This solution was the result of the combined efforts of @koleshjr and I. General DescriptionOur solution consists of a two stage approach: object detection to d... See more

hello everyone ! we wish from the top winners to share their notebooks or their approaches to learn from them.

<Error><Code>AccessDenied</Code><Message>Access Denied</Message><RequestId>4P7HR9M0RFNVZQ79</RequestId><HostId>a... See more

Hello,I have a problem to download test images by next links: https://kuyesera-ai-challenge.s3.amazonaws.com/test_image_coords.csv https://kuyesera-ai-challen... See more

Currently, I can view other team S3 buckets. Can other teams also view and read my bucket? If so, I think each team's custom data and solutions can be leaked un... See more

Hello participants! Thank you for your patience while we prepared the AWS environments for your use and enjoyment. If you were within the top 100 participants o... See more

Due to the size of the datast(approx 200gb), some of us are unable to partake in the challenge. We werre promised AWS resources for this competition, provided... See more

All my subs have disappeared after attempting to form a team which I quickly disbanded as the potential team member was already in another team.@zindi @amy

It was written that top 100 contestants will get AWs credits, how can we claim them?

# # Extract and generate NDVI, NBR, NDWI, and NDMI from s2 data in awstrain_s2_df = parallel_process(train_df, n_processes=4)val_s2_df = parallel_process(val_df... See more

Hello everyone, we hope that you are enjoying working on this challenge! This is a quick reminder that you have less than two days to make a submission in order... See more

Hello Everyone ,Is anyone using mamba bda? I am about to give up on this approach and go to the object detection approach. I honestly don't know If I am doing s... See more

Is allowed? case 1. coco pretrained ( general domain ) case 2. or something else satellite domain's pretrained model but not downstream training

It seems to me that the xview training data is nearly useless as the distribution of pixels is just too different between xview and malawi data.I am curious to... See more

"This is a starter notebook for the Kuyesera AI Disaster Damage and Displacement State competition, without any fine-tuning. If you find it helpful, please upvo... See more

I have extracted the training data into separate, more manageable datasets. You can download them from the following links: Hold XView GeoTIFF Data Size: 11 GB... See more

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 52... See more

I just now sort of understood how to approach this competition and I'm wondering what F1 scores you guys are getting in training. The maximum I got so far is 0.... See more

Hello. Trying to download the Tiff file, got the error below after clicking the link. It worked yesterday but timeout after a while.https://kuyesera-ai-challeng... See more

Please, is there way to manage memory space because of the size of the dataset?I have limited memory space

Is there anyone who is able to access train data . tell me how to dowload data from AWS. I was not able to do it .