GitHub - AntonisKl/Food-Image-Classification: 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.

Branches Tags

Name		Name	Last commit message	Last commit date
Latest commit History 17 Commits
.gitignore		.gitignore
EfficientNet.ipynb		EfficientNet.ipynb
custom_layers.py		custom_layers.py
dataset_prep.py		dataset_prep.py
food_recognition_resnet.ipynb		food_recognition_resnet.ipynb
food_recognition_resnet.py		food_recognition_resnet.py
nonsense_examples.txt		nonsense_examples.txt
utils.py		utils.py
vgg16.py		vgg16.py

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.

www.kaggle.com/c/food-recognition-challenge-2021/overview

tensorflow keras cnn kaggle kaggle-competition image-classification