The project aims to implement an iOS application for Neural Style Transfer on photos of people.
- User can either take a photo with the front/back camera or upload one from the photo gallery.
- One can generate a stylized version of the uploaded photo.
- Generated photo can be saved on the device.
- Binary classification model (human/not human) implemented and trained with
Keras
, and converted intoCoreML
format, which allows performing classification of client-side.
- The
PyTorch
model performs Neural Style Transfer as a part of the web-service, implemented withaiohttp
.
SemVer is used for versioning. For the versions available, see the tags on this repository.
This project is licensed under the MIT License - see the LICENSE file for details.
- Sergey Kastryulin - Initial work - snk4tr