Jannik Zürn

Thank you very much for your efforts in providing MADRaS. Are there any updates regarding the raw pixel observation availability?

I had the same error. You need to use a Python version >3.8

Try to decrease the size of the model (number of neurons per layer) `m = model.Model([100,00],[100,50], dropout=0.5)` worked for me, while with `m = model.Model([300,00],[100,50], dropout=0.5)` I got the same...

Hi @gchhablani, Is this feature still available? I am also interested in using `torch` and `torchmetrics` inside a worker but had no luck installing them using the `evaluation_script/__init__.py` method that...

Thank you very much for your amazing work! I was also wondering about the sensitivity of the approach w.r.t the density and and accuracy of the depth supervision source, thus,...

After integrating monodepth depth supervision into the model, I can confirm that this alternative to LiDAR depth supervision works pretty well indeed.