Skip to content

README.md

Latest commit

 

History

History
36 lines (24 loc) · 1.45 KB

README.md

File metadata and controls

36 lines (24 loc) · 1.45 KB

Post-Training Quantization of MobileNet v2 ONNX Model

This example demonstrates how to use Post-Training Quantization API from Neural Network Compression Framework (NNCF) to quantize ONNX 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 ONNX 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)
    • Performance speed up of the quantized model (INT8)

Prerequisites

Before running this example, ensure you have Python 3.10+ installed and set up your environment:

1. Create and activate a virtual environment

python3 -m venv nncf_env
source nncf_env/bin/activate  # On Windows: nncf_env\Scripts\activate.bat

2. Install NNCF and other dependencies

python3 -m pip install ../../../../ -r requirements.txt

Run Example

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