This project is based on the kaggle dataset Best Artworks of All Time. It's a collection of artworks from 50 worldwide known painters. The objective is to train a model to learn the style of these masters and later try to predict who is the painter of a never-seen dataset.
For this project, I'm working on the resized dataset.
This project explores the use of data loaders, fine-tuning transfer learning, ResNets and learning rate scheduler.
- conda 4.7.12
- python 3.7.4
- ptorch 1.3.1