@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 and efficiently search neural network architectures on your target task and hardware!

• Aug-10-2019: Training code is released.
• Dec-21-2018: TensorFlow pretrained models are released.
• Dec-01-2018: PyTorch pretrained models are released.

Mobile settings	GPU settings
	Model Top-1 Top-5 Latency MobilenetV2 72.0 91.0 6.1ms ShufflenetV2(1.5) 72.6 - 7.3ms ResNet-34 73.3 91.4 8.0ms MNasNet(our impl) 74.0 91.8 6.1ms ProxylessNAS (GPU) 75.1 92.5 5.1ms
ProxylessNAS(Mobile) consistently outperforms MobileNetV2 under various latency settings.	ProxylessNAS(GPU) is 3.1% better than MobilenetV2 with 20% faster.

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)

  If the above scripts failed to download, you download it manually from Google Drive and put them under $HOME/.torch/proxyless_nas/.

• 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

ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware (ICLR’19)

AMC: AutoML for Model Compression and Acceleration on Mobile Devices (ECCV’18)

HAQ: Hardware-Aware Automated Quantization (CVPR’19, oral)

Defenstive Quantization: When Efficiency Meets Robustness (ICLR'19)