This repository contains an implementation of the VGGNet architecture introduced in the paper "Very Deep Convolutional Networks for Large-Scale Image Recognition" by Karen Simonyan and Andrew Zisserman. The model was originally designed for the ImageNet Challenge 2014 and is renowned for its simplicity and depth, achieving state-of-the-art results in image classification tasks.
In this project, VGGNet was trained on the Fashion-MNIST dataset, showcasing its effectiveness even on simpler datasets for classification tasks.
Using Fashion-MNIST dataset, the model achieved the following results:
- Precision: 90.23%
- Recall: 90.26%
- F1-Score: 90.15%
Original Paper: "Very Deep Convolutional Networks for Large-Scale Image Recognition".
Author: Karen Simonyan, Andrew Zisserman