Use this skill to bring a supported object-detection vision model from HuggingFace or NVIDIA NGC into an NVIDIA DeepStream pipeline with end-to-end automation: ONNX download, SafeTensors export, TRT engine build, custom nvinfer bbox parser, multi-stream benchmark, and PDF report. Object detection models only.
安装
npx skills add NVIDIA/skills --skill deepstream-import-vision-modelnpx skills add NVIDIA/skills --skill deepstream-import-vision-model -a claude-code -gnpx skills add NVIDIA/skills --skill deepstream-import-vision-model -a codex -ggemini skills install https://github.com/NVIDIA/skills.git --path skills/deepstream-import-vision-modelgh skill install NVIDIA/skills deepstream-import-vision-modelgit clone --depth 1 https://github.com/NVIDIA/skills /tmp/NVIDIA__skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/NVIDIA__skills/skills/deepstream-import-vision-model ~/.claude/skills/deepstream-import-vision-model # Claude Code
cp -R /tmp/NVIDIA__skills/skills/deepstream-import-vision-model ~/.agents/skills/deepstream-import-vision-model # Codex, Cursor, Gemini CLI, Copilot, OpenCode