Geethen Singh

I have the same question I have currently setup the arch like so model = smp.Unet( encoder_name="resnet18", # choose encoder, e.g. mobilenet_v2 or efficientnet-b7 encoder_weights= None, # use `imagenet` pre-trained...

> This seems like 2 separate problems. > 1. Dealing with sampling from imbalanced datasets This is the broader problem. One of the ways I would approach this would be...

@StatMixedML Thank you very much- this seems very useful. I will give it a test drive. @alejandroschuler - I was interested in NGBoost because it has been significantly outperforming LightGBM,...

2020 SANLC (geographic): ee.Image("projects/ee-geethensingh/assets/SANLC_2020") https://sfiler.environment.gov.za:8443/ssf/s/readFile/folderEntry/40906/8afbc1c77a484088017a4e8a1abd0052/1624802570000/last/SA_NLC_2020_Geographic.tif.vat.zip 2013 SANLC (geographic): ee.Image("users/geethensingh/SANLC__2013_14") https://sfiler.environment.gov.za:8443/ssf/s/readFile/folderEntry/19341/8afbc1c75aea91ba015bd35f2c0b51b2/1462800851000/last/SALandCover_ReprojectedGEO_2013_GTI_72Classes.zip 1990 SANLC (geographic): ee.Image("projects/ee-geethensingh/assets/SANLC_1990") https://sfiler.environment.gov.za:8443/ssf/s/readFile/folderEntry/14/8afbc1c7547f664c01552a6addf000ea/1462800349000/last/SALandCover_ReprojectedGEO84_1990_GTI_72Classes.zip

I have shared the dataset. Apologies for that. Although I see you uploaded it to the project. thanks. Users should note that there have been changes to the classification nomenclature...

Hi Sam, They all contain the same type of data/information just for different regions of the world. Ideally, This would be a single image collection. Specifically, each image contains the...

This would be a great addition. the example in the gist requires the image data (used for inference) to fit into memory. rasterio allows [windowed writing](https://rasterio.readthedocs.io/en/stable/topics/windowed-rw.html) and accommodates larger than...

Yes, thats correct. LGBMTuner within verstack dataset size: 1.3Gb when stored as a feather with shape roughly 450 000 rows and 707 columns. Task type: regression

I'm working with spatial data, so I use groupkfold to limit spatial autocorrelation. Hence my request. Thanks for looking more into this. I think having a tuner that can take...