# Datathon@IndoML 2022 — Data

来源：https://www.kaggle.com/competitions/datathonindoml-2022/data

采集时间：2026-10-19T07:19:24Z

The dataset consists of 16000 grayscale images of documents such as letter, memo, email etc. The task is to predict the label given a document image. The performance will be evaluated based on mean F score. 

## Files

*   **train** - this folder consists of the training images as <id>.tiff file. DO NOT change the ids of the individual image files as they are used for mapping to the corresponding classes.
*   **validation** - this folder consists of 900 images as <id>.tiff file for the participants to check their performance. 
*   **train_labels.csv** - map of the images to the corresponding classes.  
*   **metaData.csv** - supplemental information about the data

## Columns

*   `id` - image id || <id>part of the image file.|| E.g., if the image file 1234.tiff -> 1234
*   `label` - class label for the corresponding image|| In total 16 classes indexed from 0 to 15