Install the dependencies in env.yml
$ conda env create -f env.yml
$ conda activate pix-envTrain ArtBreeder dataset with Smart Disc Feature enabled and 7 disc images.
$ python train.py --dataroot ./datasets/newbreeder/ --name art_newbreeder_allparents_bs8_disc --no_instance --fineSize 256 --loadSize 256 --label_nc 0 --resize_or_crop resize_and_crop --output_nc 3 --batchSize 8 --mv --smart_disc --num_disc_images 7Generate images from trained model.
$ python gen_imgs.py --dataroot ./datasets/newbreeder/ --name art_newbreeder_allparents_bs8_disc --no_instance --fineSize 256 --loadSize 256 --label_nc 0 --resize_or_crop resize_and_crop --output_nc 3 --batchSize 8 --mv --smart_disc --num_disc_images 7 --which_epoch 50FID Calculation
$ python -m pytorch_fid gen_images/art_newbreeder_allparents_bs8_disc/gts gen_images/art_newbreeder_allparents_bs8_disc/generated/The basis of this code is pix2pixHD.
If you use this code for your research, please cite our paper:
@InProceedings{Gokay_2021_ICCV,
author = {Gokay, Dilara and Simsar, Enis and Atici, Efehan and Ahmetoglu, Alper and Yuksel, Atif Emre and Yanardag, Pinar},
title = {Graph2Pix: A Graph-Based Image to Image Translation Framework},
booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops},
month = {October},
year = {2021},
pages = {2001-2010}
}