Is it possible to reduce GPU memory usage during inference?

slp-rl / aero

This repo contains the official PyTorch implementation of "Audio Super Resolution in the Spectral Domain" (ICASSP 2023)

MIT License

190 stars 24 forks source link

Open tshmak opened 8 months ago

tshmak commented 8 months ago

It appears it is taking >30GB of memory for inference. What are the parameters I can set which can reduce the demand?

Thanks!