A fast C++ implementation of TensorFlow Lite classification on a bare Raspberry Pi 4. The Raspberry Pi 64 bits version of Ubuntu is used as operating system. Once overclocked to 1925 MHz, your app runs at 23 FPS without any hardware accelerator.
Special made for a bare Raspberry Pi see: https://qengineering.eu/install-ubuntu-18.04-on-raspberry-pi-4.html
Papers: https://arxiv.org/pdf/1712.05877.pdf
Training set: COCO with 1000 objects
Size: 224x224
| Model | RPI 4 @1950 MHz - 64 OS |
|---|---|
| Mobile_V1 Lite | 38.5 FPS |
| Mobile_V2 Lite | 45.5 FPS |
| Inception_V2 Lite | 10.0 FPS |
| Inception_V4 Lite | 2.0 FPS |
With a regular 32 bits Raspbian OS you get lower frame rates see: https://github.com/Qengineering/TensorFlow_Lite_Classification_RPi_32-bits
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
- TensorFlow Lite framework installed. Install TensorFlow Lite
- 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/TensorFlow_Lite_Classification_RPi_64-bits/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:
tabby.jpeg
schoolbus.jpg
grace_hopper.bmp
Labels.txt
TensorFlow_Lite_Mobile.cpb
TensorFlow_Lite_Class.cpp
Next, choose your model from TensorFlow: https://www.tensorflow.org/lite/guide/hosted_models
Download a quantized model, extract the .tflite from the tarball and place it in your MyDir.
Now your MyDir folder may contain: mobilenet_v1_1.0_224_quant.tflite.
Or: inception_v4_299_quant.tflite. Or both of course.
Enter the .tflite file of your choice on line 54 in TensorFlow_Lite_Class.cpp
The image to be tested is given a line 84, also in TensorFlow_Lite_Class.cpp
Run TestTensorFlow_Lite.cpb with Code::Blocks. More info or
if you want to connect a camera to the app, follow the instructions at Hands-On.
