August 8, 2019

358 words 2 mins read



[ICLR 2019] ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware

repo name mit-han-lab/proxylessnas
repo link
language Python
size (curr.) 116 kB
stars (curr.) 980
created 2018-12-01
license Apache License 2.0

ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware [Website] [arXiv] [Poster]

  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},

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

Now, proxylessnas is on PyTorch Hub. You can load it with only two lines!

target_platform = "proxyless_cpu" # proxyless_gpu, proxyless_mobile, proxyless_mobile14 are also avaliable.
model = torch.hub.load('mit-han-lab/ProxylessNAS', target_platform, pretrained=True)


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


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.

We provide a visualization of search process. Please refer to our paper for more results.

How to use / evaluate

  • Use

    # pytorch 
    from proxyless_nas import proxyless_cpu, proxyless_gpu, proxyless_mobile, proxyless_mobile_14, proxyless_cifar
    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 --path 'Your path to imagent' --arch proxyless_cpu # pytorch ImageNet

    python -d cifar10 # pytorch cifar10

    python --path 'Your path to imagent' --arch proxyless_cpu # tensorflow

File structure

Once for All: Train One Network and Specialize it for Efficient Deployment (ICLR'20, code)

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)

comments powered by Disqus