RKNN Model Zoo YOLO exports
Collection
Rockchip Model Zoo conversions and clearly labeled custom extensions for RK3576 and RK3588. • 10 items • Updated
YOLO26-RKNN2
YOLO exports for RK3576 and RK3588. All models were compiled with RKNN Toolkit2 2.3.2.
Available tasks: detect, classify, depth, obb, pose, segment, semantic.
Download model.rknn and metadata.yaml from the same folder under models/<toolkit-version>/<task>/<variant>/<chip>/<precision>/.
The manifest records model and metadata checksums. Original checkpoints, conversion scripts, and their provenance are in source/.
The models and checkpoints are distributed under AGPL-3.0. See LICENSE and source/weights.json.
We converted the detection models on Seeed-Dev using RKNN Toolkit2 2.3.2. Rockchip Model Zoo supplied the ONNX inputs. Each detection entry in the manifest records the input ONNX and output RKNN checksums.
The detection ONNX graphs and their Model Zoo download URLs are recorded in source/onnx/ and manifest.json. These graphs declare the AGPL-3.0 license and their Ultralytics exporter versions.
Models are organized by RKNN Toolkit2 version under models/v<version>/. Each model and its metadata share a folder.
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support