aml_npu_demo_binaries repository are executable files repositories, this repository are used to run NPU demo on khadas VIM3/VIM3L
Repository address: gitlab.com/khadas/aml_npu_demo_binaries
- detect_demo/detect_demo_khadas : These two demos are demos that use cameras to recognize objects for classification
- detect_demo_picture : This demo is to identify and classify multi-object pictures
- inceptionv3 : This demo is a demo that recognizes pictures and makes top5 predictions
Please run ubuntu firmware on VIM3 and upgrade the system through
sudo apt update && sudo apt upgrade
detect_demo_khadasneed to be used in
F1to switch to
Clone the repository to VIM3/VIM3L
After installation, the instructions to install the README file can run the demo.
detect_demo_uvc is the running file of the USB camera
If you board is VIM3
If you board is VIM3L
./inceptionv3 inception_v3.nb /path/to/picture
Image format needs to use jpg format
aml_npu_app repository is used to compile demo repository, this repository runs on PC
Repository address: gitlab.com/khadas/aml_npu_app
DDK_184.108.40.206is the source code of different versions of library files
detect_library/model_codepoint to the latest version of the library source code
detect_library/yolo_demo_mipigenerate USB demo or MIPI demo
detect_library/sample_demoGenerate a demo that recognizes the picture.
Apply sdk,and unzip.
clone repository to you PC
Enter the location where you need to compile, here takes
yolov3 as an example.
After compilation, the files in the
bin_r directory are the files generated by the compilation