DSTA BrainHack TIL-AI 2025

Contents

• DSTA BrainHack TIL-AI 2025
  • Get started
  • Understanding this repo
  • Build, test, and submit
  • Links

Get started

Here's a quick overview of the initial setup instructions. You can find a more detailed tutorial, including advanced usage for power users, in the Wiki.

Use this repository as a template to create your own, and clone it into your Vertex AI workbench. You'll want to keep your repository private, so you'll need to create a GitHub Personal Access Token.

You'll also need to initialize the Git submodules:

git submodule update --init

This repository requires Python 3.12 or newer to work. Use conda to create a virtual environment with a Python version of at least 3.12.

conda create --name til python=3.12
conda activate til

Finally, install the development dependencies into your newly created virtual environment.

pip install -r requirements-dev.txt

Understanding this repo

There's a subdirectory for each challenge: asr/, cv/, ocr/, and rl/. Each contains:

• A src/ directory, where your code lives.
  • *_manager.py, which manages your model. This is where your inference and computation takes place.
  • *_server.py, which runs a local web server that talks to the rest of the competition infrastructure.
• Dockerfile, which is used to build your Docker image for each model.
• requirements.txt, which lists the dependencies you need to have bundled into your Docker image.
• README.md, which contains specifications for the format of each challenge.

You'll also find a final subdirectory, test/. This contains tools to test and score your model locally.

There are also two Git submodules, til-25-finals and til-25-environment. finals contains code that will be pulled into your repo for Semifinals and Finals. environment contains the til_environment package, which will help you train and test your RL model, and is installed by pip during setup. Don't delete or modify the contents of til-25-finals/, til-25-environment/, or .gitmodules.

Build, test, and submit

Submitting your model for evaluation is simple: just build your Docker image, test it, and submit. You can find a more detailed tutorial, including advanced usage for power users, in the Wiki.

You'll first want to cd into the directory you want to build. Then, build the image using Docker, following the naming scheme below. You should then run and test your model before using til submit to submit your image for evaluation.

# cd into the directory. For example, `cd ./asr/`
cd CHALLENGE

# Build your image. Remember the . at the end.
docker build -t TEAM_ID-CHALLENGE:TAG .

# Optionally, you can run your model locally to test it.
docker run -p PORT --gpus all -d IMAGE_NAME:TAG
python test/test_CHALLENGE.py

# Push it for submission
til submit TEAM_ID-CHALLENGE:TAG

Links

• The repo Wiki contains tutorials, specifications, resources, and more.
• Your Vertex AI Workbench on Google Cloud Platform is where you'll do most of your development.
• The Guardian's Handbook houses the Leaderboard and info about the competition.
• TIL-AI Curriculum on Google Drive contains educational materials specially crafted for TIL-AI.
• The #hackoverflow channel on the TIL-AI Discord server is a forum just for Guardians like you.

---

Code in this repo is licensed under the MIT License.