Khadas Docs

Amazing Khadas, always amazes you!

User Tools

Site Tools

Home / products / sbc / edge-2l / npu / rknn-sdk-quick-start
products:sbc:edge-2l:npu:rknn-sdk-quick-start

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision 		Previous revision
products:sbc:edge-2l:npu:rknn-sdk-quick-start [2026/05/31 22:03]
nick [View Results] 		products:sbc:edge-2l:npu:rknn-sdk-quick-start [2026/05/31 23:55] (current)
nick [Run RKNN Python demo]
Line 1: Line 1:
-====== RKNN SDK Quick Start ======+====== RKNN SDK quick start ======
  
 ===== Introduction ===== ===== Introduction =====
 This document provides a detailed introduction for beginners on how to quickly use RKNN-Toolkit2 on a computer to perform model conversion and deploy it to a Edge 2L board using RKNPU2. The examples used in this document are integrated into the [[https://github.com/airockchip/rknn_model_zoo | RKNN Model Zoo]]. This document provides a detailed introduction for beginners on how to quickly use RKNN-Toolkit2 on a computer to perform model conversion and deploy it to a Edge 2L board using RKNPU2. The examples used in this document are integrated into the [[https://github.com/airockchip/rknn_model_zoo | RKNN Model Zoo]].
  
-===== Prepare Development Environment =====+===== Prepare development environment =====
 The version information we are using is as follows:  The version information we are using is as follows: 
-  * python: 3.8+  * Host PC Python: 3.8
   * rknn-toolkit2: 2.3.2   * rknn-toolkit2: 2.3.2
   * rknn model zoo: 2.3.2   * rknn model zoo: 2.3.2
  
-==== Download RKNN Related Repositories ====+==== Download RKNN related repositories - Host PC ====
 It is recommended to create a new directory to store the RKNN repositories. For example, create a folder named ''Projects'' and place the RKNN-Toolkit2 and RKNN Model Zoo repositories in that directory. Refer to the following commands It is recommended to create a new directory to store the RKNN repositories. For example, create a folder named ''Projects'' and place the RKNN-Toolkit2 and RKNN Model Zoo repositories in that directory. Refer to the following commands
  
Line 26: Line 26:
 ``` ```
  
-==== Install the RKNN-Toolkit2 Environment on the Computer ====+==== Install the RKNN-Toolkit2 environment on your Host PC ====
  
-=== Install Python ===+=== Install Python - Host PC ===
 If the Python 3.8 environment is not installed on your system, or if there are multiple versions of Python installed, it is recommended to use Miniforge Conda to create a new Python 3.8 environment. If the Python 3.8 environment is not installed on your system, or if there are multiple versions of Python installed, it is recommended to use Miniforge Conda to create a new Python 3.8 environment.
  
-=== Install Miniforge Conda ===+=== Install Miniforge Conda - Host PC ===
  
 Download the Miniforge Conda installer from the following link: Download the Miniforge Conda installer from the following link:
Line 37: Line 37:
 $ wget -c https://github.com/conda-forge/miniforge/releases/latest/download/Miniforge3-Linux-x86_64.sh $ wget -c https://github.com/conda-forge/miniforge/releases/latest/download/Miniforge3-Linux-x86_64.sh
 ``` ```
 +
 Then, install Miniforge Conda using the following command: Then, install Miniforge Conda using the following command:
 ```shell ```shell
Line 42: Line 43:
 $ bash Miniforge3-Linux-x86_64.sh $ bash Miniforge3-Linux-x86_64.sh
 ``` ```
-=== Create Python Environment Using Miniforge Conda ===+=== Create Python environment using miniforge conda - Host PC ===
 In the terminal window on the computer, execute the following command to switch to the Miniforge conda base In the terminal window on the computer, execute the following command to switch to the Miniforge conda base
 environment: environment:
Line 56: Line 57:
 $ conda activate py38Toolkit2.3.2 $ conda activate py38Toolkit2.3.2
 ``` ```
-=== Install RKNN-Toolkit2 ===+=== Install RKNN-Toolkit2 - Host PC ===
 Install via local wheel packag. Install via local wheel packag.
  
Line 65: Line 66:
 ``` ```
  
-=== Check if the RKNN-Toolkit2 Environment is Installed Successfully ===+=== Check if the RKNN-Toolkit2 environment - Host PC ===
 Switch to Python interactive mode Switch to Python interactive mode
 ```shell ```shell
Line 75: Line 76:
 ``` ```
  
-==== Install Compilation Tools on the Computer ==== +==== Install compilation tools on your host PC ==== 
-=== Install NDK on Android System Development Board ===+=== Android - Install NDK for Android system ===
 Note: This section is applicable to development boards with the Android system. If the board is running on the Note: This section is applicable to development boards with the Android system. If the board is running on the
 Linux system, please skip this section.\\ Linux system, please skip this section.\\
Line 89: Line 90:
 ``` ```
  
-==== Install GCC Cross-Compiler on Linux System Development Board ====+==== Linux - Install GCC Cross-Compiler for Linux system ====
 Note: This section is applicable to development boards with the Linux system. If the board is running on the Note: This section is applicable to development boards with the Linux system. If the board is running on the
 Android system, please skip this section.\\ Android system, please skip this section.\\
Line 101: Line 102:
 ``` ```
  
