Vrt Add Model Crate

Use when adding a new model crate to vision-rt (a new detector/segmenter/depth/pose net) — crate layout, the async caller-owned pattern, classifying engine outputs by shape, from_engine_file/from_onnx/from_hub constructors, vrt-hub registration, export/build scripts, and the build/clippy discipline. Copy vrt-rfdetr-seg or vrt-depth-anything as the template.

kornia Updated
RF-DETR-Seg + Depth Anything V2 + a 3D tracker on one CUDA stream

File contents

kornia/vision-rt commit 4adead4350

Frequently asked questions

npx get-skill add kornia/vrt-add-model-crate