-
I was trying to train the stem when I ran into this issue
```
Constructing networks...
loaded imagenet embeddings from in_embeddings/tf_efficientnet_lite0.pkl: Embedding(1000, 320)
Setting up PyT…
-
'pretrained_models/shape_predictor_68_face_landmarks.dat' file exists in the path. What's the problem?
`!python prepare_data/preparing_faces_parallel.py \
--root_path /content/drive/MyDrive/Datase…
-
-
Resuming training using 256x256 network couse error. It didn't happen on different sizes of network.
```
Resuming from "C:\Users\user_x\Downloads\stylegan3-r-ffhqu-256x256.pkl"
Traceback (most re…
-
Thank you so much for sharing your artistic model to the community. I'm a media art student new to machine learning. I'm currently apply your 'yellow comic alien 004 kimg' model on a interactive art d…
-
when I run
```sh
python inversion/video/inference_on_video.py \
--video_path dataset/time_fly.mp4 \
--checkpoint_path pretrained_models/restyle_e4e_ffhq.pt \
--output_path dataset/video_inferenc…
-
Thank you for your great work.
Using the official implement of Stylegan3, we successfully train a generator on our custom dataset.
However, when training the encoder with your code, I can't obtain a…
-
First, thank you for sharing great work!
I trained Projected FastGAN in the LSUN bedroom.
However, FID is increasing across training iterations.
The FID and training loss trends are as follow…
-
how use pti inversion in colab , no restyle and e4e
-
Installation:
conda create --name rembg python=3.9 && conda activate rembg
pip install rembg[gpu]
Error:
```
(rembg) C:\>rembg p -m u2net "c:\test\images" "c:\test\out"
2022-03-13 02:59:00.6…
ghost updated
2 years ago