Tutorial: A Deep Learning Approach
Face masks have become a common public sight in the last few months. The Centers for Disease Control (CDC) recently advised the use of simple cloth face coverings to slow the spread of the virus and help people who may have the virus and do not know it from transmitting it to others. Wearing masks is broadly recognised as critical to reducing community transmission and limiting touching of the face.
In a time of concern about slowing the transmission of COVID-19, increased surveillance combined with AI solutions can improve monitoring and reduce the human effort needed to limit the spread of this disease. The objective of this challenge is to create an image classification machine learning model to accurately predict the likelihood that an image contains a person wearing a face mask, or not. The total dataset contains 1,800+ images of people either wearing masks or not.
Your machine learning solution will help policymakers, law enforcement, hospitals, and even commercial businesses ensure that masks are being worn appropriately in public. These solutions can help in the battle to reduce community transmission of COVID-19.
The evaluation metric for this challenge is Area Under the Curve.
Your submission file should look like:
id label ttuqxjhrmdqhppfxrbzgyciipwdxcf.jpg 0.99 qmltykiislwklsklnzhcsrfsqwmaun.jpg 0.23 lkzeblenqbovljxpucpsufmprjxxqn.jpg 0.67
This is a learning competition. Aside from knowledge, there are no prizes for this competition.
You will receive 25 points for your first submission and 50 points for your first non-sample submission. You can read more about Zindi points here.
As this is a knowledge competition it will not close.
We reserve the right to update the contest timeline if necessary.
To help make this a more useful Knowledge competition, we have compiled some tutorials and other resources for learning the techniques associated with image classification. We’ll add to this list over the course of the competition, so if you have a good tutorial, a handy video or GitHub repo, or just a pro tip, post it in the discussion forums and we’ll share it here.
In addition, we’ll be hosting two Q&A sessions this weekend where you can ask our data scientists any questions that don’t get answered on the discussion boards. See the details below.
New to this? We’ve taken a look at some resources to get you started.
OK, so you've learnt how to train an image classification model, and you try it out on a Zindi competition. Your score is decent, but there's a group of folks sitting above you on the leaderboard and you'd like to know what they have that you don't. Eking out that final 1% accuracy requires a whole bag of tricks. This tutorial takes a look at up-to-date image classification methods and shows you how you can start to climb towards the top in your next image recognition challenge.
Be sure to dial in to ask Zindi data scientist Johno Whitaker your burning questions:
Zoom room link, please send us an email at firstname.lastname@example.org with your questions if you would like to join, and we'll give you the password.
How to enroll in your first Zindi competition
How to create a team on Zindi
How to update your profile on Zindi
This challenge is open to all and not restricted to any country.
Teams and collaboration
You may participate in this competition as an individual or in a team of up to four people. When creating a team, the team must have a total submission count less than or equal to the maximum allowable submissions as of the formation date. A team will be allowed the maximum number of submissions for the competition, minus the highest number of submissions among team members at team formation.
Multiple accounts per user are not permitted, and neither is collaboration or membership across multiple teams. Individuals and their submissions originating from multiple accounts will be disqualified.
Code must not be shared privately outside of a team. Any code that is shared, must be made available to all competition participants through the platform. (i.e. on the discussion boards).
Datasets and packages
The solution must use publicly-available, open-source packages only. Your models should not use any of the metadata provided.
You may use only the datasets provided for this competition. Automated machine learning tools such as automl are not permitted.
If the challenge is a computer vision challenge, image metadata (Image size, aspect ratio, pixel count, etc) may not be used in your submission.
You may use pretrained models as long as they are openly available to everyone.
The data used in this competition is the sole property of Zindi and the competition host. You may not transmit, duplicate, publish, redistribute or otherwise provide or make available any competition data to any party not participating in the Competition (this includes uploading the data to any public site such as Kaggle or GitHub). You may upload, store and work with the data on any cloud platform such as Google Colab, AWS or similar, as long as 1) the data remains private and 2) doing so does not contravene Zindi’s rules of use.
You must notify Zindi immediately upon learning of any unauthorised transmission of or unauthorised access to the competition data, and work with Zindi to rectify any unauthorised transmission or access.
Your solution must not infringe the rights of any third party.
Submissions and winning
You may make a maximum of 10 submissions per day.
Note that to count, your submission must first pass processing. If your submission fails during the processing step, it will not be counted and not receive a score; nor will it count against your daily submission limit. If you encounter problems with your submission file, your best course of action is to ask for advice on the Competition’s discussion forum.
Note that there is no public/private leaderboard split for this challenge. Read more about public and private leaderboards in this post.
You acknowledge and agree that Zindi may, without any obligation to do so, remove or disqualify an individual, team, or account if Zindi believes that such individual, team, or account is in violation of these rules. Entry into this competition constitutes your acceptance of these official competition rules.
Zindi also reserves the right to disqualify you and/or your submissions from any competition if we believe that you violated the rules or violated the spirit of the competition or the platform in any other way. The disqualifications are irrespective of your position on the leaderboard and completely at the discretion of Zindi.