简体中文 | English

RKNN Model Zoo

Description

RKNN Model Zoo is developed based on the RKNPU SDK toolchain and provides deployment examples for current mainstream algorithms. Include the process of exporting the RKNN model and using Python API and CAPI to infer the RKNN model.

• Support RK3562, RK3566, RK3568, RK3576, RK3588 , RV1126B platforms.
• Limited support RV1103, RV1106
• Support RV1109, RV1126, RK1808 platforms.

Dependency library installation

RKNN Model Zoo relies on RKNN-Toolkit2 for model conversion. The Android compilation tool chain is required when compiling the Android demo, and the Linux compilation tool chain is required when compiling the Linux demo. For the installation of these dependencies, please refer to the Quick Start documentation at https://github.com/airockchip/rknn-toolkit2/tree/master/doc.

• Please note that the Android compilation tool chain recommends using version r18 or r19. Using other versions may encounter the problem of Cdemo compilation failure.
• Please note that the Linux compilation tool chain recommends using gcc-linaro-6.3.1(aarch64)/gcc-arm-8.3(armhf)/armhf-uclibcgnueabihf(armhf for RV1106/RV1103 series). Using other versions may encounter the problem of Cdemo compilation failure. For detailed compilation guide, please refer to Compilation_Environment_Setup_Guide.md

Model support

In addition to exporting the model from the corresponding respository, the models file are available on https://console.zbox.filez.com/l/8ufwtG (key: rknn).

Category	Name	Dtype	Model Download Link	Support platform
Classification	mobilenet	FP16/INT8	mobilenetv2-12.onnx	RK3562|RK3566|RK3568|RK3576|RK3588|RV1126B

RV1103|RV1106

RK1808|RK3399PRO

RV1109|RV1126 | | Classification | resnet | FP16/INT8 | resnet50-v2-7.onnx | RK3562|RK3566|RK3568|RK3576|RK3588|RV1126B

RK1808|RK3399PRO

RV1109|RV1126 | | Object Detection | yolov5 | FP16/INT8 | ./yolov5s_relu.onnx

./yolov5n.onnx

./yolov5s.onnx

./yolov5m.onnx | RK3562|RK3566|RK3568|RK3576|RK3588|RV1126B

RV1103|RV1106

RK1808|RK3399PRO

RV1109|RV1126 | | Object Detection | yolov6 | FP16/INT8 | ./yolov6n.onnx

./yolov6s.onnx

./yolov6m.onnx | RK3562|RK3566|RK3568|RK3576|RK3588|RV1126B

RK1808|RK3399PRO

RV1109|RV1126 | | Object Detection | yolov7 | FP16/INT8 | ./yolov7-tiny.onnx

./yolov7.onnx | RK3562|RK3566|RK3568|RK3576|RK3588|RV1126B

RK1808|RK3399PRO

RV1109|RV1126 | | Object Detection | yolov8 | FP16/INT8 | ./yolov8n.onnx

./yolov8s.onnx

./yolov8m.onnx | RK3562|RK3566|RK3568|RK3576|RK3588|RV1126B

RK1808|RK3399PRO

RV1109|RV1126 | | Object Detection | yolov8_obb | INT8 | ./yolov8n-obb.onnx | RK3562|RK3566|RK3568|RK3576|RK3588|RV1126B

RK1808|RK3399PRO

RV1109|RV1126 | | Object Detection | yolov10 | FP16/INT8 | ./yolov10n.onnx

./yolov10s.onnx | RK3562|RK3566|RK3568|RK3576|RK3588|RV1126B

RV1103|RV1106

RK1808|RK3399PRO

RV1109|RV1126 | | Object Detection | yolo11 | FP16/INT8 | ./yolo11n.onnx

./yolo11s.onnx

./yolo11m.onnx | RK3562|RK3566|RK3568|RK3576|RK3588|RV1126B

RV1103|RV1106

RK1808|RK3399PRO

RV1109|RV1126 | | Object Detection | yolox | FP16/INT8 | ./yolox_s.onnx

./yolox_m.onnx | RK3562|RK3566|RK3568|RK3576|RK3588|RV1126B

RK1808|RK3399PRO

RV1109|RV1126 | | Object Detection | ppyoloe | FP16/INT8 | ./ppyoloe_s.onnx

./ppyoloe_m.onnx | RK3562|RK3566|RK3568|RK3576|RK3588|RV1126B

RK1808|RK3399PRO

RV1109|RV1126 | | Object Detection | yolo_world | FP16/INT8 | ./yolo_world_v2s.onnx

