As described in the issue I opened, I get the following error when running the Pytorch inverse-cooking model on CPU:
RuntimeError: expected device cpu and dtype Byte but got device cpu and dtype Bool
I have tried running the demo.ipynb file in both my laptop's Intel i7-4700HQ 8 threads and my desktop Ryzen 3700x. I was using Arch Linux on my laptop and Manjaro on my desktop.
The model works fine when I run it on Google Collabs GPU.
According to the demo.ipynb file the model should be able to run on CPU as well. Does anyone know if I have to tweak any parameters in order to make it work?
