Hello everyone!

I’ve successfully downloaded the data for the Kuyesera AI Disaster Damage and Displacement Challenge and uploaded it to Kaggle. The dataset is 52GB in size, so it’s a bit hefty, but no worries! You can use TPUs on Kaggle to read and train models on this data, as it’s equipped with 300GB of RAM, which is more than enough for this dataset.

Feel free to explore the data, run experiments, and improve models. And if you find the dataset helpful, I’d really appreciate it if you could upvote it on Kaggle to help others find it too!

Let’s make the most of this opportunity to push the limits of AI in tackling disaster damage and displacement. https://www.kaggle.com/muhammadqasimshabbir/datasets name of data set is traindata-xview2-geotiff

Good luck to everyone!