NVDINOv2 for self-supervised visual representation learning. Trains vision transformers via self-distillation (teacher-student) without labels and produces general-purpose visual features. Use when training, exporting, or running inference for a TAO NVDINOv2 backbone. Trigger phrases include "train NVDINOv2", "self-supervised ViT pretraining", "DINOv2 backbone", "visual representation learning".
安装
npx skills add NVIDIA/skills --skill tao-train-nvdinov2npx skills add NVIDIA/skills --skill tao-train-nvdinov2 -a claude-code -gnpx skills add NVIDIA/skills --skill tao-train-nvdinov2 -a codex -ggemini skills install https://github.com/NVIDIA/skills.git --path skills/tao-train-nvdinov2gh skill install NVIDIA/skills tao-train-nvdinov2git 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-nvdinov2 ~/.claude/skills/tao-train-nvdinov2 # Claude Code
cp -R /tmp/NVIDIA__skills/skills/tao-train-nvdinov2 ~/.agents/skills/tao-train-nvdinov2 # Codex, Cursor, Gemini CLI, Copilot, OpenCode