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.

This code is heavily based on encoder4editing and stylegan2-pytorch. Thanks omertov and rosinality so much to make his work available 🙏🙏🙏

The loss of training.

python scripts/inference.py \
--images_dir=./test_images/ \
--save_dir=./sample \
./ckpt/best_model.pt

Name		Name	Last commit message	Last commit date
Latest commit History 4 Commits
configs		configs
criteria		criteria
datasets		datasets
editings		editings
metrics		metrics
models		models
options		options
sample		sample
scripts		scripts
training		training
utils		utils
LICENSE		LICENSE
README.md		README.md
requirements.txt		requirements.txt