YoloFastestV2 Raspberry Pi 4

YoloFastest V2 with the ncnn framework. <br/>

<br/><br/> A truly impressive YOLO family member. As long as the images are not too large and/or the objects are too small, very high frame rates are achieved with more than acceptable accuracy. Thanks dog-qiuqiu for all the hard work.<br/><br/> Special adapt for a bare Raspberry Pi 4, see Q-engineering deep learning examples

---

Benchmark.

Numbers in FPS and reflect only the inference timing. Grabbing frames, post-processing and drawing are not taken into account.

| Model | size | mAP | Jetson Nano | RPi 4 1950 | RPi 5 2900 | Rock 5 | RK3588¹<br>NPU | RK3566/68²<br>NPU | Nano<br>TensorRT | Orin<br>TensorRT | | ------------- | :-----: | :-----: | :-------------: | :-------------: | :-----: | :-----: | :-------------: | :-------------: | :-----: | :-----: | | NanoDet | 320x320 | 20.6 | 26.2 | 13.0 | 43.2 |36.0 ||||| | NanoDet Plus | 416x416 | 30.4 | 18.5 | 5.0 | 30.0 | 24.9 ||||| | PP-PicoDet | 320x320 | 27.0 | 24.0 | 7.5 | 53.7 | 46.7 ||||| | YoloFastestV2 | 352x352 | 24.1 | 38.4 | 18.8 | 78.5 | 65.4 | |||| | YoloV2 ²⁰| 416x416 | 19.2 | 10.1 | 3.0 | 24.0 | 20.0 | |||| | YoloV3 ²⁰| 352x352 tiny | 16.6 | 17.7 | 4.4 | 18.1 | 15.0 | |||| | YoloV4 | 416x416 tiny | 21.7 | 16.1 | 3.4 | 17.5 | 22.4 | |||| | YoloV4 | 608x608 full | 45.3 | 1.3 | 0.2 | 1.82 | 1.5 | |||| | YoloV5 | 640x640 nano | 22.5 | 5.0 | 1.6 | 13.6 | 12.5 | 58.8 | 14.8 | 19.0 | 100 | | YoloV5 | 640x640 small | 22.5 | 5.0 | 1.6 | 6.3 | 12.5 | 37.7 | 11.7 | 9.25 | 100 | | YoloV6 | 640x640 nano | 35.0 | 10.5 | 2.7 | 15.8 | 20.8 | 63.0 | 18.0 ||| | YoloV7 | 640x640 tiny | 38.7 | 8.5 | 2.1 | 14.4 | 17.9 | 53.4 | 16.1 | 15.0 || | YoloV8 | 640x640 nano | 37.3 | 14.5 | 3.1 | 20.0 | 16.3 | 53.1 | 18.2 ||| | YoloV8 | 640x640 small | 44.9 | 4.5 | 1.47 | 11.0 | 9.2 | 28.5 | 8.9 ||| | YoloV9 | 640x640 comp | 53.0 | 1.2 | 0.28 | 1.5 | 1.2 | |||| | YoloX | 416x416 nano | 25.8 | 22.6 | 7.0 | 38.6 | 28.5 | |||| | YoloX | 416x416 tiny | 32.8 | 11.35 | 2.8 | 17.2 | 18.1 | |||| | YoloX | 640x640 small | 40.5 | 3.65 | 0.9 | 4.5 | 7.5 | 30.0 | 10.0 |||

<b>¹</b> The Rock 5 and Orange Pi5 have the RK3588 on board.<br> <b>²</b> The Rock 3, Radxa Zero 3 and Orange Pi3B have the RK3566 on board.<br> <b>²⁰</b> Recognize 20 objects (VOC) instead of 80 (COCO)

---

Dependencies.

To run the application, you have to:

• A Raspberry Pi 4 with a 64-bit operating system. It can be the Raspberry 64-bit OS, or Ubuntu 18.04 / 20.04. Install 64-bit OS <br/>
• The Tencent ncnn framework installed. Install ncnn <br/>
• OpenCV 64-bit installed. Install OpenCV 4.5 <br/>
• Code::Blocks installed (Optional). ($ sudo apt-get install codeblocks)

---

Installing the app.

To extract and run the network in Code::Blocks <br/> $ mkdir MyDir <br/> $ cd MyDir <br/> $ wget https://github.com/Qengineering/YoloFastestV2-ncnn-Raspberry-Pi-4/archive/refs/heads/main.zip <br/> $ unzip -j master.zip <br/> Remove master.zip, LICENSE and README.md as they are no longer needed. <br/> $ rm master.zip <br/> $ rm LICENSE <br/> $ rm README.md <br/> <br/> Your MyDir folder must now look like this: <br/> James.mp4 <br/> parking.jpg <br/> parking_tiny.jpg <br/> YoloFastestV2.cpb <br/> mainFV2.cpp <br/> yolo-fastestv2.cpp <br/> yolo-fastestv2.h <br/> yolo-fastestv2-opt.bin <br/> yolo-fastestv2-opt.param <br/>

---

Running the app.

To run the application load the project file YoloFastestV2.cbp in Code::Blocks.<br>

Or use Cmake.

$ cd *MyDir*
$ mkdir build
$ cd build
$ cmake ..
$ make -j4

More info or if you want to connect a camera to the app, follow the instructions at Hands-On.<br/><br/> Many thanks to dog-qiuqiu <br/><br/> <br/> <br/> <br/>

---