Why isn't the MLPTexture3D using the tcnn Network definition about nvdiffrec HOT 2 CLOSED

Hello @ktertikas,

We used a standard float32 MLP mostly for compatibility reasons so that the code was running on more servers.
If you want to run the encoder + MLP in tcnn in float16 there may be some gradient scaling issues to consider.

Please refer to the tcnn code base to see the recommended gradient scaling approach for that use case. Note also that we currently scale the gradients for the encoder, which may need to be removed/adapted in case you run everything through tcnn.

For a general overview of gradient scaling and some best practices, please refer to
https://docs.nvidia.com/deeplearning/performance/mixed-precision-training/index.html

from nvdiffrec.

Thank you for the immediate response @jmunkberg ! I have played around with gradient scaling a bit, but maybe it needs to be done in a more principled way. In any case thank you for the reference link!

from nvdiffrec.