rknn_model_zoo

[简体中文](README_CN.md) | [English](README.md) # 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](./docs/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](https://github.com/onnx/models/tree/8e893eb39b131f6d3970be6ebd525327d3df34ea/vision/classification/mobilenet/model/mobilenetv2-12.onnx) | FP16/INT8 | [mobilenetv2-12.onnx](https://ftrg.zbox.filez.com/v2/delivery/data/95f00b0fc900458ba134f8b180b3f7a1/examples/mobilenet/mobilenetv2-12.onnx) | RK3562\|RK3566\|RK3568\|RK3576\|RK3588\|RV1126B
RV1103\|RV1106
RK1808\|RK3399PRO
RV1109\|RV1126 | | Classification | [resnet](https://github.com/onnx/models/tree/8e893eb39b131f6d3970be6ebd525327d3df34ea/vision/classification/resnet/model/resnet50-v2-7.onnx) | FP16/INT8 | [resnet50-v2-7.onnx](https://ftrg.zbox.filez.com/v2/delivery/data/95f00b0fc900458ba134f8b180b3f7a1/examples/resnet/resnet50-v2-7.onnx) | RK3562\|RK3566\|RK3568\|RK3576\|RK3588\|RV1126B
RK1808\|RK3399PRO
RV1109\|RV1126 | | Object Detection | [yolov5](https://github.com/airockchip/yolov5) | FP16/INT8 | [./yolov5s_relu.onnx](https://ftrg.zbox.filez.com/v2/delivery/data/95f00b0fc900458ba134f8b180b3f7a1/examples/yolov5/yolov5s_relu.onnx)
[./yolov5n.onnx](https://ftrg.zbox.filez.com/v2/delivery/data/95f00b0fc900458ba134f8b180b3f7a1/examples/yolov5/yolov5n.onnx)
[./yolov5s.onnx](https://ftrg.zbox.filez.com/v2/delivery/data/95f00b0fc900458ba134f8b180b3f7a1/examples/yolov5/yolov5s.onnx)
[./yolov5m.onnx](https://ftrg.zbox.filez.com/v2/delivery/data/95f00b0fc900458ba134f8b180b3f7a1/examples/yolov5/yolov5m.onnx) | RK3562\|RK3566\|RK3568\|RK3576\|RK3588\|RV1126B
RV1103\|RV1106
RK1808\|RK3399PRO
RV1109\|RV1126 | | Object Detection | [yolov6](https://github.com/airockchip/yolov6) | FP16/INT8 | [./yolov6n.onnx](https://ftrg.zbox.filez.com/v2/delivery/data/95f00b0fc900458ba134f8b180b3f7a1/examples/yolov6/yolov6n.onnx)
[./yolov6s.onnx](https://ftrg.zbox.filez.com/v2/delivery/data/95f00b0fc900458ba134f8b180b3f7a1/examples/yolov6/yolov6s.onnx)
[./yolov6m.onnx](https://ftrg.zbox.filez.com/v2/delivery/data/95f00b0fc900458ba134f8b180b3f7a1/examples/yolov6/yolov6m.onnx) | RK3562\|RK3566\|RK3568\|RK3576\|RK3588\|RV1126B
RK1808\|RK3399PRO
RV1109\|RV1126 | | Object Detection | [yolov7](https://github.com/airockchip/yolov7) | FP16/INT8 | [./yolov7-tiny.onnx](https://ftrg.zbox.filez.com/v2/delivery/data/95f00b0fc900458ba134f8b180b3f7a1/examples/yolov7/yolov7-tiny.onnx)
[./yolov7.onnx](https://ftrg.zbox.filez.com/v2/delivery/data/95f00b0fc900458ba134f8b180b3f7a1/examples/yolov7/yolov7.onnx) | RK3562\|RK3566\|RK3568\|RK3576\|RK3588\|RV1126B
