Bengali is the fifth most spoken of all native languages worldwide. After completing the month-long signature Deep Learning competition on Bengali Automatic Speech Recognition (ASR) last year, we at the **Department of Computer Science and Engineering, BUET** now focus on another computational challenge. This year again, in partnership with **Bengali.AI**, we welcome participants to attend the **DL Sprint 2.0** and play around with the first multi-domain large **Bengali Document Layout Analysis Dataset: BaDLAD**, as a part of **BUET CSE Fest 2023.**

For training the model, we will use a subset of the BaDLAD dataset contributed by our co-host, Bengali.AI. The details of the dataset can be found [in this paper](https://arxiv.org/abs/2303.05325)

***This competition is open to all, not only for undergraduates. Anyone from any institution can participate.***
***However, in the spirit of fairness, all students from BUET CSE18 (the organizing batch) are disallowed from participating.***

## How to Participate

Registration link: https://forms.gle/FffwUxn3huKYBjhZ8. **Anyone can join this competition. However, registration is mandatory to be eligible for prizes.**

Facebook event link: [DL Sprint 2.0](https://www.facebook.com/events/1882607365439555)

## Competition Schedule
Phase 1: Will be held in Kaggle from 18th June to 5th August (11:59 PM GMT+6). Participants are expected to build and train their models during this phase. The top 15 teams from this round will be selected for Phase 2.
Phase 2: Will be held onsite at the Department of CSE, BUET, on 11th August (tentative). Only invited participants can participate. Participants will present their methods live in front of the judges’ panel.

**Important**
All teams will submit working Kaggle notebooks for Train and Test with appropriate instructions and documentation for reproducibility after Phase 1. **Test(/Inference) notebook must run on Kaggle Notebooks (with any accelerator).**

## Scoring
**50% Weight on Phase-1**
<ul>
<li>15% public DICE</li>
<li>35% private DICE</li>
</ul>

**50% Weight on Phase-2**
<ul>
<li>25% mAP </li>
<li>20% Judge and Presentation (Explainability, Reproducibility)</li>
<li>5% Inference Speed</li>
</ul>


## Acknowledgements
We thank BJIT for sponsoring BUET CSE Fest 2023 and Bengali.AI for co-hosting the DL Sprint 2.0 event with technical support.