https://github.com/thesofakillers/ml_classifier-pegasus-generator
Classifying CIFAR100 and Generating Pegasus with CIFAR10
https://github.com/thesofakillers/ml_classifier-pegasus-generator
Last synced: 8 months ago
JSON representation
Classifying CIFAR100 and Generating Pegasus with CIFAR10
- Host: GitHub
- URL: https://github.com/thesofakillers/ml_classifier-pegasus-generator
- Owner: thesofakillers
- License: gpl-3.0
- Created: 2019-02-11T23:26:28.000Z (over 7 years ago)
- Default Branch: master
- Last Pushed: 2019-03-22T17:27:37.000Z (about 7 years ago)
- Last Synced: 2025-01-17T10:43:41.474Z (over 1 year ago)
- Language: Jupyter Notebook
- Homepage:
- Size: 928 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Machine Learning - Object Classifier and Pegasus Generator
Originally made for my university's Department of Computer Science's course _Software, Systems & Applications_ under the sub-module _Machine Learning_, as part of the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:
1. The first part consists in building a [classifier](https://en.wikipedia.org/wiki/Statistical_classification) that generalises well for the [CIFAR-100](https://www.cs.toronto.edu/~kriz/cifar.html) dataset. There should be thorough experimentation in determining which architectures and optimisations to utilise.
2. The second part consists in [generating](https://en.wikipedia.org/wiki/Generative_model) a colour image of a [Pegasus](https://en.wikipedia.org/wiki/Pegasus), training only on data from [CIFAR-10](https://www.cs.toronto.edu/~kriz/cifar.html)
For obvious reasons, the "data" directory is not committed to this repo.