search

soumith / ganhacks

starter from "How to Train a GAN?" at NIPS2016
11.42k stars 1.66k forks source link

Have you try more deeper networks? #6

Open zhangqianhui opened 7 years ago

zhangqianhui commented 7 years ago

Hello , Soumith As we all know , vgg , inception , resnet , this networks are very deep And Have you tried deeper networks to contruct the gans? For example Using reset in D networks.

soumith commented 7 years ago

We've used existing VGG networks in our workshop paper "Semantic Segmentation using Adversarial Networks", because it was a fine-tuning task rather than generation from scratch.

zhangqianhui commented 7 years ago

@soumith thanks for your answer , but when to open the code ?

soumith commented 7 years ago

i dont know yet.

zhangqianhui commented 7 years ago

@soumith

https://github.com/imatge-upc/saliency-salgan-2017

use vgg in Generative networks