GiacomoLeoneMaria/How-to-Increment-the-Accuracy-of-CNN-step-by-step

The aim of this project is to implement an image classifier based on convolu- tional neural networks. Starting by implementing a simple shallow network and then refining it until a pre-trained ResNet18 is implemented, showing at each step how the accuracy of the model improves. The provided dataset (from [Lazebnik et al., 2006]) contains 15 categories.

Jupyter Notebook