Matthew Tancik
Matthew Tancik
Closing as this appear stale, feel free to reopen if it is still and issue.
Some users have reported issues using TCNN with visual studio 2022. People have had better luck with the 2019 version.
Closing. Feel free to reopen if needed.
There isn't currently a prebuilt method to do this, but it should be possible by subclassing the dataloader with a custom one.
Take a look at https://github.com/javieryu/nsros_bridge for an example.
Closing, feel free to reopen if it is still and issue.
`tcnn` is used everywhere since it is much faster. At some point I think we should dig into the pytorch implementation to 1. confirm it is accurate, and 2. see...
Yes, that is indeed the purpose of the class. The issue is that when using an MLP + Hashgrid, it is fastest to use `tcnn.NetworkWithInputEncoding` then `tcnn.Encoding` followed by `tcnn.Network`....
Fixed
Closing as it appears to be stale. Feel free to reopen if needed.