Project | Paper | Video (3m) | Demo | Previous Implementation | Two Minute Papers Video
Imaginaire is released under NVIDIA Software license. For commercial use, please consult [email protected]
For installation, please checkout INSTALL.md.
We trained our model using an NVIDIA DGX1 with 8 V100 32GB GPUs. Training took about one week.
FUNIT prefers the following data structure.
${TRAINING_DATASET_ROOT_FOLDER}
└───images_content
└───content_001.jpg
└───content_002.jpg
└───content_003.jpg
...
└───images_style
└───style_001.jpg
└───style_002.jpg
...
- Download the dataset and untar the files.
python scripts/download_dataset.py --dataset animal_faces
- Build the lmdbs
for f in train train_all val; do
python scripts/build_lmdb.py \
--config configs/projects/funit/animal_faces/base64_bs8_class119.yaml \
--data_root dataset/animal_faces_raw/${f} \
--output_root dataset/animal_faces/${f} \
--overwrite
done
python -m torch.distributed.launch --nproc_per_node=8 train.py \
--config configs/projects/funit/animal_faces/base64_bs8_class119.yaml \
--logdir logs/projects/funit/animal_faces/base64_bs8_class119.yaml
FUNIT prefers the following file arrangement for testing.
${TEST_DATASET_ROOT_FOLDER}
└───images_content
└───0001.jpg
└───0002.jpg
└───0003.jpg
...
└───images_style
└───0001.jpg
└───0002.jpg
└───0003.jpg
...
The style in style image 0001.jpg will be transferred to the content image 0001.jpg.imaginaire
- Download sample test data by running
python scripts/download_test_data.py --model_name funit
python inference.py --single_gpu \
--config configs/projects/funit/animal_faces/base64_bs8_class149.yaml \
--output_dir projects/funit/output/animal_faces
The results are stored in projects/funit/output/animal_faces
Below we show the expected style--content-output images.
Style | Content | Translation |
If you use this code for your research, please cite our papers.
@inproceedings{liu2019few,
title={Few-shot Unsueprvised Image-to-Image Translation},
author={Ming-Yu Liu and Xun Huang and Arun Mallya and Tero Karras and Timo Aila and Jaakko Lehtinen and Jan Kautz.},
booktitle={IEEE International Conference on Computer Vision (ICCV)}},
year={2019}
}