Carlos Gomes

Hi @Ni-vik and @JulsdL . I am trying to replicate the error, but am not being able to. My first hunch would be to make sure you ran `pip install...

It seems you are running this on windows. I would suggest trying it from windows subsystem for Linux. https://learn.microsoft.com/en-us/windows/wsl/install Windows tends to make things a bit messier with these libraries......

For running on CPU, it is sufficient to install the CPU version of torch and the matching version of mmcv-full. For running on GPU, you should have the appropriate drivers...

Hi, This issue becomes critical if one wants to use aim together with LightningCLI. LightningCLI rejects the current Aim Logger as it is not a subclass of classes from the...

Hi @aleksmirosh . This is somewhat confusing to me, as the predictions should be either 0 or 1 for each pixel, so completely dark or completely white, So I suspect...

@mxyqsh could you provide more details of what you executed to obtain that image? At a first glance, it seems like that channels are somehow stacked in the spatial dimension....

Indeed, for running on CPU I merged a new PR that should fix this. You should be able to pull again from main and this should be fixed.

Hi, I am not sure what directory you are referring to. The Readme provides example commands to run fine-tuning on any of the 3 provided examples in the configs folder....

Thank you @aTnT for the mapping to S2 data. That is indeed the mapping to adopt. The input should be a stacked Tiff file where each channel corresponds to a...

Hi, could you please provide a bit more information on what you are trying to run? E.g. the config file, the splits (if you are using any) and the structure...