huan ling

as stated in README. To reproduce numbers in the paper you need at least 8 GPUs. I would recommend you try at least 8 * 16GB (I reproduce numbers by...

> @shifangtian You can follow my repo https://github.com/HAOCHENYE/GSCNN-for-Single-GPU > This net is very hard to training on single GPU,my mean iou only reached 0.4084 WiderResNet38 can't be trained on single...

If you want to use 16G GPU memory V100, there are also multiple tricks to reduce memory usage. For example, you can consider reducing stylegan model size to 256* 256...

It's out of the scope of the current research project however It's definitely doable! I don't have a RTX-GPU set up in our research environment. Let me know if you...

Hi. stylegan2-pytorch codebase from rosinality gives a nice example! https://github.com/rosinality/stylegan2-pytorch/blob/master/convert_weight.py

You need to draw a box on your uploaded image.

backend starts well. Can you show your frontend logs? Using Inspect of google Chrome

are you on linux?

what's the path where you run frontend from?

Demo js is at [static/demo_origin.js](https://github.com/nv-tlabs/editGAN_release/blob/release_final/static/demo_origin.js) Could you please also let me know how it's going on google Colab? Would like to help and update the Colab option in released code...