Pytorch example of Faster R-CNN for CPU

Hi all,
I’m quite new to Pytorch and i’d like to find an example of Faster R-CNN that can run on a simple CPU. I’ve found several examples in GitHub but i don’t know if running them on a CPU will be very complicated. Has anyone tried? Any kind of guide would be appreciated.
Thanks in advance for your help!!

Just get rid of all .cuda() calls and run the script. This prevents moving the model or tensors onto a GPU.
Often there are optional arguments for the main script where you can specify using a GPU or not.

EDIT: This code uses an argument for GPU usage. (Haven’t tried it myself)

1 Like

Thanks @ptrblck !! This is the kind of help that i needed. i will try and came back to edit the post