https://github.com/talkuhulk/encoder4editing-mobilenetv3
Re-implementation of e4e that use mobilenet-v3 and stylegan2-1024p
https://github.com/talkuhulk/encoder4editing-mobilenetv3
cartoonify face-editing openvino pytorch
Last synced: about 1 month ago
JSON representation
Re-implementation of e4e that use mobilenet-v3 and stylegan2-1024p
- Host: GitHub
- URL: https://github.com/talkuhulk/encoder4editing-mobilenetv3
- Owner: TalkUHulk
- License: mit
- Created: 2021-08-22T04:46:38.000Z (almost 4 years ago)
- Default Branch: master
- Last Pushed: 2022-12-16T06:34:31.000Z (over 2 years ago)
- Last Synced: 2023-03-05T13:19:12.969Z (about 2 years ago)
- Topics: cartoonify, face-editing, openvino, pytorch
- Language: Python
- Homepage:
- Size: 5.79 MB
- Stars: 21
- Watchers: 2
- Forks: 6
- Open Issues: 2
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# encoder4editing with MobileNetV3
The demo of different styles images of e4e-mbv3 framework.
## Description
Re-implementation of e4e that use mobilenet-v3 and stylegan2-1024p. Then mix different styles by stylegan2 and convert to openvino.
## Citation
This code is heavily based on [encoder4editing](https://github.com/omertov/encoder4editing) and [stylegan2-pytorch](https://github.com/rosinality/stylegan2-pytorch). Thanks `omertov` and `rosinality` so much to make his work available 🙏🙏🙏
## Pretrained Models
链接: https://pan.baidu.com/s/1JlJTyBmFLZhju4MpDHLdAA 密码: 086q
[Google Drive](https://drive.google.com/file/d/18zK4A_iM6v8wHQAxd9_dmqGxLg3Z3Oyh/view?usp=share_link)
## Training Log
### Tensorboard
The loss of training.
## Test
```
python scripts/inference.py \
--images_dir=./test_images/ \
--save_dir=./sample \
./ckpt/best_model.pt
```
## More
[Inference on openvino and more demo](https://github.com/TalkUHulk/realworld-stylegan2-encoder)