PyTorch-BayesianCNN icon indicating copy to clipboard operation
PyTorch-BayesianCNN copied to clipboard

GPU Memory usage

Open Neronjust2017 opened this issue 3 years ago • 0 comments

Hi, thanks for your great work! I wonder if the GPU memory usage will grow linearly with the parameter "num_ens" in the code? If I increase "num_ens", there will be an OOM error definitely, right? Maybe it's better to implement the MC sampling process in the "forward" function of the "BBBConv" and "BBBLinear" to avoid this issue.

Neronjust2017 avatar Jun 05 '22 04:06 Neronjust2017