RK1808\|RK3399PRO
RV1109\|RV1126 | | Object Detection | [yolov8](https://github.com/airockchip/ultralytics_yolov8) | FP16/INT8 | [./yolov8n.onnx](https://ftrg.zbox.filez.com/v2/delivery/data/95f00b0fc900458ba134f8b180b3f7a1/examples/yolov8/yolov8n.onnx)
[./yolov8s.onnx](https://ftrg.zbox.filez.com/v2/delivery/data/95f00b0fc900458ba134f8b180b3f7a1/examples/yolov8/yolov8s.onnx)
[./yolov8m.onnx](https://ftrg.zbox.filez.com/v2/delivery/data/95f00b0fc900458ba134f8b180b3f7a1/examples/yolov8/yolov8m.onnx) | RK3562\|RK3566\|RK3568\|RK3576\|RK3588\|RV1126B
RK1808\|RK3399PRO
RV1109\|RV1126 | | Object Detection | [yolov8_obb](https://github.com/airockchip/ultralytics_yolov8) | INT8 | [./yolov8n-obb.onnx](https://ftrg.zbox.filez.com/v2/delivery/data/95f00b0fc900458ba134f8b180b3f7a1/examples/yolov8_obb/yolov8n-obb.onnx) | RK3562\|RK3566\|RK3568\|RK3576\|RK3588\|RV1126B
RK1808\|RK3399PRO
RV1109\|RV1126 | | Object Detection | [yolov10](https://github.com/THU-MIG/yolov10) | FP16/INT8 | [./yolov10n.onnx](https://ftrg.zbox.filez.com/v2/delivery/data/95f00b0fc900458ba134f8b180b3f7a1/examples/yolov10/yolov10n.onnx)
[./yolov10s.onnx](https://ftrg.zbox.filez.com/v2/delivery/data/95f00b0fc900458ba134f8b180b3f7a1/examples/yolov10/yolov10s.onnx) | RK3562\|RK3566\|RK3568\|RK3576\|RK3588\|RV1126B
RV1103\|RV1106
RK1808\|RK3399PRO
RV1109\|RV1126 | | Object Detection | [yolo11](https://github.com/airockchip/ultralytics_yolo11) | FP16/INT8 | [./yolo11n.onnx](https://ftrg.zbox.filez.com/v2/delivery/data/95f00b0fc900458ba134f8b180b3f7a1/examples/yolo11/yolo11n.onnx)
[./yolo11s.onnx](https://ftrg.zbox.filez.com/v2/delivery/data/95f00b0fc900458ba134f8b180b3f7a1/examples/yolo11/yolo11s.onnx)
[./yolo11m.onnx](https://ftrg.zbox.filez.com/v2/delivery/data/95f00b0fc900458ba134f8b180b3f7a1/examples/yolo11/yolo11m.onnx) | RK3562\|RK3566\|RK3568\|RK3576\|RK3588\|RV1126B
RV1103\|RV1106
RK1808\|RK3399PRO
RV1109\|RV1126 | | Object Detection | [yolox](https://github.com/airockchip/YOLOX) | FP16/INT8 | [./yolox_s.onnx](https://ftrg.zbox.filez.com/v2/delivery/data/95f00b0fc900458ba134f8b180b3f7a1/examples/yolox/yolox_s.onnx)
[./yolox_m.onnx](https://ftrg.zbox.filez.com/v2/delivery/data/95f00b0fc900458ba134f8b180b3f7a1/examples/yolox/yolox_m.onnx) | RK3562\|RK3566\|RK3568\|RK3576\|RK3588\|RV1126B
RK1808\|RK3399PRO
RV1109\|RV1126 | | Object Detection | [ppyoloe](https://github.com/PaddlePaddle/PaddleDetection/blob/release/2.6/configs/ppyoloe) | FP16/INT8 | [./ppyoloe_s.onnx](https://ftrg.zbox.filez.com/v2/delivery/data/95f00b0fc900458ba134f8b180b3f7a1/examples/ppyoloe/ppyoloe_s.onnx)
