voa18105
voa18105
@ESanchezLozano thank you for a detailed response. Yes, of course, I see your point, as well as I see that the generated image look somehow like me. But looking like...
@yyssmm did you succeed with this? Does it work?
@Sampson-Lee did you overcome this problem? I have a same one now, it generates faces itself and changes their emotions
@RegisWu did you find out? 1.2? 1.8 obvisously does not work, I've started re-writing functions with old syntax, but at some point i've stucked completely...
@13293824182 Yes, I've managed to pass the quest of repeating original train/test completely and I can tell you its a waste of time.
@13293824182 I use 1.8, but I had to edit codes to adapt something... I don't remember already. What I do remember is that this code overfits badly with the dataset....
Hello! Actually, there is a same issue with "per sample" - no alpha given
hi guys, so, how to overpass this issue? I've tried different versions of pytorch, but still have "ValueError: expected 2D or 3D input (got 4D input)"
> Hi, @jagjeet-singh > > Thanks for sharing the baseline code. I'm trying to train the LSTM Social model and evaluate on the validation set. > The results of LSTM...
@rosinality @aparafita guys, am I correct that this before/after changes do not require retrain? Feels like this impacts only inference