Lightlines
By nvidia

tao-train-oneformer

nvidia1.6k installs

Train one model for three image segmentation tasks.

What it does

Trains, evaluates, quantizes, and exports OneFormer segmentation models and runs them on images.

When to use it

Use for OneFormer training, evaluation, export, quantization, or inference, including requests for universal or task-conditioned segmentation.

How to use it

Give it segmentation datasets and any checkpoint required by the requested operation; it produces model results in a results directory.

What you provide

  • Your files

Uses

Latest review

What you need · 6

Requires Docker for the container-based workflow.

Requires NVIDIA Container Toolkit alongside Docker.

States a minimum of two GPUs with at least 24 GB VRAM per GPU; recommends four GPUs and A100 hardware.


Access · 1

This skill

GitHub

Read

Downloads pretrained Swin weights