Hello everyone. Is the training labels now available ?PLEASE @Zindi @Amy_Bray @meganomaly, RESPOND. This is a very SHORT competition with 25 DAYS REMAINING and... See more

Good day, This is coming after a long while(competition ended 4 months ago or so) but we'd just like to clarify things.As per the leaderboard here on Zindi, my... See more

Thanks to the organizers. I have endless hours of fun understanding this problem. I am glad to share my approach.**Detecting Human Settlements**The competition... See more

Hello Fellow Zindians, Sorry this took too long. Thank you @Zindi and INEGI for such an amazing competition. My solution was purely gbdt models. All gbdt models... See more

- TLDR; An ensemble of 1D CNN modelsDetails - Seeing that 2D CNN approaches were limited as it was difficult for a human to detect whether the class of an imag... See more

Dear Zindians,The leaderboard has been revealed. We would like to extend our congratulations to the winners of this challenge on detecting human settlements.We... See more

The private leaderboard has been updated now. It was fun participating in this one. I and my team mate have recieved mails for code submission, although this ma... See more

Hello Zindians,Some of you have asked why the leaderboard was not revealed at challenge close. As indicated in the challenge description, winners of this challe... See more

Good day Concerning the final(private) leaderboardUsually, when competitions end, it takes little to no time for the private leaderboard to be uploaded. For som... See more

Hi there. I tried several methods, using both ML and deep learning. I, however, got the best results using a CNN with ResNet50 with class weights. My lb score n... See more

Seems rather odd for a competition like this not to have Private Board results immediately after the competition ends. Was it mentioned somewhere that results w... See more

My submission just keep on showing "scoring....". It's been 40+ minutes now. I'm sure the format is correct.Nevermind, I just resubmit the same file at it worke... See more

Hi Zindi team,We are unable to select the final submission. Can anyone help ??

Hello Everyone, I hope you do enjoy the competition.I'm a bit curious about the correlation between CV (Cross Validation Score) and LB (leaderboard). I hope you... See more

Those who crossed 0.8 LB , which strategy you followed? Deep learning based or Machine learning based?

Where is info for this challenge. @Zindi It was observed that virtually all ongoing challenges on zindi has no information anymore on your platform.

Hello, anyone who finds the image data resolution; the landsat patches to be worrisome? On plotting a few samples, I find that I cannot tell what is in the imag... See more

Hello everyone. I have a question on the submission process: we need to submit the probabilities of the predictions?I have this doubt because inside the competi... See more

I'm using machine learning classifiers as a starter, but not getting accuracy lower or higher than around 0.5. What could be the reason? How to approach the pro... See more

I've created a baseline for the INEGI-GCIM Human Settlement Detection Challenge by ITU You can find the code at mubrij/INEGI-GCIM-Human-Settlement-Detection-Cha... See more

My LB scores seem to be no better than random guesses for NN or GBT models, despite local AUC CV being 0.81 for NN and 0.76 for GBT. Has anyone else experienced... See more

@Amy_Bay and the competition host. After working on this challenge for few minutes, I could see that target file was missing. Kindly provide the target file fo... See more

To echo back this discussion https://zindi.africa/competitions/inegi-gcim-human-settlement-detection-challenge/discussions/22233. The training labels are not pr... See more

I guess I am not able to find the target classAlso the following code is working for loading train data - train_path = "/content/drive/MyDrive/train_data.npy"tr... See more