# Segmenting Buildings for Disaster Resilience **URL:** https://community.drivendata.org/c/segmenting-building-footprints/31.md [Latest](https://community.drivendata.org/latest.md) · [Categories](https://community.drivendata.org/categories.md) --- ## [About the Segmenting Buildings for Disaster Resilience category](https://community.drivendata.org/t/about-the-segmenting-buildings-for-disaster-resilience-category/3998)
**Author:** [@emily](https://community.drivendata.org/u/emily)\ **Replies:** 0
This category is for posts about the Open Cities AI Challenge: Segmenting Buildings for Disaster Resilience competition. Please keep all posts here specific to the competition. --- ## [Test data spatial resolution](https://community.drivendata.org/t/test-data-spatial-resolution/7661)
**Author:** [@Damjanh](https://community.drivendata.org/u/Damjanh)\ **Replies:** 1\ **Last updated:** [April 29, 2022, 10:41pm UTC](https://community.drivendata.org/t/test-data-spatial-resolution/7661 "2022-04-29T22:41:38Z")
@johnowhitaker @Agedev As mentioned in the problem description, the images in the test set have been generated without valid georeferencing. “The correct georeferences for the test chips have been removed”. I am doing… --- ## [Release of Test dataset labels](https://community.drivendata.org/t/release-of-test-dataset-labels/4391)
**Author:** [@aghandour](https://community.drivendata.org/u/aghandour)\ **Replies:** 0\ **Last updated:** [May 4, 2020, 10:57am UTC](https://community.drivendata.org/t/release-of-test-dataset-labels/4391 "2020-05-04T10:57:28Z")
Hi @daveluo\_gfdrr Hi @bull, Thanks for organizing this nice competition. Are you planing to release the test dataset labels soon? Also, I am wondering how the private score got computed? Ali @Hasan\_N --- ## [Winners and winning methods](https://community.drivendata.org/t/winners-and-winning-methods/4326)
**Author:** [@chrisjames](https://community.drivendata.org/u/chrisjames)\ **Replies:** 0\ **Last updated:** [March 24, 2020, 11:22am UTC](https://community.drivendata.org/t/winners-and-winning-methods/4326 "2020-03-24T11:22:34Z")
Sorry if I’m jumping the gun, but are you going to share the methods of the winners (I see one has already made a GitHub repo available) and the winning responsible AI submissions? Keen to see what people came up with! (… --- ## [Submission close](https://community.drivendata.org/t/submission-close/4304)
**Author:** [@Agedev](https://community.drivendata.org/u/Agedev)\ **Replies:** 3\ **Last updated:** [March 17, 2020, 3:54am UTC](https://community.drivendata.org/t/submission-close/4304 "2020-03-17T03:54:16Z")
On the main page, the following is stated: March 16, 2020, midnight UTC Submissions close. I presume this means UTC 24:00:00 on Match 16th However as at 03:15:06 UTC Sunday, 15 March 2020 on the same page it is sayi… --- ## [Responsible AI Track dedicated thread](https://community.drivendata.org/t/responsible-ai-track-dedicated-thread/4009)
**Author:** [@daveluo\_gfdrr](https://community.drivendata.org/u/daveluo_gfdrr)\ **Replies:** 3\ **Last updated:** [March 13, 2020, 9:45pm UTC](https://community.drivendata.org/t/responsible-ai-track-dedicated-thread/4009 "2020-03-13T21:45:35Z")
Hi all, I’m Dave from GFDRR Labs and one of the challenge organizers. We’re excited to have this competition, especially with this Responsible AI track with $3K in prizes for your best ideas exploring the appropriate de… --- ## [Submission Error](https://community.drivendata.org/t/submission-error/4278)
**Author:** [@rpartsey](https://community.drivendata.org/u/rpartsey)\ **Replies:** 2\ **Last updated:** [March 4, 2020, 8:45pm UTC](https://community.drivendata.org/t/submission-error/4278 "2020-03-04T20:45:44Z")
Hi, guys could you please help me to figure out the cause of this error. It doesn’t make sense to me, but it used one of my 3 submissions. Thanks in advance. --- ## [Submission format](https://community.drivendata.org/t/submission-format/4027)
