Running Inference on Models #13
Description
Hi everyone,
I am trying to run inference on the models you published, but I am always getting almost 0 probability everywhere. I am not sure what exactly the problem is, but my best guess is that the values that I fit into the model are different from what the model expects. I tried to follow exactly the steps that you described in the readme and in the paper, but I am not sure if I got them correctly. Especially the normalization is something I am struggling a lot, as I do not know if you normalized all values to [0, 1] and if yes, what are the scaling values you used.
I copy pasted my earth engine script for downloading data and my inference script.
Could you pinpoint me what I am doing wrong? Or maybe provide scaling values (means and variances or min and max) that you used for normalization during training? Or put some examples how to run inference given the date and a polygon? I know that you have published the probability maps for 2020 & 2023 for some countries, but I want to run the model on other years and countries.