Soumya Ranjan Mohanty

@rbavery I was able to reproduce the test errors locally. The array values are different for tiles in - tests/data/rastertile_test_fill_nodata_expected/ - tests/data/rastertile_test_fill_nodata_result/ Visually they look similar but array values are...

@fnattino Did you set up a `~/.netrc` file to access NASA CMR STAC data? You can sign-up [here](https://urs.earthdata.nasa.gov/) & run this [script](https://git.earthdata.nasa.gov/projects/LPDUR/repos/daac_data_download_python/browse/EarthdataLoginSetup.py) to set things up.

@rbavery I had my fair share of trouble trying to access NASA CMR STAC and tried multiple things. I guess I found this from one of the tutorials: https://nasa-openscapes.github.io/2021-Cloud-Workshop-AGU/how-tos/Earthdata_Cloud__Single_File__HTTPS_Access_COG_Example.html

@stas00 Thank you for maintaining the ML-engineering guide! I noticed that [you recommend setting --ntasks-per-node=1](https://github.com/stas00/ml-engineering/blob/0ed96ca4fdfd2dc35b96a94a3386f8b4794888c1/orchestration/slurm/launchers/lightning-launcher.slurm#L8), whereas the [Lightning documentation suggests --ntasks-per-node=8](https://lightning.ai/docs/fabric/stable/guide/multi_node/slurm.html) (which corresponds to the number of GPUs per node)....

Addressed in PR #193

Good article on normalizing EO imagery: https://medium.com/sentinel-hub/how-to-normalize-satellite-images-for-deep-learning-d5b668c885af Another option to consider, use BatchNorm as a way to learn normalized weights for each band in the imagery,

@weiji14 I suggest we continue the discussion on the other thread.

@TaniaJG We conducted a [pixel-wise regression for ABG](https://clay-foundation.github.io/model/finetune/regression.html), and the details are available in the CLAY documentation. We didn’t observe any checkerboard patterns during this process, but the results do...

Update: We are conducting another model run for CLAY with the following updates: - Added MODIS to the list of sensors. #311 - Implemented [MRL](https://arxiv.org/abs/2205.13147) on CLAY embeddings. - Introduced...

Thank you, @anindabitm, for the well-formatted and clean notebook. Before we proceed with merging the pull request, here are a few additions I recommend: - Please include a brief description...