Model is not available yet as my GPU is not powerful enough to train on the full dataset. I will rent some time later. Check back in a while.
A relatively simple CNN. All images are resized to 256x256 before fed through the network. Details can be found in the files.
Data used is the classic Food101 dataset. Big thanks to the contributors!
Copyright (c) 2025 ShadowProgrammer.
Permission is granted to copy, distribute and/or modify this document under the terms of the GNU Free Documentation License, Version 1.3 or any later version published by the Free Software Foundation; with no Invariant Sections, no Front-Cover Texts, and no Back-Cover Texts. A copy of the license is included in the section entitled "GNU Free Documentation License".