Mukund
Hey, is there any workaround for this? Restarting tensorboard does work but it's quite a hassle if I am running something on a remote server.
Hey @warner, I thought I could try patching this. However, what I noticed is that the message is different when run from a local machine vs when run from a...
Apologies for the delayed response. Nerf Synthetic images contain 4 channels, the last indicating occupancy of an object in the scene (or simply put a mask of the object). Hence...
@AllenXiangX Thank you for your prompt response. This is actually quite surprising in the sense a model that would obtain around 19x10^-4 would achieve close to 7x10^-4 on the test...
Any solution for this? is the GT test set made publicly available anywhere?
@aswinkumar1999 This would be a wonderful feature. I am not sure if this is done or not! But I did come across a python package called inquirer which basically gives...
I am not sure but how do we ensure that the user has packages required to run the python setup scripts. Like in the above case, how will a user...
Sure count me in. Let me know how I can help. Just one additional thing, maybe we can try to use python for displaying the terminal outputs. Cause as far...
Hi @ds22058, thank you for your interest in our work! and apologies for the delay in our response. The released checkpoints were trained from a private codebase, which I cleaned...
Apologies for the (super) delayed response. Yes, I have also observed that GNT seems to be sensitive to the depth range and can't especially handle scenes where the ranges are...