This repo only implements the demo code for GhostNet. Please move to the official repo for more details.

This repo provides demo Pytorch implementation of CVPR 2020 paper GhostNet: More Features from Cheap Operations. The TensorFlow/PyTorch implementation with pretrained model is available at here.

The code was verified on Python3, PyTorch 1.0+.

Usage example:

import torch
from ghost_net import ghost_net

model = ghost_net(width_mult=1.0)
input = torch.randn(32,3,224,224)
y = model(input)
print(y)

GhostNet: More Features from Cheap Operations. CVPR 2020. [arXiv]

By Kai Han, Yunhe Wang, Qi Tian, Jianyuan Guo, Chunjing Xu, Chang Xu.

• Approach

• Performance

GhostNet beats other SOTA lightweight CNNs such as MobileNetV3 and FBNet.

@inproceedings{ghostnet,
  title={GhostNet: More Features from Cheap Operations},
  author={Han, Kai and Wang, Yunhe and Tian, Qi and Guo, Jianyuan and Xu, Chunjing and Xu, Chang},
  booktitle={CVPR},
  year={2020}
}