-===== Run Example Programs =====+===== Run example programs =====
  
-==== Prepare Model ====+==== Prepare model ====
 Switch to the ''rknn_model_zoo/examples/yolov5/model'' directory, and execute the ''download_model.sh'' script. This Switch to the ''rknn_model_zoo/examples/yolov5/model'' directory, and execute the ''download_model.sh'' script. This
 script will download an available YOLOv5 ONNX model and store it in the current model directory. Refer to the script will download an available YOLOv5 ONNX model and store it in the current model directory. Refer to the
Line 113: Line 114:
 ``` ```
  
-==== Model Conversion ====+==== Model conversion ====
 Switch to the ''rknn_model_zoo/examples/yolov5/python'' directory and run the ''convert.py'' script. This script converts Switch to the ''rknn_model_zoo/examples/yolov5/python'' directory and run the ''convert.py'' script. This script converts
 the original ONNX model to the RKNN model. Refer to the following commands: the original ONNX model to the RKNN model. Refer to the following commands:
Line 122: Line 123:
 ``` ```
  
-==== Run RKNN Python Demo ==== +==== Run RKNN Python demo ==== 
-Switch to the rknn_model_zoo/examples/yolov5/python directory, execute the yolov5.py script, and you can run the+=== Android === 
 +Switch to the ''rknn_model_zoo/examples/yolov5/python'' directory, execute the ''yolov5.py'' script, and you can run the
 YOLOv5 model on the development board using on-board debugging. Refer to the following command: YOLOv5 model on the development board using on-board debugging. Refer to the following command:
  
Line 131: Line 133:
 ``` ```
  
-==== Run RKNN C Demo ==== +=== Linux === 
-To run a RKNN C Demo, you need to first compile the C/C++ source code into an executable file. After that, push+ 
 +Running on a Ubuntu 24.04 system which ship the python version of 3.12. 
 + 
 +Download the model zoo to your Edge 2L: 
 + 
 +```shell 
 +git clone -b v2.3.2 https://github.com/airockchip/rknn_model_zoo.git --depth 1 
 +``` 
 + 
 +Install the python virtual environment: 
 + 
 +```shell 
 +sudo apt update 
 +sudo apt install python3.12-venv -y 
 +``` 
 + 
 +Create the python virtual environment: 
 +```shell 
 +python3 -m venv myenv312 
 +``` 
 + 
 +Activate the python virtual environment: 
 + 
 +```shell 
 +source myenv312/bin/activate 
 +(myenv312) khadas@Khadas:~$ python --version 
 +Python 3.12.3 
 +``` 
 + 
 +Install the python package from ''rknn-toolkit2/rknn-toolkit-lite2/packages/rknn_toolkit_lite2-2.3.2-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl'' 
 + 
 +```shell 
 +(myenv312) khadas@Khadas:~$ pip install rknn_toolkit_lite2-2.3.2-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl  
 +``` 
 + 
 +Install the runtime libraries from ''rknn-toolkit2/rknpu2/runtime/Linux/librknn_api/aarch64/librknnrt.so'' 
 + 
 +```shell 
 +sudo cp librknnrt.so /usr/lib/ 
 +``` 
 + 
 +Install the OpenCV: 
 + 
 +```shell 
 +(myenv312) khadas@Khadas:~$ pip install opencv-python 
 +``` 
 + 
 +Copy the converted model in [[#model-conversion | Model conversion]] to your Edge 2L: 
 + 
 +```shell 
 +adb push examples/yolov5/model/yolov5s_relu.rknn /home/khadas/rknn_model_zoo/examples/yolov5/model 
 +``` 
 + 
 +Modify the demo code: 
 + 
 +```diff 
 +diff --git a/py_utils/rknn_executor.py b/py_utils/rknn_executor.py 
 +index 21b4132..46b24d4 100644 
 +--- a/py_utils/rknn_executor.py 
 ++++ b/py_utils/rknn_executor.py 
 +@@ -1,5 +1,5 @@ 
 +-from rknn.api import RKNN 
 +- 
 ++from rknnlite.api import RKNNLite as RKNN 
 ++import numpy as np 
 +  
 + class RKNN_model_container(): 
 +     def __init__(self, model_path, target=None, device_id=None) -> None: 
 +@@ -9,10 +9,7 @@ class RKNN_model_container(): 
 +         rknn.load_rknn(model_path) 
 +  
 +         print('--> Init runtime environment') 
 +-        if target==None: 
 +-            ret = rknn.init_runtime() 
 +-        else: 
 +-            ret = rknn.init_runtime(target=target, device_id=device_id) 
 ++        ret = rknn.init_runtime() 
 +         if ret != 0: 
 +             print('Init runtime environment failed') 
 +             exit(ret) 
 +@@ -33,10 +30,12 @@ class RKNN_model_container(): 
 +         else: 
 +             inputs = [inputs] 
 +  
 ++        inputs = [np.expand_dims(item, axis=0) if len(item.shape) == 3 else item for item in inputs] 
 ++ 
 +         result = self.rknn.inference(inputs=inputs) 
 +      
 +         return result 
 +  
 +     def release(self): 
 +         self.rknn.release() 
 +-        self.rknn = None 
 +\ No newline at end of file 
 ++        self.rknn = None 
 +(myenv312) khadas@Khadas:~/rknn_model_zoo$  
 +``` 
 + 
 +Run the Yolov5 demo: 
 + 
 +```shell 
 +(myenv312) khadas@Khadas:~/rknn_model_zoo/examples/yolov5/python$ export QT_QPA_PLATFORM=xcb 
 +(myenv312) khadas@Khadas:~/rknn_model_zoo/examples/yolov5/python$ python yolov5.py --model_path ../model/yolov5s_relu.rknn --target rk3576 --img_show 
 +``` 
 + 
 +{{:products:sbc:edge-2l:npu:yolov5-linux-demo.webp?600|}} 
 + 
 +Deactivate the python virtual enviranment: 
 + 
 +```shell 
 +(myenv312) khadas@Khadas:~/rknn_model_zoo$ deactivate  
 +``` 
 + 
 + 
 +==== Run RKNN C demo ==== 
 +To run a RKNN C demo, you need to first compile the C/C++ source code into an executable file. After that, push
 the executable file, model files, input images, and other related files to the development board. Finally, execute the executable file, model files, input images, and other related files to the development board. Finally, execute
 the executable file on the development board. the executable file on the development board.
  
-=== Board is running on the Android system ===+=== Android ===
 In the ''build-android.sh'' script, add the following command: In the ''build-android.sh'' script, add the following command:
  
Line 149: Line 266:
 ``` ```
  
