A fast C++ implementation of TensorFlow Lite classification on a bare Raspberry Pi 4.
Once overclocked to 1950 MHz, your app runs an amazing 33 FPS without any hardware accelerator.
Special made for a bare Raspberry Pi 4 see Q-engineering deep learning examples
Papers: https://arxiv.org/pdf/1712.05877.pdf
Training set: COCO with 1000 objects
Size: 224x224
Frame rate Mobile_V1 Lite : 33 FPS (RPi 4 @ 1950 MHz - 32 bits OS)
Frame rate Mobile_V2 Lite : 36.2 FPS (RPi 4 @ 1950 MHz - 32 bits OS)
Frame rate Inception_V2 Lite : 8.9 FPS (RPi 4 @ 1950 MHz - 32 bits OS)
Frame rate Inception_V4Lite : 1.6 FPS (RPi 4 @ 1950 MHz - 32 bits OS)
With a 64 bits OS you get higher frame rates see: https://github.com/Qengineering/TensorFlow_Lite_Classification_RPi_64-bits
To run the application, you have to:
- TensorFlow Lite framework installed. Install TensorFlow Lite
- OpenCV 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_32-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.