./clip_text.onnx | RK3562|RK3566|RK3568|RK3576|RK3588|RV1126B

| | Body Pose | yolov8_pose | INT8 | ./yolov8n-pose.onnx | RK3562|RK3566|RK3568|RK3576|RK3588|RV1126B

| | Image Segmentation | deeplabv3 | FP16/INT8 | ./deeplab-v3-plus-mobilenet-v2.pb | RK3562|RK3566|RK3568|RK3576|RK3588|RV1126B

RK1808|RK3399PRO

RV1109|RV1126 | | Image Segmentation | yolov5_seg | FP16/INT8 | ./yolov5n-seg.onnx

./yolov5s-seg.onnx

./yolov5m-seg.onnx | RK3562|RK3566|RK3568|RK3576|RK3588|RV1126B

RK1808|RK3399PRO

RV1109|RV1126 | | Image Segmentation | yolov8_seg | FP16/INT8 | ./yolov8n-seg.onnx

./yolov8s-seg.onnx

./yolov8m-seg.onnx | RK3562|RK3566|RK3568|RK3576|RK3588|RV1126B

RK1808|RK3399PRO

RV1109|RV1126 | | Image Segmentation | ppseg | FP16/INT8 | pp_liteseg_cityscapes.onnx | RK3562|RK3566|RK3568|RK3576|RK3588|RV1126B

RK1808|RK3399PRO

RV1109|RV1126 | | Image Segmentation | mobilesam | FP16 | mobilesam_encoder_tiny.onnx

mobilesam_decoder.onnx | RK3562|RK3566|RK3568|RK3576|RK3588|RV1126B | | Face Key Points | RetinaFace | INT8 | RetinaFace_mobile320.onnx

RetinaFace_resnet50_320.onnx | RK3562|RK3566|RK3568|RK3576|RK3588|RV1126B

RK1808|RK3399PRO

RV1109|RV1126 | | Car Plate Recognition | LPRNet | FP16/INT8 | ./lprnet.onnx | RK3562|RK3566|RK3568|RK3576|RK3588|RV1126B

RV1103|RV1106

RK1808|RK3399PRO

RV1109|RV1126 | | Text Detection | PPOCR-Det | FP16/INT8 | ../ppocrv4_det.onnx | RK3562|RK3566|RK3568|RK3576|RK3588|RV1126B

RK1808|RK3399PRO

RV1109|RV1126 | | Text Recognition | PPOCR-Rec | FP16 | ../ppocrv4_rec.onnx | RK3562|RK3566|RK3568|RK3576|RK3588|RV1126B

RK1808|RK3399PRO

RV1109|RV1126 | | Neural Machine Translation | lite_transformer | FP16 | lite-transformer-encoder-16.onnx

lite-transformer-decoder-16.onnx | RK3562|RK3566|RK3568|RK3576|RK3588|RV1126B

RK1808|RK3399PRO

RV1109|RV1126 | | Image-Text Matching | clip | FP16 | ./clip_images.onnx

./clip_text.onnx | RK3562|RK3566|RK3568|RK3576|RK3588|RV1126B

| | Speech Recognition | wav2vec2 | FP16 | wav2vec2_base_960h_20s.onnx | RK3562|RK3566|RK3568|RK3576|RK3588|RV1126B | | Speech Recognition | whisper | FP16 | whisper_encoder_base_20s.onnx

whisper_decoder_base_20s.onnx | RK3562|RK3566|RK3568|RK3576|RK3588|RV1126B

| | Speech Recognition | zipformer | FP16 | encoder-epoch-99-avg-1.onnx

decoder-epoch-99-avg-1.onnx

joiner-epoch-99-avg-1.onnx | RK3562|RK3566