Agent skill · nvidia
rtvi-cv-customize-model
How to swap the DeepStream CV detection model in the VSS Alerts Blueprint verification (2d_cv) mode - covers ONNX export, custom bbox parsers, compose mount gotchas, nvinfer config, runtime TRT engine build, deployment, and a segmentation-capable model addendum handoff.
What it needs
About 8k tokens when loaded.
What this skill does
CV Detection Model Customization — VSS Alerts Blueprint (2dcv mode only) The RT-CV perception container (vss-rt-cv) runs a DeepStream pipeline with a configurable primary GIE (GPU Inference Engine). By default it uses GDINO or RTDETR. This guide covers replacing it with any ONNX-format model, using YOLOv11 COCO 80 as the worked example. This only applies to --mode verification (2dcv). Real-time alerts mode (2dvlm) has no CV detector. For instance-segmentation or detection-plus-mask models, complete references/segmentation-model-contract.md before writing parser or handoff code. --- When to use Use this skill when the user wants to: swap the stock vss-rt-cv detector for another ONNX model in verification mode, debug a broken ONNX staging path, ghost-directory bind mount, or missing runtime TRT engine build, fix a DeepStream parser load failure such as dlsym failed on the bbox parser symbol. Do not use this skill for: 2dvlm real-time alerts mode, scaffolding a brand-new standalone RTVI CV microservice (use rtvi-cv-scaffold-vss-service). Instructions Keep the answer scoped to VSS Alerts Blueprint verification mode (2dcv) unless the user explicitly asks to compare modes. Paths beginning with deploy/docker/ are relative to the VSS Blueprint repository, not the DeepStream repository. Clone or reuse a VSS checkout that is v3.2.1 or compatible, then run these commands from that repository root (see VSS Quickstart). If the user asks about ONNX staging or a compose mount, explicitly say that mounting a missing file path is wrong: use the stock parent-directory mount, keep the ONNX under ${VSSDATADIR}/models/yolo, and re-stage the ONNX file after any dev-profile.sh up that recreates the models directory. If the user asks about parser load failures, line up parse-bbox-func-name, the extern "C" function symbol, and CHECKCUSTOMPARSEFUNCPROTOTYPE(...), then rebuild the .so with both DeepStream and CUDA include paths present. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills nvidia/rtvi-cv-customize-model