Challenge: Completed #educational Weight: 20.0
2330
219
15
91

🛠 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.

🕵️ Introduction

Chess veterans can take one quick look at the board and plan their next moves. This puzzle is all about teaching your AI to identify the chessboard configuration, given an image. We will be doing this using the Forsyth–Edwards Notation (FEN). It is a one-line ASCII-string used as a standard notation for describing a chess game’s particular board position. Given an image, your task is to identify the FEN value of the chessboard.

Understand with code! Here is getting started code for you.😄

💾 Dataset

The given dataset contains images of chess board with pieces of both black and white. Each image is of size 254 * 254. A CSV is also provided containing the image id and the configuration(pieces and their position) of that image. The configuration of chess board is calculated using the Forsyth-Edwards Notation.

Sample Column

|ImageID|label |
|-------|----------------------------------------------|
|0      |5k2/6n1/3pP2b/P1q1Pp1p/1p1P3B/2p2K1P/2N1R1PR/8|

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 has least number of pieces.

📁 Files

Following files are available in the resources section:

• train.csv - (40000 samples) This csv file contains ImageID column which corresponds to train.zip and labels
• train.zip - (40000 samples) This zip file contains images corresponding to the first column of train.csv.
• val.csv - (4000 samples) This csv file contains ImageID column which corresponds to val.zip and labels
• val.zip - (4000 samples) This zip file contains images corresponding to the first column of val.csv.
• test.zip - (10000 samples) This zip file contains testing images that will be used for actual evaluation for the leaderboard score.

🚀 Submission

• Prepare a CSV containing two columns, one is ImageID which corresponds to test.zip image names and model predictions label column in FEN format.
• Sample submission format available at sample_submission.csv in the resorces section.

Make your first submission here 🚀 !!

🖊 Evaluation Criteria

During evaluation Word Error Rate will be used to test the efficiency of the model and in python using jiwer. For ex.

from jiwer import wer

ground_truth = 'hello world' hypothesis = 'hello duck'

error = wer(ground_truth, hypothesis)