YOLOv8 Seg

环境配置

信息

参考 RKNN 安装 配置好相关环境。

参考 RKNN Model Zoo 下载示例文件。

模型下载

下载 onnx 模型文件。

X64 Linux PC

cd rknn_model_zoo/examples/yolov8_seg/model/
bash download_model.sh

模型转换

选择目标平台。

rk3588

X64 Linux PC

export TARGET_PLATFORM=rk3588

rk356x

X64 Linux PC

export TARGET_PLATFORM=rk356x

rk3576

X64 Linux PC

export TARGET_PLATFORM=rk3576

将 onnx 模型转换为 rknn 模型。

X64 Linux PC

cd ../python/
python convert.py ../model/yolov8s-seg.onnx ${TARGET_PLATFORM}

C API

编译示例

切换到 rknn_model_zoo 目录下执行 build-linux.sh 编译脚本。

X64 Linux PC

cd ../../..
bash build-linux.sh -t ${TARGET_PLATFORM} -a aarch64 -d yolov8_seg

文件同步

然后将编译生成的 install 目录下的 demo 目录推送到板端。

X64 Linux PC

cd install/${TARGET_PLATFORM}_linux_aarch64/
scp -r rknn_yolov8_seg_demo/ user@your_device_ip:target_directory

运行示例

导出运行时库到环境变量。

Device

cd rknn_yolov8_seg_demo/
export LD_LIBRARY_PATH=./lib

运行示例。

Device

./rknn_yolov8_seg_demo ./model/yolov8_seg.rknn ./model/bus.jpg

$ ./rknn_yolov8_seg_demo ./model/yolov8_seg.rknn ./model/bus.jpg
[RKNN] Can not find libdrm.so
load label ./model/coco_80_labels_list.txt
model input num: 1, output num: 13
input tensors:
  index=0, name=images, n_dims=4, dims=[1, 640, 640, 3], n_elems=1228800, size=1228800, fmt=NHWC, type=INT8, qnt_type=AFFINE, zp=-128, scale=0.003922
output tensors:
  index=0, name=375, n_dims=4, dims=[1, 64, 80, 80], n_elems=409600, size=409600, fmt=NCHW, type=INT8, qnt_type=AFFINE, zp=-61, scale=0.115401
  index=1, name=onnx::ReduceSum_383, n_dims=4, dims=[1, 80, 80, 80], n_elems=512000, size=512000, fmt=NCHW, type=INT8, qnt_type=AFFINE, zp=-128, scale=0.003514
  index=2, name=388, n_dims=4, dims=[1, 1, 80, 80], n_elems=6400, size=6400, fmt=NCHW, type=INT8, qnt_type=AFFINE, zp=-128, scale=0.003540
  index=3, name=354, n_dims=4, dims=[1, 32, 80, 80], n_elems=204800, size=204800, fmt=NCHW, type=INT8, qnt_type=AFFINE, zp=27, scale=0.019863
  index=4, name=395, n_dims=4, dims=[1, 64, 40, 40], n_elems=102400, size=102400, fmt=NCHW, type=INT8, qnt_type=AFFINE, zp=-15, scale=0.099555
  index=5, name=onnx::ReduceSum_403, n_dims=4, dims=[1, 80, 40, 40], n_elems=128000, size=128000, fmt=NCHW, type=INT8, qnt_type=AFFINE, zp=-128, scale=0.003555
  index=6, name=407, n_dims=4, dims=[1, 1, 40, 40], n_elems=1600, size=1600, fmt=NCHW, type=INT8, qnt_type=AFFINE, zp=-128, scale=0.003680
  index=7, name=361, n_dims=4, dims=[1, 32, 40, 40], n_elems=51200, size=51200, fmt=NCHW, type=INT8, qnt_type=AFFINE, zp=30, scale=0.022367
  index=8, name=414, n_dims=4, dims=[1, 64, 20, 20], n_elems=25600, size=25600, fmt=NCHW, type=INT8, qnt_type=AFFINE, zp=-55, scale=0.074253
  index=9, name=onnx::ReduceSum_422, n_dims=4, dims=[1, 80, 20, 20], n_elems=32000, size=32000, fmt=NCHW, type=INT8, qnt_type=AFFINE, zp=-128, scale=0.003813
  index=10, name=426, n_dims=4, dims=[1, 1, 20, 20], n_elems=400, size=400, fmt=NCHW, type=INT8, qnt_type=AFFINE, zp=-128, scale=0.003922
  index=11, name=368, n_dims=4, dims=[1, 32, 20, 20], n_elems=12800, size=12800, fmt=NCHW, type=INT8, qnt_type=AFFINE, zp=43, scale=0.019919
  index=12, name=347, n_dims=4, dims=[1, 32, 160, 160], n_elems=819200, size=819200, fmt=NCHW, type=INT8, qnt_type=AFFINE, zp=-119, scale=0.032336
model is NHWC input fmt
model input height=640, width=640, channel=3
origin size=640x640 crop size=640x640
input image: 640 x 640, subsampling: 4:2:0, colorspace: YCbCr, orientation: 1
scale=1.000000 dst_box=(0 0 639 639) allow_slight_change=1 _left_offset=0 _top_offset=0 padding_w=0 padding_h=0
rga_api version 1.10.1_[0]
rknn_run
-- matmul_by_cpu_uint8 use: 13.651000 ms
-- resize_by_opencv_uint8 use: 3.066000 ms
-- crop_mask_uint8 use: 4.863000 ms
-- seg_reverse use: 0.303000 ms
bus @ (87 137 553 439) 0.911
person @ (109 236 226 534) 0.900
person @ (211 241 283 508) 0.869
person @ (476 234 559 519) 0.866
person @ (79 327 125 514) 0.540
tie @ (248 284 259 310) 0.274
write_image path: out.png width=640 height=640 channel=3 data=0xaaab07e88330

效果展示

Python API

激活虚拟环境

Device

conda activate rknn

运行示例

将相关文件推送到板端执行下面的命令。

Device

python yolov8_seg.py --model_path ../model/yolov8_seg.rknn --target ${TARGET_PLATFORM} --img_save

$ python yolov8_seg.py --model_path ../model/yolov8_seg.rknn --target rk3588 --img_save
/home/radxa/miniforge3/envs/rknn/lib/python3.12/site-packages/rknn/api/rknn.py:51: UserWarning: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html. The pkg_resources package is slated for removal as early as 2025-11-30. Refrain from using this package or pin to Setuptools<81.
  self.rknn_base = RKNNBase(cur_path, verbose)
I rknn-toolkit2 version: 2.3.2
--> Init runtime environment
I target set by user is: rk3588
done
Model-../model/yolov8_seg.rknn is rknn model, starting val
W inference: The 'data_format' is not set, and its default value is 'nhwc'!


IMG: bus.jpg
bus  @ (87 137 553 439) 0.911
person @ (108 236 227 537) 0.900
person @ (211 241 283 508) 0.869
person @ (477 232 559 519) 0.866
person @ (79 327 125 514) 0.540
tie @ (248 284 259 310) 0.274
The segmentation results have been saved to ./result/bus.jpg

效果展示