Xinglei Wang

Hi I was trying to use the method as the ArcGIS tool. I did everything step by step just as told. Having successfully installed GDAL-2.2.3win32 and networkx-2.1. But when I...

Hi, razvanc92 The reason that this inconsistency occurred is that I only implemented the "filter_type=laplacian" case, while the original implementation has considered all three different cases: "laplacian", "random_walk", "dual_random_walk". In...

Hi, @razvanc92 I have modified the code. Now, when testing with the METR-LA dataset, the model produces exactly the same amount of parameters as the original implementation does.

Hi seifer, Thanks for pointing this issue out. This is a mistake, "null_val=0" should be specified during evaluation process. I will correct it.

Hi Marc, Thank you for your prompt response. I tested adding a line of code to the [forward function of grid_and_sphere.py](https://github.com/MarcCoru/locationencoder/blob/685892ee1f9945d368b2dbfbb153dc1f9813f8bd/locationencoder/pe/grid_and_sphere.py#L120) and run "grid+fcnet" and "grid+siren" on the land ocean...