Paper: https://arxiv.org/pdf/2207.02696.pdf
Specially 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/YoloV7-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
YoloV7.cpb
yolo.cpp
yolo.h
yoloV7main.cpp
yolov7-tiny.bin
yolov7-tiny.param
To run the application load the project file YoloV7.cbp in Code::Blocks. More info or
if you want to connect a camera to the app, follow the instructions at Hands-On.
YoloV7 can handle different input resolutions without changing the deep learning model.
On line 28 of yolov7main.cpp you can change the target_size (default 640).
Decreasing the size to say 412 will speed up the inference time. On the other hand, the resizing makes the image less detailed; the model will no longer detect all objects.
Many thanks to nihui and Xiang Shin Wuu
