Jhin

How can I get 2d expression transfer results

2

Which render method should I choose to get 2d image based on your expression transfer result

import torch

Should I resize an image from other dataset to 128*128 when I test this model ?

pytorch version

2

Hi, what is the PyTorch version of this code? 0.4.0, 0.4.1 or >=1.0 ? thanks

What's the version of pytorch and tensorflow ? And python ?

Cannot reproduce the results of speedup

4

I implemented a script to test the acceleration by myself and tested it on 3090GPU, but it could not achieve the acceleration effect of Table 4 in the paper. ```...

Hi, thanks for releasing this nice project. Some of the code ([L58](https://github.com/csxmli2016/textbsr/blob/1e5b82092ae2bbc363d7e26a2f9f01cc19a9010d/textbsr/models/TextEnhancement.py#L58C7-L58C7) ~ [L85](https://github.com/csxmli2016/textbsr/blob/1e5b82092ae2bbc363d7e26a2f9f01cc19a9010d/textbsr/models/TextEnhancement.py#L85) from TextEnhancement.py) was hard for me to understand. Could you explain what `move_w, move_h, ref_point` are...

Hi, Thanks for sharing this nice work! I have some questions about training details of VQGAN on ImageNet. - How many epochs should I train? - How many GPUs are...

Code

1

Nice work! When release the code?