Originally made for my university's Department of Computer Science's course Software, Systems & Applications under the sub-module Machine Learning, as part of the coursework in 2018/2019.
This project has two main parts:
- The first part consists in building a classifier that generalises well for the CIFAR-100 dataset. There should be thorough experimentation in determining which architectures and optimisations to utilise.
- The second part consists in generating a colour image of a Pegasus, training only on data from CIFAR-10
For obvious reasons, the "data" directory is not committed to this repo.