Rules
General Rules
- The goal of this competition is to classify the liquid amount of bottles as accurately as possible.
 - Students can implement
any
training methods taught in class or practiced in homework,
or even external ideas not covered
.
 - The baseline accuracy is 70% and is what everyone should achieve. 1 point will be reduced for each 1% below 70%. Top 10 students would have bonus points. 
 - Students should participate in the competition using only Tensorflow 1.13.
Submission details
1. No groups! Each student must participate as a team with only one person. Please go to
'Team'
, use your name as the team name. 
2. A valid submission is a .csv file containing 2 columns in a similar format as the sample (prediction_labels_template.csv) that is available on this site.
3. One can submit at most 20 times a day.
4. The public leaderboard uses 70% of the test data to generate the accuracy. The final leaderboard will also consider the rest 30% of the test data. So what you see on the public leaderboard may be different from the final rankings (the private leaderboard). The bonus distribution would depend on the result of the
private leaderboard
.
Academic integrity
- Don't cheat! Discussions among each other are encouraged, but
do not copy other people's results!!
This will be considered as plagiarism.
- If you use some external open source code you find on Internet, you must reference it.