Run the full DEFT smart-data-augmentation loop for NVIDIA TAO Grounding DINO object detection: zero-shot baseline inference, KPI analysis, per-class gap analysis, SigLIP embedding of weak images, unique-neighbor mining against a source pool, ODVG dataset staging, and retraining — repeated for a fixed number of iterations.
安装
npx skills add NVIDIA/skills --skill tao-run-deft-object-detectionnpx skills add NVIDIA/skills --skill tao-run-deft-object-detection -a claude-code -gnpx skills add NVIDIA/skills --skill tao-run-deft-object-detection -a codex -ggemini skills install https://github.com/NVIDIA/skills.git --path skills/tao-run-deft-object-detectiongh skill install NVIDIA/skills tao-run-deft-object-detectiongit clone --depth 1 https://github.com/NVIDIA/skills /tmp/NVIDIA__skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/NVIDIA__skills/skills/tao-run-deft-object-detection ~/.claude/skills/tao-run-deft-object-detection # Claude Code
cp -R /tmp/NVIDIA__skills/skills/tao-run-deft-object-detection ~/.agents/skills/tao-run-deft-object-detection # Codex, Cursor, Gemini CLI, Copilot, OpenCode