Rozenberszki Dávid
Rozenberszki Dávid
Hey @chrischoy, First of all thank you for this work and all the effort. As a kind reminder do you have an estimate if the CUSTOM kernels will be implemented?...
Hey @HuitongJin, Every necessary step for our final results are detailed in this repo. Also, others were able to reproduce our results already, but it is still possible that local...
Hey, A couple of questions to clarify what might be going wrong: - Can you provide your train logs so I could check if something is off there? - What...
Hi, interesting, after the first check your parameters are looking alright and it seems you are also loading the pretrained weights. Could you try finetuning from the weights that we...
Right, but thats expected at this point. I see from your logs, that you are using the standard CE losses, instead of our class balanced focal loss. Our results were...
Not yet :/
I think you are having problems with pykdtree structs and recent pytorch version incompatibility. This answer helped me solve the problem: https://github.com/autonomousvision/differentiable_volumetric_rendering/issues/46#issuecomment-869823496
Hey @cugcsu, I am having the same error with the same device. Can you help me how you solved the problem?
Hey @zhang-zihui, We treated every instance category and a combined foreground class, so we haven't computed per class performance. On the other hand, I do agree this is a pretty...
Hey @oscarlorente, Sadly, I don't have the bandwidth right now to create an interactive demo, maybe ina. couple months I will be able to get to it. In the meantime,...