engharat

I'm trying both using unmodified 2048 features or applying a bottleneck FC layer, as well as reducing images to 64x64 for the discriminator, but in all cases the GAN does...

Very thanks for your fast reply and support - I see how the system could perform good D.A. even if produced images are not realistic, but my trials to let...

I'm trying to modify the code for theano backend as you, but I encounter several obstacles. jf003320018 did you manage to convert the code? It is not ( or not...

I managed to fix it by replacing scikit-tensor-py3 calls with tensotly calls. The example works fine now, and I avoided also an ugly numpy&scipy downgrade, which was required by scikit-tensor-py3....

are those pretrained weights obtained by training on ImageNet?

Szagorukyo could you provide the network structure you are using for training on imagenet? What is the depth and width used on that case?

I tried to alternate D(positive) and D(negative) with G training, and the resulting Gan is wildly oscillating. I got good results by training D(positive) and D(negative) each time before G...

I face this issue too, latest version of Ryujinx and Steam Deck hardware. I partially solved by creating a script that moves away the poke_trade and the backup files which...

@revilokeb I would be interested into the train_val / solver you are using on imagenet! Plus, and advice on how big should I set the convolutions if testing on imagenet...

The error does not decrease, but I have built it choosing myself the convolutions sizes. I would like to explore the same. Anyway, didn't you find suspicious the fact that...