a free or open-source option.