The Food101 dataset consists of pictures of 101 types of food. Each folder corresponds to a type of food, and contains 1000 pictures for each folder. This dataset takes up to ~5GB of memory, so in order to make this repository lighter, we didn't include them. However, this dataset can be downloaded directly from Kaggle.
The dataset is not necessary for the model to run. Use it only if your plan is training the model by yourself.
This is the Food 101 dataset, available from:
It contains images of food organized by type of food. It was used in the Paper "Food-101 – Mining Discriminative Components with Random Forests" by Lukas Bossard, Matthieu Guillaumin and Luc Van Gool.
It's a good (and large) dataset for testing computer vision techniques.
The Food-101 data set consists of images from Foodspotting [1] which are not property of the Federal Institute of Technology Zurich (ETHZ). Any use beyond scientific fair use must be negociated with the respective picture owners according to the Foodspotting terms of use [2]. [1] http://www.foodspotting.com/ [2] http://www.foodspotting.com/terms/