**Author:** [@johnowhitaker](https://community.drivendata.org/u/johnowhitaker)\ **Replies:** 11\ **Last updated:** [March 3, 2020, 4:11pm UTC](https://community.drivendata.org/t/submission-format/4027 "2020-03-03T16:11:26Z")
Question re: required format for submission. I’m saving my predictions as tiff images, 1024px a side, single band (shape = 1024x1024), max value 1, min 0, no floats. dtype int32 (tried using PIL im.save and imageio save… --- ## [Submit to the Responsible AI track to be eligible for prizes](https://community.drivendata.org/t/submit-to-the-responsible-ai-track-to-be-eligible-for-prizes/4270)
**Author:** [@emily](https://community.drivendata.org/u/emily)\ **Replies:** 0\ **Last updated:** [March 2, 2020, 6:40pm UTC](https://community.drivendata.org/t/submit-to-the-responsible-ai-track-to-be-eligible-for-prizes/4270 "2020-03-02T18:40:33Z")
Friendly reminder! Segmentation track participants must also submit at least once to the Responsible AI track to qualify for the $12,000 in cash prizes. Visit the Responsible AI description and discussion forum thread to… --- ## [Official pre-trained models / external data thread](https://community.drivendata.org/t/official-pre-trained-models-external-data-thread/4003)
**Author:** [@glipstein](https://community.drivendata.org/u/glipstein)\ **Replies:** 15\ **Last updated:** [March 2, 2020, 6:25pm UTC](https://community.drivendata.org/t/official-pre-trained-models-external-data-thread/4003 "2020-03-02T18:25:11Z")
Pre-trained models and external data are allowed in this competition as long as they can be released under an Open Source License. We want to build on the best of what’s available. If you do use a pre-trained model or ex… --- ## [Metric Calculation](https://community.drivendata.org/t/metric-calculation/4258)
**Author:** [@bonlime](https://community.drivendata.org/u/bonlime)\ **Replies:** 3\ **Last updated:** [March 2, 2020, 4:18pm UTC](https://community.drivendata.org/t/metric-calculation/4258 "2020-03-02T16:18:56Z")
How is the IoU for this competition is calculated exactly? I have pretty diverse local validation data but the local score still doesn’t correlate much with the Leader Board. Do you calculate it per image and average or… --- ## [Getting Started](https://community.drivendata.org/t/getting-started/4022)
**Author:** [@johnowhitaker](https://community.drivendata.org/u/johnowhitaker)\ **Replies:** 32\ **Last updated:** [February 26, 2020, 9:39am UTC](https://community.drivendata.org/t/getting-started/4022 "2020-02-26T09:39:39Z")
Hello all, I figured it would be useful to collate some ‘getting started’ info and tips. I’ll be documenting how to do an entry from start to finish, and as I go I’ll keep posting things here. If anyone else has resourc… --- ## [Lat/long to Pixel transformation](https://community.drivendata.org/t/lat-long-to-pixel-transformation/4209)
**Author:** [@aghandour](https://community.drivendata.org/u/aghandour)\ **Replies:** 2\ **Last updated:** [February 18, 2020, 6:55am UTC](https://community.drivendata.org/t/lat-long-to-pixel-transformation/4209 "2020-02-18T06:55:37Z")
Hi @daveluo\_gfdrr, Hi @emily, Hi all, I am wondering how to transform the lat/long coordinates of a specific building polygon into pixel coordinates relative to the top left corner of a tiled window. Ali --- ## [Geo-reference metada](https://community.drivendata.org/t/geo-reference-metada/4210)
**Author:** [@aghandour](https://community.drivendata.org/u/aghandour)\ **Replies:** 2\ **Last updated:** [February 18, 2020, 6:55am UTC](https://community.drivendata.org/t/geo-reference-metada/4210 "2020-02-18T06:55:11Z")
Hi @daveluo\_gfdrr, Hi @emily, Hi all, I am wondering how to embed the new geo-referencing metadata with along a tiled window. Ali --- ## [Browse challenge data online with STAC Browser](https://community.drivendata.org/t/browse-challenge-data-online-with-stac-browser/4011)
**Author:** [@daveluo\_gfdrr](https://community.drivendata.org/u/daveluo_gfdrr)\ **Replies:** 0\ **Last updated:** [December 19, 2019, 7:30pm UTC](https://community.drivendata.org/t/browse-challenge-data-online-with-stac-browser/4011 "2019-12-19T19:30:10Z")
Hi all, To make the Open Cities AI Challenge training datasets more accessible, especially to participants with less geospatial data experience or internet bandwidth limitations, we’ve created a customized STAC Browser …