07hyx06

I got the same bad result.....Do you solve it?

> no..... > […](#) > On Wed, Jan 1, 2020 at 6:24 PM Yuxuan Han ***@***.***> wrote: I got the same bad result.....Do you solve it? — You are receiving...

> Disable this line. > > ``` > model = model.eval() > ``` > > It works for me. Hi! What about your generated image quality?I got very ugly outputs...

Got it. Thanks for your kind reply! Another question is, in EVALUATION.md I notice that when evaluate on KITTI, the argument absolute_depth is specified and the prediction is scaled by...

@ranftlr @AlexeyAB Thanks for your help!

Hi! I did some experiments on the [flower dataset](https://drive.google.com/drive/folders/14boI-o5hGO9srnWaaogTU5_ji7wkX2S7) these days. Can you give me some help to improve the alignment result? I run COLMAP with the default configuration to...

In my device, it needs about 3616MB of Cuda memory to run the demo.

You can open the UGATIT.py then add "with torch.no_grad()" before "step%print_freq"!

> Hi @gwern! > Thank you for referring the pretrained models. We will do our best to add it (yet in a few weeks, probably, after the 5 of March)....

I mean this [dataset](https://github.com/makegirlsmoe/makegirlsmoe_web) The author trained SnGAN on this dataset in the paper, i also prepare to train a SnGAN on it, but i find this dataset doesn't release....