prs-eth / film-ensemble Goto Github PK

Thank you for the great work. Is it possible to provide the code for your experiments.
I am interested to use it in one of my experiments. Thanks in advance.

--Amit

First of all, this work is fantastic.
Secondly, the paper has not mentioned any experiment using FiLM-Ensemble with different inputs (like point clouds, for example).
I'm currently working on uncertainty estimation in place recognition and I'm using explicit ensemble to do that. With FiLM, I can create an implicit ensemble (actually using PointNet as the backbone and aggregation layer like NetVLAD), but I have a problem with GPU memory overflow.
To my understanding, the problem comes from during the forwarding pass, where there is the repeat_interleave call.
Is this the efficient way to feed the model with CBN layers?
Have you thought about more memory-efficient ways to feed the model?