Skip to main content

SqueezeNet

This document describes how to run SqueezeNet on NPU.

info

Refer to Model Zoo Download for the example.

SqueezeNet Example Directory Structure:

$ tree ./
./
├── class_post.cpp
├── class_pre.cpp
├── CMakeLists.txt
├── convert_model
│   ├── config_yml.py
│   ├── convert_model_env.sh
│   └── inputs_outputs.txt
├── label.h
├── main.cpp
├── model
│   └── space_shuttle_227x227.jpg
└── README.md

Model Conversion​

Download Model​

Click to download squeezenet1_0.pt.

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/squeezenet_pytorch/convert_model/
X86 Linux PC
./pegasus_import.sh squeezenet1_0
./pegasus_quantize.sh squeezenet1_0 uint8 10
X86 Linux PC
./pegasus_export_ovx_nbg.sh squeezenet1_0 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/squeezenet_pytorch/
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 squeezenet_demo_linux_a733/
Radxa SBC
chmod +x ./squeezenet_demo_a733
./squeezenet_demo_a733 -nb model/squeezenet1_0_uint8_a733.nb -i model/space_shuttle_227x227.jpg

The running result is as follows:

$ ./squeezenet_demo_a733 -nb model/squeezenet1_0_uint8_a733.nb -i model/space_shuttle_227x227.jpg
model_file=model/squeezenet1_0_uint8_a733.nb, input=model/space_shuttle_227x227.jpg, loop_count=1, malloc_mbyte=10
VIPLite driver software version 2.0.3.2-AW-2024-08-30
input  0 dim 3 227 227 1, data_format=2, quant_format=0, name=input/output[0], none-quant
output 0 dim 1000 1 0 0, data_format=0, name=uid_20000_sub_uid_1_out_0, none-quant
nbg name=model/squeezenet1_0_uint8_a733.nb, size: 1066072.
create network 0: 2628 us.
prepare network: 844 us.
network: 0, loop count: 1
run time for this network 0: 2455 us.
class_postprocess.cpp run.
========== top5 ==========
class id: 812, prob: 16.893208, label: space shuttle
class id: 404, prob: 15.730225, label: airliner
class id: 833, prob: 14.984619, label: submarine, pigboat, sub, U-boat
class id: 554, prob: 14.686523, label: fireboat
class id: 895, prob: 14.611816, label: warplane, military plane
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 VIP9000squeezenet227×2272.6 ms0.8 ms2.5 ms5.9 ms400.0 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