(Help) TFJS on GPU: Trying to Compare the performance of TFJS-node and TFJS-node-GPU

Hi,

Tried to use an NVIDIA GeForce RTX 1080Ti GPU PC Card to work with TFJS and followed the hardware and software requirements as stated in the documentation but were unable to see a drastic difference in performance yet.

I am unsure if I’m following the correct guidelines as the above documentation seems like it’s for Tensorflow Python.

Do I need to do some more settings for using the GPU version TensorFlow.js node?

Please let me know!

Thanks.

you don’t need more settings, you need to check if gpu is being utilized at all as tfjs-node-gpu has auto-fallback if it cannot initialize cuda correctly which means it then runs exactly as tfjs-node.

and default logging level is typically sufficient - when you start your app, what does it say?