This example demonstrates how to use Post-Training Quantization API from Neural Network Compression Framework (NNCF) to quantize OpenVINO models on the example of MobileNet v2 quantization, pretrained on Imagenette dataset.
The example includes the following steps:
- Loading the Imagenette dataset (~340 Mb) and the MobileNet v2 OpenVINO model pretrained on this dataset.
- Quantizing the model using NNCF Post-Training Quantization algorithm.
- Output of the following characteristics of the quantized model:
- Accuracy drop of the quantized model (INT8) over the pre-trained model (FP32)
- Compression rate of the quantized model file size relative to the pre-trained model file size
- Performance speed up of the quantized model (INT8)
At this point it is assumed that you have already installed NNCF. You can find information on installation NNCF here.
To work with the example you should install the corresponding Python package dependencies:
pip install -r requirements.txt
It's pretty simple. The example does not require additional preparation. It will do the preparation itself, such as loading the dataset and model, etc.
python main.py