@inproceedings{
  cai2018proxylessnas,
  title={Proxyless{NAS}: Direct Neural Architecture Search on Target Task and Hardware},
  author={Han Cai and Ligeng Zhu and Song Han},
  booktitle={International Conference on Learning Representations},
  year={2019},
  url={https://arxiv.org/pdf/1812.00332.pdf},
}

Without any proxy, directly search neural network architectures on your target task and hardware!

Website, arXiv

• PyTorch 0.3.1 or Tensorflow 1.5
• Python 3.6

• Dec-21-2018: TensorFlow pretrained models are released.
• Dec-01-2018: PyTorch pretrained models are released.

ProxylessNAS consistently outperforms MobileNetV2 under various latency settings.

People used to deploy one model to all platforms, but this is not good. To fully exploit the efficiency, we should specialize architectures for each platform.

Please refer to our paper for more results.

• Use

  # pytorch 
  from proxyless_nas import proxyless_cpu, proxyless_gpu, proxyless_mobile, proxyless_mobile_14
  net = proxyless_cpu(pretrained=True) # Yes, we provide pre-trained models!

  # tensorflow
  from proxyless_nas_tensorflow import proxyless_cpu, proxyless_gpu, proxyless_mobile, proxyless_mobile_14
  tf_net = proxyless_cpu(pretrained=True)

• Evaluate

  python eval.py --path 'Your path to imagent' --arch proxyless_cpu # pytorch

  python eval_tf.py --path 'Your path to imagent' --arch proxyless_cpu # tensorflow