Skip to main content

PPSeg

This document describes how to run PPSeg on NPU.

info

Refer to Model Zoo Download for the example.

PPSeg Example Directory Structure:

$ tree ./
./
├── CMakeLists.txt
├── convert_model
│ ├── config_yml.py
│ ├── convert_model_env.sh
│ ├── model.pdparams
│ └── pp_liteseg_cityscapes.txt
├── figures
│ └── out_ppseg.png
├── main.cpp
├── model
│ └── munster_000022_000019_leftImg8bit.png
├── model_config.h
├── ppseg_post.cpp
├── ppseg_pre.cpp
└── README.md

Model Conversion

Download Model

Click to download pp_liteseg_cityscapes.

Then move the model to the convert_model/ directory.

X86 Linux PC
cd convert_model/
./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/ppseg/convert_model/
X86 Linux PC
./pegasus_import.sh pp_liteseg_cityscapes
./pegasus_quantize.sh pp_liteseg_cityscapes pcq 10
X86 Linux PC
./pegasus_export_ovx_nbg.sh pp_liteseg_cityscapes pcq 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/ppseg/
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 ppseg_demo_linux_a733/
Radxa SBC
chmod +x ./ppseg_demo_a733
./ppseg_demo_a733 -nb model/pp_liteseg_cityscapes_pcq_a733.nb -i model/munster_000022_000019_leftImg8bit.png

The running result is as follows:

$ ./ppseg_demo_a733 -nb model/pp_liteseg_cityscapes_pcq_a733.nb -i model/munster_000022_000019_leftImg8bit.png
model_file=model/pp_liteseg_cityscapes_pcq_a733.nb, input=model/munster_000022_000019_leftImg8bit.png, loop_count=1, malloc_mbyte=10
VIPLite driver software version 2.0.3.2-AW-2024-08-30
input 0 dim 3 512 512 1, data_format=2, quant_format=0, name=input/output[0], none-quant
output 0 dim 512 512 19 1, data_format=0, name=uid_20000_sub_uid_1_out_0, none-quant
nbg name=model/pp_liteseg_cityscapes_pcq_a733.nb, size: 10615496.
create network 0: 30474 us.
prepare network: 1578 us.
buffer ptr: 0x190c0300, buffer size: 786432
network: 0, loop count: 1
run time for this network 0: 81842 us.
output 0, ptr 0xffffa2a2b040, size 4980736.
post process time : 146 ms
ppseg_postprocess finished.
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 VIP9000pp_liteseg_cityscapes512×51230.5 ms1.6 ms81.8 ms146.0 ms260 ms12.2 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