Skip to content

zzhang05/DANI

Repository files navigation

Codes for ACMMM2024 paper ''Improving the Training of the GANs with Limited Data via Dual Adaptive Noise Injection''

We have provided the codes of DANI with Projected GAN on low-shot datasets. The details are shown as follows.

Dataset

The low-shot datasets can be found in [link]

Requirement

Please follow the Projected GAN [link] to build your conda enviroment.

conda env create -f environment.yml
conda activate pg

Training

To train your own Projected GAN + DANI (FastGAN backbone) on the low-shot dataset (100-shot obama dataset as example), run the following command:

python train.py --outdir=training-runs --data="100-shot-obama.zip" --subset=100 --gpus=2 --batch 64 --batch-gpu=32 --cfg fastgan --kimg 70000 --target 0.45 --d_pos first --noise_sd 0.5

Important notes

  1. The codes of this module is built upon the codes of the Projected GAN [link] and Diffusion GAN [link]. We thanks a lot for their great work.

  2. Feel free to contact me at zzhang55@qub.ac.uk if you have any questions.

Citation:

@inproceedings{zhang2024improving,
  title={Improving the Training of the GANs with Limited Data via Dual Adaptive Noise Injection},
  author={Zhang, Zhaoyu and Hua, Yang and Sun, Guanxiong and Wang, Hui and McLoone, Se{\'a}n},
  booktitle={Proceedings of the 32nd ACM International Conference on Multimedia},
  pages={6725--6734},
  year={2024}
}

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published