This repository presents an in-depth evaluation of neural network quantization methods for edge deployment. It analyzes accuracy–compression trade-offs across image classification and object detection models using TensorFlow Lite, QKeras, and SQuant, providing practical insights for deploying efficient, low-resource machine learning models.
deep-learning tensorflow pytorch quantization squant nueral-networks edge-computing tensorflow-lite qkeras
-
Updated
Dec 29, 2025 - Jupyter Notebook