Code for our CVPR 2020 paper "AdversarialNAS: Adversarial Neural Architecture Search for GANs".

Contributed by Chen Gao, Yunpeng Chen, Si Liu, Zhenxiong Tan, Shuicheng Yan.

We propose a novel AdversarialNAS method, which is the first gradient-based fully differentiable NAS method in GAN field and achieves state-of-art performance with much higher efficiency. We also design a large architecture search space for GAN and make it feasible to search in.

• Searched architecture of generative model on CIFAR-10 dataset.
• Re-trained generative models on CIFAR-10 and STL-10.
• Inference codes for evaluation.
• Training codes for the searched architectures.
• Searching codes.

1. Clone this repository.

   git clone https://github.com/chengaopro/AdversarialNAS.git
   

2. Install pytorch 1.1.0, tensorflow 1.9.0, CUDA 9.0 and corresponding CUDNN via conda.

   conda install pytorch==1.1.0 torchvision==0.3.0 cudatoolkit=9.0 -c pytorch
   

   conda install tensorflow-gpu==1.9.0 cudnn
   

3. Install the requirements via pip.

   pip install -r requirements.txt
   

1. Download the two trained generative models (Baidu drive, passcode: uplb) to ./exps/arch_train_cifar10/Model and ./exps/arch_train_stl10/Model respectively.

   mkdir -p exps/arch_train_cifar10/Model exps/arch_train_stl10/Model 
   

2. Download the pre-calculated statistics (Baidu drive, passcode: uplb) to ./fid_stat for calculating the FID.

   mkdir fid_stat
   

3. Download the inception model (Baidu drive, passcode: uplb) to ./tmp for calculating the IS and FID.

   mkdir tmp
   

Coming soon.

1. Train the weights of generative model with the searched architecture (the architecture is saved in ./exps/arch_cifar10/Genotypes/latest_G.npy)

   sh scripts/train_arch_cifar10.sh
   

   or

   sh scripts/train_arch_stl10.sh
   

2. Test the trained model

   sh scripts/test_arch_cifar10.sh
   

   or

   sh scripts/test_arch_stl10.sh
   

Please consider citing our paper in your publications if it helps your research. The following is a BibTeX reference. The BibTeX entry requires the url LaTeX package.

@InProceedings{Gao_2020_CVPR,
author = {Gao, Chen and Chen, Yunpeng and Liu, Si and Tan, Zhenxiong and Yan, Shuicheng},
title = {AdversarialNAS: Adversarial Neural Architecture Search for GANs},
booktitle = {The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2020}
}

AdversarialNAS is released under the MIT license. See LICENSE for additional details.

Some of the codes are built upon improved-gan, AutoGAN and DARTS. Thanks them for their great works!