Welcome to ACM AI's first Mini-ML Challenge!

In this challenge, you’ll build a model to automatically identify the biome type (e.g. Desert, Plains, Forest, etc.) from images captured in a Minecraft world. The theme around this challenge is *efficiency* since you only have a few hours to train a model.

Your Task

Use the provided train images (with labels) to train your model.

Generate predictions for the test images and submit them in the required format.

Your submissions will be scored on a public leaderboard during the competition and a private leaderboard at the end.

All images and CSVs are available under the Data tab. See the Evaluation page for details about the hidden ground truth and leaderboard splits.

Good luck!