# AII2023-Competition — Data

来源：https://www.kaggle.com/competitions/aii2023-conference-competition/data

采集时间：2026-10-19T07:38:47Z

### **About the data:**

**What files do I need?**  The participant needs images present in the train and test folder, and corresponding train.csv file to train the model. 
Number of Train samples: 62870
Number of Test samples:  28080

For more details about the dataset, refer:  N. Shaffi and F. Hajamohideen, "uTHCD: A New Benchmarking for Tamil Handwritten OCR," in IEEE Access, vol. 9, pp. 101469-101493, 2021, doi: 10.1109/ACCESS.2021.3096823.


**What should I expect the data format to be?**  The image files are in BMP format. The CSV files consists of two columns (ID) and corresponding class label in the second column. 

**What am I predicting?**  The class label of the input image consisting of isolated Tamil handwritten character sample 

## Files

*   **train.csv** - the training set consists of two columns. The first column (ID) consists of filename and the second column (Class Label) consists of corresponding ground truth label. 
*   **test.csv** - the test set consists of just the filenames in the only column (ID).
*   **sample_submission.csv** - a sample submission file in the correct format. The Class Label column is mapped to String format (not int value). 
*   **ReadMe.pdf** - supplemental information about the data

## Columns
*   `ID` - filename of each sample in train/test folder. 
*   `Class Label` - Represents the class label of the Tamil character image.