Food Recognition

This is one of two assignments on deep learning. You only have to complete one of the two assignments. The other assignment is Deep Learning for Natural Language Processing . 

The food-11 dataset

This assignment is meant for those of you that have a bit more experience as all you get to start with is the data. You might want to think about how you can exploit already trained networks. 

Images of food, 11 classes, variable size, colour images.
https://mmspg.epfl.ch/downloads/food-image-datasets/ Links to an external site.

Links to an external site.If that link doesnt work, try 

https://www.kaggle.com/vermaavi/food11 Links to an external site.

This is a dataset containing 16643 food images grouped in 11 major food categories. The 11 categories are Bread, Dairy product, Dessert, Egg, Fried food, Meat, Noodles/Pasta, Rice, Seafood, Soup, and Vegetable/Fruit. Similar as Food-5K dataset, the whole dataset is divided in three parts: training, validation and evaluation. The same naming convention is used, where ID 0-10 refers to the 11 food categories respectively.

Your task is to train a classifier and evaluating it on the food-11 dataset. Handin your code and a small presentation (say 5-15 pages) describing your results in Canvas before the deadline.