User Tools
Sidebar
products:sbc:vim3:npu:npu-prebuilt-demo-usage
This is an old revision of the document!
Table of Contents
NPU Prebuilt Demo Usage
- Please follow this docs to upgrade the system to latest version before run any NPU demos.
- Just support Opencv4
install OpenCV4
- Install-OpenCV4.sh
sudo apt install libopencv-dev python3-opencv
Get NPU Demo
NPU Demo is not installed on the board by default. You need to download it from github first
1) Clone to the board through the git command.
- get-npu-demo-from-demo.sh
cd {workspace} git clone --recursive https://github.com/khadas/aml_npu_demo_binaries
2) Or download the compressed package directly, and then unzip it to the board.
There are three directories in NPU Demo:
detect_demo
- detect_demo: A collection of yolo series models for camera dynamic recognition.
detect_demo_picture
- detect_demo_picture: A collection of yolo series models that identify pictures.
inceptionv3
- inceptionv3: Identify the inception model of the picture
Inception Model
- The inception model does not need to install any libraries into the system. Enter the inceptionv3 directory.
- imagenet_slim_labels.txt is a label file. After the result is identified, the label corresponding to the result can be queried in this file.
$ cd {workspace}/aml_npu_demo_binaries/inceptionv3
$ ls
dog_299x299.jpg goldfish_299x299.jpg imagenet_slim_labels.txt VIM3 VIM3L
If your board is VIM3, enter the VIM3 directory, if it is VIM3L, then enter the VIM3L directory. Here is VIM3 as an example.
1 $ cd {workspace}/aml_npu_demo_binaries/inceptionv3/VIM3
2 $ inceptionv3 inception_v3.nb run.sh
1 $ cd {workspace}/aml_npu_demo_binaries/inceptionv3/VIM3
2 $ ./run.sh
3 Create Neural Network: 59ms or 59022us
4 Verify...
5 Verify Graph: 0ms or 739us
6 Start run graph [1] times...
7 Run the 1 time: 20.00ms or 20497.00us
8 vxProcessGraph execution time:
9 Total 20.00ms or 20540.00us
10 Average 20.54ms or 20540.00us
11 --- Top5 ---
12 2: 0.833984
13 795: 0.009102
14 974: 0.003592
15 408: 0.002207
16 393: 0.002111
By querying imagenet_slim_labels.txt, the result is a goldfish, which is also correctly identified.You can use the method above to identify other images.
Last modified: 2022/09/16 02:34 by ivan