Mask2Former for universal image segmentation (panoptic, instance, and semantic). Transformer-based with masked attention for high-quality segmentation results. Use when training, evaluating, exporting, quantizing, or running inference for a TAO Mask2Former model.
Install
npx skills add NVIDIA/skills --skill tao-train-mask2formernpx skills add NVIDIA/skills --skill tao-train-mask2former -a claude-code -gnpx skills add NVIDIA/skills --skill tao-train-mask2former -a codex -ggemini skills install https://github.com/NVIDIA/skills.git --path skills/tao-train-mask2formergh skill install NVIDIA/skills tao-train-mask2formergit clone --depth 1 https://github.com/NVIDIA/skills /tmp/NVIDIA__skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/NVIDIA__skills/skills/tao-train-mask2former ~/.claude/skills/tao-train-mask2former # Claude Code
cp -R /tmp/NVIDIA__skills/skills/tao-train-mask2former ~/.agents/skills/tao-train-mask2former # Codex, Cursor, Gemini CLI, Copilot, OpenCode