Topaz denoising

Particle Picking
1

When I run the topaz denoiser job, I get the following error in cryosparc 3.1:
RuntimeError: CUDA out of memory. Tried to allocate 360.00 MiB (GPU 2; 15.90 GiB total capacity; 364.22 MiB already allocated; 363.38 MiB free; 366.00 MiB reserved in total by PyTorch).

I tried decreasing Shape of split micrographs but no success. I am assuming that it’s happening because of the size of the micrographs. What are the other parameters that can be tuned to make it work?

2

Hi @tushancse, are you running any other programs/applications on the same GPU or node? These may be contributing to the lack of available memory.