-
```
from argparse import Namespace
from models.psp import pSp
import torch.nn as nn
import torch
import onnx
#Function to Convert to ONNX
def Convert_ONNX():
device = "cuda" if torch.c…
-
Some time ago I found this awesome package called [Barbershop](https://github.com/ZPdesu/Barbershop). Unfortunately I am unable to get it working, or find anyone who actually got this thing working.
…
-
Hi lucidrains,
Many thanks for your work about stylegan2-pytorch!
I'm trying to apply stylegan2 on image debluring task(GoPro dataset), is there any clue for the structure of dataset directory?…
-
我用原始的10w+张网红数据集，基于style2官方源码训练框架，不管是在stylegan2-ffhq-config-f.pkl或者generator_wanghong-stylegan2-config-f.pkl模型上refine，很快清晰度就会下降，面部的立体感、发丝很明显不如generator_wanghong-stylegan2-config-f.pkl的效果，也调了下参数，感觉还是难以复…
-
I encountered the following error when trying `interactive.py` with a conda installation following the readme.
```
"...\models\stylegan2\stylegan2-pytorch\model.py", line 273, in forward
o…
ghost updated
2 years ago
-
Thanks for your great project!
I meet with a problem when running this command:
`python generate.py --ckpt ./checkpoint/550000.pt`
the detailed errors as follow:
`Traceback (most recent call l…
-
python main.py --input_dir ./ffhq_image/ --im_path1 source.png --im_path2 target.png \
After putting this line i get this message
C:\Users\mertk\anaconda3\envs\test\lib\site-packages\torch\utils\cp…
-
I try to train the network but there is something wrong.
Traceback (most recent call last):
File "/home/ff/ZHL/stylegan2-based-face-frontalization-main/train.py", line 29, in
from model impo…
-
Environment:
Anaconda & Python3.7
CUDA 11.2 & cudnn 8.0.5
torch-gpu 1.7.1 & torchvision 0.8.2
When I run the training command
stylegan2_pytorch --data images/128a --image-size 128 --num-trai…
-
Just tried to train a model with a 3.5K-face dataset but it seems strange.
My command was this:
`unet_stylegan2 --batch_size 4 --network_capacity 32 --gradient_accumulate_every 8 --aug_prob 0.25 --a…