yxt132
yxt132
Well done! It seems the pytorch version's results are smoother than the official tf version. What changes did you make in the pytorch version? I acutally like the pytorch version's...
the author said you could train without guided filter and add guided filter during inference.
that's good to know! Looking forward to it.
> Good news! We will release the datasets soon!! Any update on expected release date? Thanks!
The file link doesn't work. Can you please check?
> anything from alibaba has about a 35-40% chance of being released. I am not holding my breath
> Apparently tts was published, but the given example puts out the error: audioldm2: error: unrecognized arguments: --transciption ... I got the same error
Similar problem here. I am using 4-channel image and get an error message: ValueError: Trying to share variable generator_A/conv/conv2d/kernel, but specified shape (7, 7, 3, 64) and found shape (7,...
+1
Also want to know. Thanks for the author's innovative work.