Given a set of grayscale document images, the task is to classify each image into one of the 16 classes or document types. The training dataset consists of 16000 images with 1000 images belonging to each class. The dataset was collected from the RVL-CDIP dataset [1].

![](https://lh4.googleusercontent.com/g2CLiBvekM5cRzBCZA4zHDMOypCTmIYxfQIbjtDADEssJFiQ7FiOd5X5wsip2D4eCdJP54R2FyFI1sa-9YZK1ZM0ArP63Q--4J06x4y9038tZdiBmFAmTfPGEb_L-1rIZA=w1280)

![](https://lh6.googleusercontent.com/_taiQGOKhNQwU_bkgDKMYTefotZe2ihA0Qec5Uy-9B9vi3kqLcHioQwetSdbcE3tK8iFCxSyfFRF5GMYKxK8RpztPnfDQpy2D6hOt9OtslbxPNlc3JRTo29woOR9QoPcuw=w1280)

**Check out our Datathon [page](https://sites.google.com/view/datathonindoml/home) for more information**

**Note: All the teams are requested to fill this [form](https://forms.gle/Dh2GQeuDAVvwFaNTA) to be eligible for prizes** (ignore, if already filled).

**Note: All teams are requested to join this [group] (https://groups.google.com/g/datathonatindoml-2022). We will be making all the necessary announcements here.**

**Note: We would like to remind all the participants that attaining the highest score on the public leaderboard does not guarantee a winning position. The submitted code will be tested on a separate private dataset. The merit of the work will also be judged based on the submitted report and other judging criteria as mentioned on the [Datathon webpage](https://sites.google.com/view/datathonindoml/home) . So, teams will have a chance even if the model does not attain the highest score on the specific validation set.**

**For questions, reach out to us at <datathonatindoml@gmail.com>**

[1] A. W. Harley, A. Ufkes, K. G. Derpanis, "Evaluation of Deep Convolutional Nets for Document Image Classification and Retrieval," in ICDAR, 2015