https://github.com/nihui/ncnn-android-nanodet
ncnn android nanodet lightweight object detection
https://github.com/nihui/ncnn-android-nanodet
android lightweight ncnn object-detection realtime
Last synced: 5 months ago
JSON representation
ncnn android nanodet lightweight object detection
- Host: GitHub
- URL: https://github.com/nihui/ncnn-android-nanodet
- Owner: nihui
- Created: 2021-03-12T14:55:16.000Z (over 5 years ago)
- Default Branch: master
- Last Pushed: 2026-01-14T06:55:36.000Z (5 months ago)
- Last Synced: 2026-01-14T10:31:32.567Z (5 months ago)
- Topics: android, lightweight, ncnn, object-detection, realtime
- Language: C++
- Homepage:
- Size: 41.4 MB
- Stars: 415
- Watchers: 8
- Forks: 81
- Open Issues: 13
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
- awesome-ncnn - **Android Demo** - Official NCNN implementation (🎯 Object Detection / 🌟 NanoDet (Lightweight Detection))
- awesome-ncnn - ncnn-android-nanodet
README
# ncnn-android-nanodet
The NanoDet object detection
This is a sample ncnn android project, it depends on ncnn library and opencv
https://github.com/Tencent/ncnn
https://github.com/nihui/opencv-mobile
## android apk file download
https://github.com/nihui/ncnn-android-nanodet/releases/latest
## how to build and run
### step1
https://github.com/Tencent/ncnn/releases
* Download ncnn-YYYYMMDD-android-vulkan.zip or build ncnn for android yourself
* Extract ncnn-YYYYMMDD-android-vulkan.zip into **app/src/main/jni** and change the **ncnn_DIR** path to yours in **app/src/main/jni/CMakeLists.txt**
### step2
https://github.com/nihui/opencv-mobile
* Download opencv-mobile-XYZ-android.zip
* Extract opencv-mobile-XYZ-android.zip into **app/src/main/jni** and change the **OpenCV_DIR** path to yours in **app/src/main/jni/CMakeLists.txt**
### step3
* Open this project with Android Studio, build it and enjoy!
## some notes
* Android ndk camera is used for best efficiency
* Crash may happen on very old devices for lacking HAL3 camera interface
* All models are manually modified to accept dynamic input shape
* Most small models run slower on GPU than on CPU, this is common
* FPS may be lower in dark environment because of longer camera exposure time
## screenshot