-Push Files to the Edge 2L Board:+Push Files to the Edge 2L board:
 ```shell ```shell
 $ cd Projects/rknn_model_zoo $ cd Projects/rknn_model_zoo
 $ adb root $ adb root
-$ adb install/rk3576_android_arm64-v8a/rknn_yolov5_demo/ /data/+$ adb push install/rk3576_android_arm64-v8a/rknn_yolov5_demo/ /data/
 ``` ```
  
-Run the Demo on Edge 2L Board:+Run the Demo on Edge 2L board:
 ```shell ```shell
 $ adb shell $ adb shell
Line 163: Line 280:
 $ ./rknn_yolov5_demo model/yolov5s_relu.rknn model/bus.jpg $ ./rknn_yolov5_demo model/yolov5s_relu.rknn model/bus.jpg
 ``` ```
-=== Board is running on the Linux system ===+=== Linux ===
 In the ''build-linux.sh'' script, add the following command: In the ''build-linux.sh'' script, add the following command:
  
Line 176: Line 293:
 ``` ```
  
-Push Files to the Edge 2L Board:+Push Files to the Edge 2L board:
 ```shell ```shell
 $ cd Projects/rknn_model_zoo $ cd Projects/rknn_model_zoo
Line 182: Line 299:
 ``` ```
  
-Run the Demo on Edge 2L Board:+Run the Demo on Edge 2L board:
 ```shell ```shell
 $ adb shell $ adb shell
Line 190: Line 307:
 ``` ```
  
- +==== View results ====
- +
-==== View Results ====+
 By default, the output image is saved at the path ''rknn_yolov5_demo/out.png''. You can use the adb tool to pull it By default, the output image is saved at the path ''rknn_yolov5_demo/out.png''. You can use the adb tool to pull it
 from the board to the local machine. In the local computer terminal, execute the following command: from the board to the local machine. In the local computer terminal, execute the following command:
 ```shell ```shell
-$ adb pull /data/rknn_yolov5_demo/out.png .+$ adb pull /home/khadas/rknn_yolov5_demo/out.png .
 ``` ```
 {{:products:sbc:edge-2l:npu:yolov5-bus-result.webp?600|}} {{:products:sbc:edge-2l:npu:yolov5-bus-result.webp?600|}}
  
  
- +===== See also =====
-===== See Also =====+
  
 [[https://github.com/airockchip/rknn-toolkit2/tree/master/doc | RKNN Toolkit2 Documentations]] [[https://github.com/airockchip/rknn-toolkit2/tree/master/doc | RKNN Toolkit2 Documentations]]
  
Last modified: 2026/05/31 22:03 by nick

Page Tools

Khadas Site

Khadas Community

Khadas GitHub

Khadas Downloads