Skip to main content

YOLOv8 Seg

This document describes how to run YOLOv8 Seg on NPU.

info

Refer to Model Zoo Download for the example.

YOLOv8 Seg Example Directory Structure:

$ tree ./
./
├── CMakeLists.txt
├── convert_model
│   ├── config_yml.py
│   ├── convert_model_env.sh
│   ├── python
│   │   ├── onnx_extract.py
│   │   └── yolov8s-seg_640.txt
│   └── yolov8s-seg_10.txt
├── figures
│   ├── diff_img.png
│   └── out_yolov8_seg.png
├── main.cpp
├── model
│   ├── bus.jpg
│   └── dog.jpg
├── model_config.h
├── README.md
├── yolov8_seg_10_post.cpp
└── yolov8_seg_10_pre.cpp

Model Conversion​

Configure Virtual Environment​

X86 Linux PC
python -m venv .venv && source .venv/bin/activate
pip install ultralytics onnxsim

Export ONNX Model​

X86 Linux PC
cd convert_model/python/
yolo export model=yolov8s-seg.pt format=onnx dynamic=True opset=11

Fixed Shape​

X86 Linux PC
python3 -m onnxsim yolov8s-seg.onnx yolov8s-seg_640.onnx --input-shape=1,3,640,640

Prune Model​

X86 Linux PC
python3 onnx_extract.py
cd ..
X86 Linux PC
./convert_model_env.sh

Model Import/Quantization/Conversion​

You need to enter the container development environment first. Refer to the Create Container section in Model Zoo Download.

info

Different platforms use corresponding Docker images:

  • A733: ubuntu-npu:v2.0.10.1
  • T527: ubuntu-npu:v1.8.11
X86 Linux PC
docker exec -it model-zoo /bin/bash

After entering the container, navigate to the corresponding directory and run the script.

X86 Linux PC
cd /workspace/examples/yolov8_seg/convert_model/
X86 Linux PC
./pegasus_import.sh yolov8s-seg_10
./pegasus_quantize.sh yolov8s-seg_10 uint8 12
X86 Linux PC
./pegasus_export_ovx_nbg.sh yolov8s-seg_10 uint8 a733

The exported model files are stored in the ../model directory.

Compile Example​

Now you can compile the example. First exit the container, then execute the following command to compile the example.

First, you need to configure third-party libraries and cross-compilation toolchain.

info

You can skip this step if you have already configured third-party libraries and cross-compilation toolchain in other examples.

X86 Linux PC
cd ../../../3rdparty/opencv/
unzip opencv-4.9.0-aarch64-linux-sunxi-glibc.zip
cd ../../0-toolchains/

You need to manually download via this link first, then place it in 0-toolchains/ before executing the following command:

X86 Linux PC
tar -xvf gcc-arm-10.2-2020.11-x86_64-aarch64-none-linux-gnu.tar.xz
X86 Linux PC
cd ../examples/yolov8_seg/
X86 Linux PC
../build_linux.sh -t a733 -s debian11

Model Deployment​

After compilation, the example will be installed in the install directory. You can use scp to transfer it to the board.

Configure NPU Driver​

info

You can skip this step if you have already configured NPU driver in other examples.

Transfer the driver library to the board's lib directory via scp.

  • A733 corresponds to the common/lib_linux_aarch64/A733 directory
  • T527 corresponds to the common/lib_linux_aarch64/T527 directory

Then execute the following command to export to environment variables.

Radxa SBC
echo 'export LD_LIBRARY_PATH=$HOME/lib:$LD_LIBRARY_PATH' >> ~/.bashrc

Run Example​

After configuring the driver, you can run the example.

tip

For T527 platform, you need to first enable NPU by referring to the A5E's "Enable NPU on Board" documentation, then use the following command to grant the current user permission to use /dev/vipcore.

Radxa SBC
sudo chmod 777 /dev/vipcore
Radxa SBC
cd yolov8_seg_demo_linux_a733/
Radxa SBC
chmod +x ./yolov8_seg_demo_a733
./yolov8_seg_demo_a733 -nb model/yolov8s-seg_10_uint8_a733.nb -i model/dog.jpg

The running result is as follows:

$ ./yolov8_seg_demo_a733 -nb model/yolov8s-seg_10_uint8_a733.nb -i model/dog.jpg
model_file=model/yolov8s-seg_10_uint8_a733.nb, input=model/dog.jpg, loop_count=1, malloc_mbyte=10
VIPLite driver software version 2.0.3.2-AW-2024-08-30
input  0 dim 3 640 640 1, data_format=2, quant_format=0, name=input/output[0], none-quant
output 0 dim 80 80 64 1, data_format=0, name=uid_19_out_0b_uid_1_out_0, none-quant
output 1 dim 80 80 80 1, data_format=0, name=uid_18_out_0b_uid_1_out_0, none-quant
output 2 dim 80 80 32 1, data_format=0, name=uid_17_out_0b_uid_1_out_0, none-quant
output 3 dim 40 40 64 1, data_format=0, name=uid_16_out_0b_uid_1_out_0, none-quant
output 4 dim 40 40 80 1, data_format=0, name=uid_15_out_0b_uid_1_out_0, none-quant
output 5 dim 40 40 32 1, data_format=0, name=uid_14_out_0b_uid_1_out_0, none-quant
output 6 dim 20 20 64 1, data_format=0, name=uid_13_out_0b_uid_1_out_0, none-quant
output 7 dim 20 20 80 1, data_format=0, name=uid_12_out_0b_uid_1_out_0, none-quant
output 8 dim 20 20 32 1, data_format=0, name=uid_11_out_0b_uid_1_out_0, none-quant
output 9 dim 160 160 32 1, data_format=0, name=uid_20009_sub_uid_1_out_0, none-quant
nbg name=model/yolov8s-seg_10_uint8_a733.nb, size: 8089336.
create network 0: 21684 us.
prepare network: 4881 us.
buffer ptr: 0x127ba600, buffer size: 1228800
network: 0, loop count: 1
run time for this network 0: 38144 us.
output 0, ptr 0x128e6780, size 409600.
output 1, ptr 0x12a76800, size 512000.
output 2, ptr 0x12c6a880, size 204800.
output 3, ptr 0x12d32900, size 102400.
output 4, ptr 0x12d969c0, size 128000.
output 5, ptr 0x12e13a40, size 51200.
output 6, ptr 0x12e45ac0, size 25600.
output 7, ptr 0x12e5eb40, size 32000.
output 8, ptr 0x12e7e000, size 12800.
output 9, ptr 0x12e8a880, size 819200.
post process time : 12 ms
detection num: 3
 1:  89%, [ 126,  133,  568,  425], bicycle
16:  96%, [ 131,  220,  310,  541], dog
 7:  65%, [ 470,   73,  688,  171], truck
destroy npu finished.
~NpuUint.

This performance data only calculates the time consumption of model inference. Unless otherwise specified, it does not include the time consumption of pre-processing and post-processing.

SoCNPUModelInput ResolutionNetwork Creation TimeNetwork Preparation TimeSingle Frame Inference TimePost-processing TimeTotal TimeFrame Rate
Allwinner A733Vivante VIP9000yolov8s-seg640×64021.7 ms4.9 ms38.1 ms12 ms76.7 ms26.3 FPS

    You need to be logged into GitHub to post a comment. If you are already logged in, please ignore this message.

    Radxa-docs © 2026 by Radxa Computer (Shenzhen) Co.,Ltd. is licensed under CC BY 4.0