π Contribute: Found a typo? Or any other change in the description that you would like to see? Please consider sending us a pull request in the public repo of the challenge here.
π΅οΈ Introduction
World-class chess players are known for anticipating the moves of the opposition. They have the foresight to see various permutations of moving a chess piece and its implication long before it happens. Thatβs what makes them the best!
Are you up for a similar challenge? Can you create a model that will predict the winner a chess game? With inputs of few moves before checkmate, can you predict which side will win the match - white or black?
Your model should be able to predict the winner of the game few moves before the checkmate!
Understand with code! Here is getting started code
for you.π
π Explainer Video
πΎ Dataset
The given dataset contains images of chess board with pieces of both black and white. Each image is of size 256 * 256. A CSV is also provided containing the ImageID
and label
as the color which wins after few moves before checkmate. The CSV also contains turn
column which represents which side ( black/white ) has the turn to move it's pieces.
The dataset is divided into train and validation set, each containing a zip file and csv corresponding to it. For evaluation you are provided with the test.zip which contain the images for which you need to find which color wins.
π Files
Following files are available in the resources
section:
train.csv
- (40000
samples) This csv file contains ImageID column which corresponds totrain.zip
and turn & label column.train.zip
- (40000
samples) This zip file contains image corresponding to the first column oftrain.csv
.val.csv
- (4000
samples) This csv file contains ImageID column which corresponds toval.zip
and turn & label column.val.zip
- (4000
samples) This zip file contains image corresponding to the first column ofval.csv
.test.csv
- (10000
samples) This csv file contains ImageID column which corresponds totest.zip
and turn column.test.zip
- (10000
samples) This zip file contains testing images that will be used for actual evaluation for the leaderboard score. Theturn
column for this set is available intest.csv
π Submission
- Prepare a CSV containing two columns, one is ImageID which corresponds to the images in
test.zip
andlabel
as predicted value denoting if thewhite
orblack
won the match. - Sample submission format available at sample_submission.csv in the resorces section.
Make your first submission here π !!
π Evaluation Criteria
During evaluation F1 score is used as Primary Score and Accuracy Score as Secondary Score will be used to test the efficiency of the model.
π Links
- πͺ Challenge Page: https://www.aicrowd.com/challenges/chess-win-prediction
- π£οΈ Discussion Forum: https://www.aicrowd.com/challenges/chess-win-prediction/discussion
- π Leaderboard: https://www.aicrowd.com/challenges/chess-win-prediction/leaderboards