# Overhead Geopose Challenge **URL:** https://community.drivendata.org/c/overhead-geopose-challenge/44.md [Latest](https://community.drivendata.org/latest.md) · [Categories](https://community.drivendata.org/categories.md) --- ## [About the Overhead Geopose Challenge category](https://community.drivendata.org/t/about-the-overhead-geopose-challenge-category/6130)
**Author:** [@kwetstone](https://community.drivendata.org/u/kwetstone)\ **Replies:** 0\ **Last updated:** [May 14, 2021, 7:24pm UTC](https://community.drivendata.org/t/about-the-overhead-geopose-challenge-category/6130 "2021-05-14T19:24:58Z")
This category is for posts about the Overhead Geopose Challenge competition. Please keep all posts here specific to the competition. --- ## [Results are in!](https://community.drivendata.org/t/results-are-in/6633)
**Author:** [@glipstein](https://community.drivendata.org/u/glipstein)\ **Replies:** 0\ **Last updated:** [October 1, 2021, 5:29pm UTC](https://community.drivendata.org/t/results-are-in/6633 "2021-10-01T17:29:20Z")
Results from the Overhead Geopose Challenge are out! You can find a great summary of the challenge and an introduction to the winners in the results announcement blog post. You can also check out all the winning solutio… --- ## [Question on model write-ups submission](https://community.drivendata.org/t/question-on-model-write-ups-submission/6307)
**Author:** [@hengcherkeng](https://community.drivendata.org/u/hengcherkeng)\ **Replies:** 1\ **Last updated:** [July 20, 2021, 4:17pm UTC](https://community.drivendata.org/t/question-on-model-write-ups-submission/6307 "2021-07-20T16:17:00Z")
A great thanks to the organizer for organizing the challenge. I have a few questions on model write-up submission: For this submission, do we need to upload code for cross-checking? Or only a technical write-up docum… --- ## [Are we allowed to use metadata (gsd and city) as input to model for prediction?](https://community.drivendata.org/t/are-we-allowed-to-use-metadata-gsd-and-city-as-input-to-model-for-prediction/6246)
**Author:** [@hengcherkeng](https://community.drivendata.org/u/hengcherkeng)\ **Replies:** 3\ **Last updated:** [July 12, 2021, 7:21pm UTC](https://community.drivendata.org/t/are-we-allowed-to-use-metadata-gsd-and-city-as-input-to-model-for-prediction/6246 "2021-07-12T19:21:41Z")
in the metadata.csv, we are given metadata (gsd and city) for train and test images. are we allowed to use them at prediction for the test images? (Note: there is almost a direct relationship between gsd and the target… --- ## [FYI: Neural Radiance Fields used in satellite images?](https://community.drivendata.org/t/fyi-neural-radiance-fields-used-in-satellite-images/6264)
**Author:** [@hengcherkeng](https://community.drivendata.org/u/hengcherkeng)\ **Replies:** 0\ **Last updated:** [July 6, 2021, 8:52pm UTC](https://community.drivendata.org/t/fyi-neural-radiance-fields-used-in-satellite-images/6264 "2021-07-06T20:52:19Z")
Shadow Neural Radiance Fields for Earth Observation Researcher Dr. Dawa Derksen from the Advanced Concepts Team explains his Shadow NeRF, a deep architecture able to reconstruct differentiable 3D models fr… --- ## [Any size limitation for a submission file?](https://community.drivendata.org/t/any-size-limitation-for-a-submission-file/6245)
**Author:** [@smly](https://community.drivendata.org/u/smly)\ **Replies:** 2\ **Last updated:** [July 5, 2021, 7:39am UTC](https://community.drivendata.org/t/any-size-limitation-for-a-submission-file/6245 "2021-07-05T07:39:39Z")
All of the submission files should be compressed to one .tar.gz file. Your tar.gz file for submission should be around 1.6 GB. Large tar.gz files will be rejected. When I submit a file larger than 4GB, I get an error … --- ## [Pseudo labeling allowance](https://community.drivendata.org/t/pseudo-labeling-allowance/6213)
**Author:** [@maksimovka](https://community.drivendata.org/u/maksimovka)\ **Replies:** 2\ **Last updated:** [June 28, 2021, 11:12pm UTC](https://community.drivendata.org/t/pseudo-labeling-allowance/6213 "2021-06-28T23:12:02Z")
Is pseudo labeling is allowed, or does it violate the competition rules? --- ## [AWS CLI access forbidden](https://community.drivendata.org/t/aws-cli-access-forbidden/6165)
**Author:** [@aghandour](https://community.drivendata.org/u/aghandour)\ **Replies:** 6\ **Last updated:** [June 28, 2021, 12:38pm UTC](https://community.drivendata.org/t/aws-cli-access-forbidden/6165 "2021-06-28T12:38:31Z")
Hi all, Hi @isms @kwetstone @dinay I am trying to download the dataset via AWS CLI: aws s3 cp s3://drivendata-prod/data/78/public/train\_nano.tar . But I am receiving 403 Forbidden error. Please advise. Ali --- ## [Errors in Google Colab](https://community.drivendata.org/t/errors-in-google-colab/6188)
**Author:** [@JM1000](https://community.drivendata.org/u/JM1000)\ **Replies:** 0\ **Last updated:** [June 18, 2021, 11:26am UTC](https://community.drivendata.org/t/errors-in-google-colab/6188 "2021-06-18T11:26:50Z")
Hi, Has anyone run the benchmark code thro’ google colab? When I run the training block I get the following error (end of text) logged to the training.txt file. I’ve adjusted the file paths accordingly and I’m sure pat… --- ## [Using Pre-trained models](https://community.drivendata.org/t/using-pre-trained-models/6178)
**Author:** [@tetelias](https://community.drivendata.org/u/tetelias)\ **Replies:** 1\ **Last updated:** [June 10, 2021, 4:30pm UTC](https://community.drivendata.org/t/using-pre-trained-models/6178 "2021-06-10T16:30:09Z")
Given prohibition of external data, question is whether pre-trained model weights that are publicly available under permissive license like MIT or Apache can be used in solutions? --- ## [Fastest way to download the geopose\_train.tar.gz](https://community.drivendata.org/t/fastest-way-to-download-the-geopose-train-tar-gz/6168)
**Author:** [@suresh12](https://community.drivendata.org/u/suresh12)\ **Replies:** 0\ **Last updated:** [June 5, 2021, 7:16am UTC](https://community.drivendata.org/t/fastest-way-to-download-the-geopose-train-tar-gz/6168 "2021-06-05T07:16:59Z")
Hi All, There is any way to fastest way of downloading the Geopose challenge data . I tried with google colab and I was download the train images file , but store is less . --- ## [Large file size makes it difficult to upload](https://community.drivendata.org/t/large-file-size-makes-it-difficult-to-upload/6161)
**Author:** [@chuchu](https://community.drivendata.org/u/chuchu)\ **Replies:** 1\ **Last updated:** [May 29, 2021, 2:29pm UTC](https://community.drivendata.org/t/large-file-size-makes-it-difficult-to-upload/6161 "2021-05-29T14:29:48Z")
My submission file is nearly 1.79 GB. It always meets network error. How do I reduce file size further?