This repository contains the implementation and experimental code for neural network pruning techniques published in the IET Electronics Letter paper. The project focuses on reducing the size and computational complexity of neural networks while maintaining accuracy, using morphological pruning methodologies.

This repository contains the Python code that implements the methodology of the related publication. You will find a Python package with a TensorFlow morphological layer, necessary for the pruning methodology. Additionally, you will find examples in python notebooks for pruning LeNet-300 and some models that have already been pruned. The sample networks are trained using MNIST, FASHION-MNIST and CIFAR-10 datasets from the TF repositories.