search

sentinel-hub / cv4a-iclr-2020-starter-notebooks

Starter notebooks using eo-learn for the CV4A workshop at ICLR 2020
6 stars 4 forks source link

Data availability #5

Closed daisy12321 closed 1 year ago

daisy12321 commented 1 year ago

I am hoping to replicate the experiment from https://github.com/sentinel-hub/cv4a-iclr-2020-starter-notebooks/blob/master/experiments/intercropping.ipynb

Specifically, it references some prepared data from MLHub: NP_DATA_PATH = '/mnt/azrael/spatialdata/projects/eo_data/iclr-2020-challange/mlhub/prepared_data/original_data.npz'

I can download the raw data from the challenge on the MLHub website, but can't find the prepared ones, or the script that was used to generate them. Could you point me to them if they are available?

batic commented 1 year ago

Hi @daisy12321 ,

We don't have the data any longer, but with some luck you should be able to recreate it.

If I am not mistaken (that code has been prepared and used quite some time ago), the numpy arrays you are after were prepared in the https://github.com/sentinel-hub/cv4a-iclr-2020-starter-notebooks/blob/338cdcfa8c342600ef0d2bd4e10c7aa04c6bdd14/cv4a-process-and-train.ipynb. If you see cell 20, it creates features, field_id and crop_id.

Hope that helps.

daisy12321 commented 1 year ago

Thank you so much for the prompt answer!