Round 1: Completed Weight: 35.0

πŸ•΅οΈ Introduction

Maintaining a healthy diet is difficult. As the saying goes, the best way to escape a problem is to solve it. So why not leverage the power of deep learning and computer vision to build the foundation of a semi-automated food tracking application?

With over 9300 hand-annotated images with 61 classes, the challenge is to train accurate models that can look at images of food items and detect the food items present in the image. It's time to unleash the food (data)scientist in you! Given any image, identify the food item present in it.

Understand with code! Here is getting started code for you.πŸ˜„

πŸ’Ύ Dataset

The dataset is a set of images of food items and a CSV file linking each image to its annotated food class. For simplification, each image contains only a single food item in it. The images are of varying sizes. A total of 61 classes of different food items are present like egg, bread, and water to name a few. The list of classes is present in dataset_info.txt.

πŸ“ Files

Following files are available in the resources section:

  • train.zip - (9233 samples) This zip file contains a folder train_images with a set of 9233 images and a train.csv containing the image id and the class name associated with the image.
  • test.zip - (484 samples) This zip file contains a folder test_images with a set of 484 images and a train.csv with the list comprising only all the image ids and not their respective class names.

πŸš€ Submission

  • Prepare a CSV containing a single column with the header as ClassName containing the predicted class for the corresponding image in the test.csv.
  • The name of the above file should be submission.csv.
  • Sample submission format available at sample_submission.csv.

Make your first submission here πŸš€ !!

πŸ–Š Evaluation Criteria

During evaluation, F1 score will be used to test the efficiency of the model where,

πŸ”— Links

πŸ“± Contact


See all
Getting Started Notebook for FOODCH
Over 2 years ago