Generation Datasets

It is recommended to symlink the dataset root to $MMEDITING/data. If your folder structure is different, you may need to change the corresponding paths in config files.

MMEditing supported generation datasets:

Paired Dataset for Pix2pix

[DATASET]

@inproceedings{isola2017image,
  title={Image-to-image translation with conditional adversarial networks},
  author={Isola, Phillip and Zhu, Jun-Yan and Zhou, Tinghui and Efros, Alexei A},
  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
  pages={1125--1134},
  year={2017}
}

You can download paired datasets from here. Then, you need to unzip and move corresponding datasets to follow the folder structure shown above. The datasets have been well-prepared by the original authors.

mmediting
├── mmedit
├── tools
├── configs
├── data
│   ├── paired
│   │   ├── facades
│   │   ├── maps
|   |   ├── edges2shoes
|   |   |    ├── train
|   |   |    ├── test

Unpaired Dataset for CycleGAN

[DATASET]

@inproceedings{zhu2017unpaired,
  title={Unpaired image-to-image translation using cycle-consistent adversarial networks},
  author={Zhu, Jun-Yan and Park, Taesung and Isola, Phillip and Efros, Alexei A},
  booktitle={Proceedings of the IEEE international conference on computer vision},
  pages={2223--2232},
  year={2017}
}

You can download unpaired datasets from here. Then, you need to unzip and move corresponding datasets to follow the folder structure shown above. The datasets have been well-prepared by the original authors.

mmediting
├── mmedit
├── tools
├── configs
├── data
│   ├── unpaired
│   │   ├── facades
|   |   ├── horse2zebra
|   |   ├── summer2winter_yosemite
|   |   |    ├── trainA
|   |   |    ├── trainB
|   |   |    ├── testA
|   |   |    ├── testB