RT-DETR (Real-Time DEtection TRansformer) for 2D object detection. Designed for real-time inference with competitive accuracy and supports distillation and quantization for deployment optimization. Use when training, evaluating, distilling, quantizing, exporting, or running inference for a TAO RT-DETR model.
安装
npx skills add NVIDIA/skills --skill tao-train-rtdetrnpx skills add NVIDIA/skills --skill tao-train-rtdetr -a claude-code -gnpx skills add NVIDIA/skills --skill tao-train-rtdetr -a codex -ggemini skills install https://github.com/NVIDIA/skills.git --path skills/tao-train-rtdetrgh skill install NVIDIA/skills tao-train-rtdetrgit 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-rtdetr ~/.claude/skills/tao-train-rtdetr # Claude Code
cp -R /tmp/NVIDIA__skills/skills/tao-train-rtdetr ~/.agents/skills/tao-train-rtdetr # Codex, Cursor, Gemini CLI, Copilot, OpenCode