Skip to main content

MobilenetV2

This tutorial guides you through running the MobilenetV2 model on RevyOS using either the CPU or NPU. MobilenetV2 is an efficient deep neural network model, widely used for optimization on mobile and embedded systems.

Initial Environment Setup

Before proceeding, please ensure you have completed the environment setup section.

Obtaining Example Code

The example code for this tutorial is available on Github. Clone it locally using the following command:

$ git clone https://github.com/zhangwm-pt/lpi4a-example.git

The relevant code for this tutorial is located in the classification/mobilenetv2 directory.

Obtaining the Model

The model used in this tutorial is from the ONNX Model Zoo. Download the MobilenetV2 model with the following command:

$ curl -OL https://raw.githubusercontent.com/onnx/models/raw/main/validated/vision/classification/mobilenet/model/mobilenetv2-10.onnx
About Github Network Proxy

If you encounter network issues accessing GitHub from mainland China, consider using a network proxy tool to accelerate access.

Model Information

input nameoutput nameinput shapelayoutchannel orderscale valuemean values
inputoutput1, 3, 224, 224NCHWRGB0.017124, 117, 104

Model Conversion and Compilation

On an x86 machine, use the HHB tool to convert the ONNX model into a computation graph and glue code suitable for RevyOS. Before proceeding, ensure you have started the HHB container and cloned the example repository as described in the environment setup section.

Model Conversion with HHB

In this step, the onnx model is converted into a format compatible with the HHB platform.

Navigate to the classification/mobilenetv2 directory and execute the following commands:

$ hhb -D --model-file mobilenetv2-12.onnx \
--data-scale 0.017 --data-mean "124 117 104" \
--board th1520 --postprocess save_and_top5 \
--input-name "input" --output-name "output" \
--input-shape "1 3 224 224" --calibrate-dataset persian_cat.jpg \
--quantization-scheme "int8_asym"
HHB Parameter Description
  • -D: Specifies the HHB process to stop at the executable generation stage
  • --model-file: Specifies the input model file
  • --data-mean: Specifies the mean values
  • --data-scale: Specifies the scale value
  • --board: Target platform, C920 (CPU) or TH1520 (NPU)
  • --input-name: Model input tensor name
  • --output-name: Model output tensor name
  • --input-shape: Model input tensor shape
  • --postprocess: Specifies the post-processing behavior for the generated glue code. save_and_top5 saves the output and prints the top 5 results
  • --quantization-scheme: Specifies the quantization type (float16 for CPU, int8_asym for NPU)

You can run hhb --help to view all available parameters and options.

About HHB Generated Files

After execution, an hhb_out subdirectory will be generated in the current directory, containing files such as hhb_runtime, model.c, and others:

  • hhb.bm: HHB model file, including quantized weights and related data
  • hhb_runtime: Executable for the development board, compiled from the C files in the directory
  • main.c: Reference entry for the generated example program
  • model.c: Model structure representation file
  • model.params: Model weights file
  • io.c: Example program with file I/O helper functions
  • io.h: Declarations for I/O helper functions
  • process.c: Example program with image preprocessing functions
  • process.h: Declarations for preprocessing functions

For more details on HHB options, refer to the HHB User Manual.

Compiling the Application

The glue code generated by HHB only tests the model's functionality. For complete image preprocessing and postprocessing, an application using OpenCV is provided to load the model and perform inference.

In the classification/mobilenetv2 directory, compile the application with:

$ export OPENCV_DIR=../../modules/opencv/ # Set the path to OpenCV
$ riscv64-unknown-linux-gnu-g++ main.cpp -I${OPENCV_DIR}/include/opencv4 -L${OPENCV_DIR}/lib \
-lopencv_imgproc -lopencv_imgcodecs -L${OPENCV_DIR}/lib/opencv4/3rdparty/ \
-llibjpeg-turbo -llibwebp -llibpng -llibtiff -llibopenjp2 \
-lopencv_core -ldl -lpthread -lrt -lzlib -lcsi_cv -latomic -static \
-o mobilenetv2_example # Compile the program
About OpenCV

The example code uses OpenCV for model input preprocessing. Please ensure OpenCV is installed as described in the environment setup section.

Compilation Parameter Description
  • -I../prebuilt_opencv/include/opencv4: Header file search path, pointing to the OpenCV headers
  • -L../prebuilt_opencv/lib: Library search path, pointing to the precompiled OpenCV binaries
  • -lopencv_imgproc -lopencv_imgcodecs -lopencv_core: OpenCV libraries
  • -llibjpeg-turbo -llibwebp -llibpng -llibtiff -llibopenjp2 -lcsi_cv: OpenCV dependencies
  • -static: Static linking
  • -o mobilenetv2_example: Output executable name

After successful compilation, the mobilenetv2_example file will be generated in the example directory.

Uploading and Running the Application

Upload to the Development Board

Package all files in this directory and upload them to the development board. For example, use the scp command to upload to /home/debian/npu:

$ scp -r ../mobilenetv2/ debian@<board_ip>:/home/debian/mobilenetv2/

Alternatively, you may use other methods such as USB storage devices or network sharing.

Running the Program

On the development board, navigate to /home/debian/mobilenetv2. Ensure the SHL library is installed and LD_LIBRARY_PATH is configured. Then run:

$ ./mobilenetv2_example
hhb_runtime Error

If you encounter the following error:

hhb_out/hhb_runtime: error while loading shared libraries: libshl_th1520.so.2: cannot open shared object file: No such file or directory

Ensure LD_LIBRARY_PATH is correctly set. If the issue persists, run pip show shl-python to check the version.

If the version is 3.x.x, it is too high. The program requires shl-python version 2.x. Downgrade with:

$ pip install shl-python==2.6.17
About NPU Device Permissions

If you encounter the following error:

FATAL: could not open driver '/dev/vha0': Permission denied

Check if the current user has read/write permissions for /dev/vha0. Set permissions with:

$ sudo chmod 0666 /dev/vha0

It is recommended to configure udev rules for automatic permission setting. Consult AI or documentation for udev configuration.

About Long NPU Inference Time

In theory, the program should run quickly. However, the first run may take over 5 minutes due to JIT compilation when loading the model on the NPU. Due to HHB runtime design, JIT compilation occurs on every run, resulting in long execution times.

For more details, refer to Common Issues and Solutions.

Sample output:

In this tutorial, the input is a picture of a Persian cat. The expected result for ResNet50 is that the largest value is at index 283, corresponding to Persian cat. Persian cat

$ ./mobilenetv2_example
********** preprocess image **********
********** run mobilenetv2 **********
Run graph execution time: 82.31609ms, FPS=12.15

=== tensor info ===
shape: 1 3 224 224
data pointer: 0x30762380

=== tensor info ===
shape: 1 1000
data pointer: 0x306ce340
The max_value of output: 16.843750
The min_value of output: -7.414062
The mean_value of output: 0.001131
The std_value of output: 9.056762
============ top5: ===========
283: 16.843750
281: 13.789062
287: 12.257812
282: 10.898438
285: 10.765625
********** postprocess result **********
********** probability top5: **********
n02123394 Persian cat
n02123045 tabby, tabby cat
n02127052 lynx, catamount
n02123159 tiger cat
n02124075 Egyptian cat