Paper: https://arxiv.org/pdf/2004.10934.pdf
Special made for a Jetson Nano see Q-engineering deep learning examples
| Model | size | mAP | Jetson Nano | RPi 4 1950 | RPi 5 2900 | Rock 5 |
|---|---|---|---|---|---|---|
| NanoDet | 320x320 | 20.6 | 26.2 FPS | 13.0 FPS | 43.2 FPS | 36.0 FPS |
| NanoDet Plus | 416x416 | 30.4 | 18.5 FPS | 5.0 FPS | 30.0 FPS | 24.9 FPS |
| PP-PicoDet | 320x320 | 27.0 | 24.0 FPS | 7.5 FPS | 53.7 FPS | 46.7 FPS |
| YoloFastestV2 | 352x352 | 24.1 | 38.4 FPS | 18.8 FPS | 78.5 FPS | 65.4 FPS |
| YoloV2 20 | 416x416 | 19.2 | 10.1 FPS | 3.0 FPS | 24.0 FPS | 20.0 FPS |
| YoloV3 20 | 352x352 tiny | 16.6 | 17.7 FPS | 4.4 FPS | 18.1 FPS | 15.0 FPS |
| YoloV4 | 416x416 tiny | 21.7 | 16.1 FPS | 3.4 FPS | 26.8 FPS | 22.4 FPS |
| YoloV4 | 608x608 full | 45.3 | 1.3 FPS | 0.2 FPS | 1.82 FPS | 1.5 FPS |
| YoloV5 | 640x640 small | 22.5 | 5.0 FPS | 1.6 FPS | 14.9 FPS | 12.5 FPS |
| YoloV6 | 640x640 nano | 35.0 | 10.5 FPS | 2.7 FPS | 25.0 FPS | 20.8 FPS |
| YoloV7 | 640x640 tiny | 38.7 | 8.5 FPS | 2.1 FPS | 21.5 FPS | 17.9 FPS |
| YoloV8 | 640x640 nano | 37.3 | 14.5 FPS | 3.1 FPS | 20.0 FPS | 16.3 FPS |
| YoloV8 | 640x640 small | 44.9 | 4.5 FPS | 1.47 FPS | 11.0 FPS | 9.2 FPS |
| YoloX | 416x416 nano | 25.8 | 22.6 FPS | 7.0 FPS | 34.2 FPS | 28.5 FPS |
| YoloX | 416x416 tiny | 32.8 | 11.35 FPS | 2.8 FPS | 21.8 FPS | 18.1 FPS |
| YoloX | 640x640 small | 40.5 | 3.65 FPS | 0.9 FPS | 9.0 FPS | 7.5 FPS |
20 Recognize 20 objects (VOC) instead of 80 (COCO)
To run the application, you have to:
- The Tencent ncnn framework installed. Install ncnn
- Code::Blocks installed. (
$ sudo apt-get install codeblocks)
To extract and run the network in Code::Blocks
$ mkdir MyDir
$ cd MyDir
$ wget https://github.com/Qengineering/YoloV4-ncnn-Jetson-Nano/archive/refs/heads/main.zip
$ unzip -j master.zip
Remove master.zip, LICENSE and README.md as they are no longer needed.
$ rm master.zip
$ rm LICENSE
$ rm README.md
Your MyDir folder must now look like this:
parking.jpg
busstop.jpg
YoloV4.cpb
yolov4-tiny-opt.bin
yolov4-tiny-opt.param
To run the application load the project file YoloV4.cbp in Code::Blocks.
Next, follow the instructions at Hands-On.
You can switch between the YoloV4 tiny and the YoloV4 full version by the define at line 26
When deploying the full version, you have to download the 250 MB deep learning weight file yolov4-opt.bin from Mega.
Many thanks to nihui again!
