Skip to content

This project was implemented for a Kaggle competition (see link in repo's details). The goal was to classify food photos by using a training set of ~30.000 images. After experimentation with different models like VGG16 and ResNet CNNs, the final decision was to use transfer learning with ResNet50 achieving 61% top-1 accuracy.

Notifications You must be signed in to change notification settings

AntonisKl/Food-Image-Classification

About

This project was implemented for a Kaggle competition (see link in repo's details). The goal was to classify food photos by using a training set of ~30.000 images. After experimentation with different models like VGG16 and ResNet CNNs, the final decision was to use transfer learning with ResNet50 achieving 61% top-1 accuracy.

Topics

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Jupyter Notebook 64.7%
  • Python 35.3%