Fronk Supakorn comments

Repositories
Issues
Comments

Results 3 comments of


                                            Fronk Supakorn

readtext fails when specifying a GPU other than cuda:0

I think the problem occurred because when initializing the model, `torch.nn.DataParallel` is used with the default `device_ids` value. So, even if you declare the `gpu="cuda:3"`, the default device_ids is still...

did you put the invert(from white bg & black line) preprocessor?

I got the same question regarding the lineart and linart_anime preprocessors. I'm curious about why we need to invert the black and white colors in the last step, where the...

VRAM needed for 512x512 unpaired training

> You can see [this PR](https://github.com/GaParmar/img2img-turbo/pull/30) to reduce the VRAM required with mixed precision training. I trained my unpaired models on A6000, which has 48GB VRAM. > > -Gaurav @GaParmar...