Paper: https://arxiv.org/abs/1611.10012
Special made for a bare Raspberry Pi 4 see Q-engineering deep learning examples
Training set: COCO
Size: 300x300
Frame rate V1 : 3.19 FPS (RPi 4)
Frame rate V1_0.75: 4.98 FPS (RPi 4)
Frame rate V2 : 2.02 FPS (RPi 4)
Frame rate V2 Lite: 3.86 FPS (RPi 4)
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
- OpenCV 64 bit installed. Install OpenCV 4.5
- 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/MobileNet_SSD_OpenCV_TensorFlow/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:
Traffic.jpg
COCO_labels.txt
frozen_inference_graph_V1.pb (download this file from: https://drive.google.com/open?id=1sDn1guYV6oj-AeYuC-riGRh4kv9XBTMz )
frozen_inference_graph_V2.pb (download this file from: https://drive.google.com/open?id=1EU6tVcDNLNwv-pbJUXL7wYUchFHxr5fw )
ssd_mobilenet_v1_coco_2017_11_17.pbtxt
ssd_mobilenet_v2_coco_2018_03_29.pbtxt
TestOpenCV_TensorFlow.cpb
MobileNetV1.cpp (can be use for V2 version also)
To run the application load the project file TestOpenCV_TensorFlow.cbp in Code::Blocks. More info or
if you want to connect a camera to the app, follow the instructions at Hands-On.