https://github.com/qengineering/yolact-ncnn-raspberry-pi-4
Yolact running on the ncnn framework on a bare Raspberry Pi 4 with 64 OS, overclocked to 1950 MHz
https://github.com/qengineering/yolact-ncnn-raspberry-pi-4
aarch64 cpp deep-learning ncnn ncnn-framework ncnn-model raspberry-pi raspberry-pi-4 raspberry-pi-64-os yolact
Last synced: 3 months ago
JSON representation
Yolact running on the ncnn framework on a bare Raspberry Pi 4 with 64 OS, overclocked to 1950 MHz
- Host: GitHub
- URL: https://github.com/qengineering/yolact-ncnn-raspberry-pi-4
- Owner: Qengineering
- License: bsd-3-clause
- Created: 2020-07-21T15:51:41.000Z (almost 5 years ago)
- Default Branch: master
- Last Pushed: 2022-12-29T16:29:07.000Z (over 2 years ago)
- Last Synced: 2025-03-27T09:23:15.010Z (3 months ago)
- Topics: aarch64, cpp, deep-learning, ncnn, ncnn-framework, ncnn-model, raspberry-pi, raspberry-pi-4, raspberry-pi-64-os, yolact
- Language: C++
- Homepage: https://qengineering.eu/deep-learning-examples-on-raspberry-32-64-os.html
- Size: 837 KB
- Stars: 12
- Watchers: 1
- Forks: 3
- Open Issues: 2
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
 Find this example on our [SD-image](https://github.com/Qengineering/RPi-image)
# Yolact-ncnn on Raspberry Pi 64 bits
## Yolact with the ncnn framework.
[](https://opensource.org/licenses/BSD-3-Clause)
The frame rate is about 3.5 sec per image (RPi overclocked to 1950 MHz)
Special made for a bare Raspberry Pi see [Q-engineering deep learning examples](https://qengineering.eu/deep-learning-examples-on-raspberry-32-64-os.html)
Paper: https://openaccess.thecvf.com/content_ICCV_2019/papers/Bolya_YOLACT_Real-Time_Instance_Segmentation_ICCV_2019_paper.pdf
------------
## Benchmark.
| Model | size | objects | mAP | RPi 4 64-OS 1950 MHz |
| ------------- | :-----: | :-----: | :-------------: | :-------------: |
| [YoloV5n](https://github.com/Qengineering/YoloV5-segmentation-ncnn-RPi4) | 640x640 nano| 80 | 28.0 | 1.4 - 2.0 FPS |
| [YoloV5s](https://github.com/Qengineering/YoloV5-segmentation-ncnn-RPi4) | 640x640 small| 80 | 37.4 | 1.0 FPS |
| [YoloV5l](https://github.com/Qengineering/YoloV5-segmentation-ncnn-RPi4) | 640x640 large| 80 | 49.0 | 0.25 FPS |
| [YoloV5x](https://github.com/Qengineering/YoloV5-segmentation-ncnn-RPi4) | 640x640 x-large| 80 | 50.7 | 0.15 FPS |
| Yoact | 550x550 | 80 | 28.2 | 0.28 FPS |
------------
## Dependencies.
To run the application, you have to:
- A raspberry Pi 4 with a 32 or 64-bit operating system. It can be the Raspberry 64-bit OS, or Ubuntu 18.04 / 20.04. [Install 64-bit OS](https://qengineering.eu/install-raspberry-64-os.html)
- The Tencent ncnn framework installed. [Install ncnn](https://qengineering.eu/install-ncnn-on-raspberry-pi-4.html)
- OpenCV 64 bit installed. [Install OpenCV 4.3](https://qengineering.eu/install-opencv-4.3-on-raspberry-64-os.html)
- Code::Blocks installed. (``` $ sudo apt-get install codeblocks ```)
------------
## Installing the app.
To extract and run the network in Code::Blocks
$ mkdir *MyDir*
$ cd *MyDir*
$ wget https://github.com/Qengineering/Yolact-ncnn/archive/refs/heads/master.zip
$ unzip -j master.zip
Remove master.zip and README.md as they are no longer needed.
$ rm master.zip
$ rm README.md
Your *MyDir* folder must now look like this:
dog.jpg
elephant.jpeg
girafe.jpeg
mumbai.jpg
onyx.jpeg
result_elephant.png
result_zebra.png
Yolact.cpb
yolact.cpp
yolact.bin (download this file from [Gdrive](https://drive.google.com/file/d/1vu3GGOEWh-jmedM-cvoqzhGzaZaOQB9k) )
yolact.param
------------
## Running the app.
Run Yolact.cpb with Code::Blocks.
For more info follow the instructions at [Hands-On](https://qengineering.eu/deep-learning-examples-on-raspberry-32-64-os.html#HandsOn).
Many thanks to [nihui](https://github.com/nihui/) again!
------------
[](https://www.paypal.com/cgi-bin/webscr?cmd=_s-xclick&hosted_button_id=CPZTM5BB3FCYL)