search

pit-ray / Anime-Semantic-Segmentation-GAN

This repository was implemented to perform semantic segmentation for pixiv anime illust.
MIT License
53 stars 3 forks source link

pretrained weights #1

Closed ghost closed 4 years ago

ghost commented 4 years ago

Awesome results!

It would be better if you could release the trained model so that people can easily try your model. Thank you!

pit-ray commented 4 years ago

Thanks for your comment!

pretrained weights

I prepared pre-trained weights of Generator and Discriminator and added scripts in order to get these weights.
You can get them by executing a following command. 

python get_pretrained_weight.py

Totally about 200MB, so it may take few minutes.

sample illusts

You are able to download a sample image from safebooru.org. 

python get_sample_data.py

How to predict

If you want pre-trained model to predict, please do a next python script. 

python predict.py

predict.py creates predicted images from predict_from directory to predict_to.
In addition, sources are assumed 256 x 256 white-background png.

If you have any questions, feel free to contact me.

ghost commented 4 years ago

Thank you! Appreciate the prompt reply