[./ppyoloe_m.onnx](https://ftrg.zbox.filez.com/v2/delivery/data/95f00b0fc900458ba134f8b180b3f7a1/examples/ppyoloe/ppyoloe_m.onnx) | RK3562\|RK3566\|RK3568\|RK3576\|RK3588\|RV1126B
RK1808\|RK3399PRO
RV1109\|RV1126 | | Object Detection | [yolo_world](https://github.com/AILab-CVC/YOLO-World) | FP16/INT8 | [./yolo_world_v2s.onnx](https://ftrg.zbox.filez.com/v2/delivery/data/95f00b0fc900458ba134f8b180b3f7a1/examples/yolo_world/yolo_world_v2s.onnx)
[./clip_text.onnx](https://ftrg.zbox.filez.com/v2/delivery/data/95f00b0fc900458ba134f8b180b3f7a1/examples/yolo_world/clip_text.onnx) | RK3562\|RK3566\|RK3568\|RK3576\|RK3588\|RV1126B
| | Body Pose | [yolov8_pose](https://github.com/airockchip/ultralytics_yolov8) | INT8 | [./yolov8n-pose.onnx](https://ftrg.zbox.filez.com/v2/delivery/data/95f00b0fc900458ba134f8b180b3f7a1/examples/yolov8_pose/yolov8n-pose.onnx) | RK3562\|RK3566\|RK3568\|RK3576\|RK3588\|RV1126B
| | Image Segmentation | deeplabv3 | FP16/INT8 | [./deeplab-v3-plus-mobilenet-v2.pb](https://ftrg.zbox.filez.com/v2/delivery/data/95f00b0fc900458ba134f8b180b3f7a1/examples/deeplabv3/deeplab-v3-plus-mobilenet-v2.pb) | RK3562\|RK3566\|RK3568\|RK3576\|RK3588\|RV1126B
RK1808\|RK3399PRO
RV1109\|RV1126 | | Image Segmentation | [yolov5_seg](https://github.com/airockchip/yolov5) | FP16/INT8 | [./yolov5n-seg.onnx](https://ftrg.zbox.filez.com/v2/delivery/data/95f00b0fc900458ba134f8b180b3f7a1/examples/yolov5_seg/yolov5n-seg.onnx)
[./yolov5s-seg.onnx](https://ftrg.zbox.filez.com/v2/delivery/data/95f00b0fc900458ba134f8b180b3f7a1/examples/yolov5_seg/yolov5s-seg.onnx)
[./yolov5m-seg.onnx](https://ftrg.zbox.filez.com/v2/delivery/data/95f00b0fc900458ba134f8b180b3f7a1/examples/yolov5_seg/yolov5m-seg.onnx) | RK3562\|RK3566\|RK3568\|RK3576\|RK3588\|RV1126B
RK1808\|RK3399PRO
RV1109\|RV1126 | | Image Segmentation | [yolov8_seg](https://github.com/airockchip/ultralytics_yolov8) | FP16/INT8 | [./yolov8n-seg.onnx](https://ftrg.zbox.filez.com/v2/delivery/data/95f00b0fc900458ba134f8b180b3f7a1/examples/yolov8_seg/yolov8n-seg.onnx)
[./yolov8s-seg.onnx](https://ftrg.zbox.filez.com/v2/delivery/data/95f00b0fc900458ba134f8b180b3f7a1/examples/yolov8_seg/yolov8s-seg.onnx)
[./yolov8m-seg.onnx](https://ftrg.zbox.filez.com/v2/delivery/data/95f00b0fc900458ba134f8b180b3f7a1/examples/yolov8_seg/yolov8m-seg.onnx) | RK3562\|RK3566\|RK3568\|RK3576\|RK3588\|RV1126B
RK1808\|RK3399PRO
RV1109\|RV1126 | | Image Segmentation | [ppseg](https://github.com/PaddlePaddle/PaddleSeg/tree/release/2.8) | FP16/INT8 | [pp_liteseg_cityscapes.onnx](https://ftrg.zbox.filez.com/v2/delivery/data/95f00b0fc900458ba134f8b180b3f7a1/examples/ppseg/pp_liteseg_cityscapes.onnx) | RK3562\|RK3566\|RK3568\|RK3576\|RK3588\|RV1126B
RK1808\|RK3399PRO
RV1109\|RV1126 | | Image Segmentation | [mobilesam](https://github.com/ChaoningZhang/MobileSAM) | FP16 | [mobilesam_encoder_tiny.onnx](https://ftrg.zbox.filez.com/v2/delivery/data/95f00b0fc900458ba134f8b180b3f7a1/examples/mobilesam/mobilesam_encoder_tiny.onnx)
[mobilesam_decoder.onnx](https://ftrg.zbox.filez.com/v2/delivery/data/95f00b0fc900458ba134f8b180b3f7a1/examples/mobilesam/mobilesam_decoder.onnx) | RK3562\|RK3566\|RK3568\|RK3576\|RK3588\|RV1126B | | Face Key Points | [RetinaFace](https://github.com/biubug6/Pytorch_Retinaface) | INT8 | [RetinaFace_mobile320.onnx](https://ftrg.zbox.filez.com/v2/delivery/data/95f00b0fc900458ba134f8b180b3f7a1/examples/RetinaFace/RetinaFace_mobile320.onnx)
[RetinaFace_resnet50_320.onnx](https://ftrg.zbox.filez.com/v2/delivery/data/95f00b0fc900458ba134f8b180b3f7a1/examples/RetinaFace/RetinaFace_resnet50_320.onnx) | RK3562\|RK3566\|RK3568\|RK3576\|RK3588\|RV1126B
RK1808\|RK3399PRO
RV1109\|RV1126 | | Car Plate Recognition | [LPRNet](https://github.com/sirius-ai/LPRNet_Pytorch/) | FP16/INT8 | [./lprnet.onnx](https://ftrg.zbox.filez.com/v2/delivery/data/95f00b0fc900458ba134f8b180b3f7a1/examples/LPRNet/lprnet.onnx) | RK3562\|RK3566\|RK3568\|RK3576\|RK3588\|RV1126B
RV1103\|RV1106
RK1808\|RK3399PRO
RV1109\|RV1126 | | Text Detection | [PPOCR-Det](https://github.com/PaddlePaddle/PaddleOCR/tree/release/2.7) | FP16/INT8 | [../ppocrv4_det.onnx](https://ftrg.zbox.filez.com/v2/delivery/data/95f00b0fc900458ba134f8b180b3f7a1/examples/PPOCR/ppocrv4_det.onnx) | RK3562\|RK3566\|RK3568\|RK3576\|RK3588\|RV1126B
RK1808\|RK3399PRO
RV1109\|RV1126 | | Text Recognition | [PPOCR-Rec](https://github.com/PaddlePaddle/PaddleOCR/tree/release/2.7) | FP16 | [../ppocrv4_rec.onnx](https://ftrg.zbox.filez.com/v2/delivery/data/95f00b0fc900458ba134f8b180b3f7a1/examples/PPOCR/ppocrv4_rec.onnx) | RK3562\|RK3566\|RK3568\|RK3576\|RK3588\|RV1126B
RK1808\|RK3399PRO
RV1109\|RV1126 | | Neural Machine Translation | [lite_transformer](https://github.com/airockchip/lite-transformer) | FP16 | [lite-transformer-encoder-16.onnx](https://ftrg.zbox.filez.com/v2/delivery/data/95f00b0fc900458ba134f8b180b3f7a1/examples/lite_transformer/lite-transformer-encoder-16.onnx)
[lite-transformer-decoder-16.onnx](https://ftrg.zbox.filez.com/v2/deliver