DPN* models

Y. Chen, J. Li, H. Xiao, X. Jin, S. Yan, and J. Feng, “Dual path networks,” in Advances in Neural Information Processing Systems (NIPS), 2017, pp. 4467–4475.

@inproceedings{chen2017dual,
  title={Dual path networks},
  author={Chen, Yunpeng and Li, Jianan and Xiao, Huaxin and Jin, Xiaojie and Yan, Shuicheng and Feng, Jiashi},
  booktitle={Advances in Neural Information Processing Systems (NIPS)},
  pages={4467--4475},
  year={2017}
}

Source: MXNET repo of Chen Yunpeng

The porting has been made possible by Ross Wightman in his PyTorch repo.

As you can see here DualPathNetworks allows you to try different scales. The default one in this repo is 0.875 meaning that the original input size is 256 before croping to 224.

• dpn68(num_classes=1000, pretrained='imagenet')
• dpn98(num_classes=1000, pretrained='imagenet')
• dpn131(num_classes=1000, pretrained='imagenet')
• dpn68b(num_classes=1000, pretrained='imagenet+5k')
• dpn92(num_classes=1000, pretrained='imagenet+5k')
• dpn107(num_classes=1000, pretrained='imagenet+5k')

'imagenet+5k' means that the network has been pretrained on imagenet5k before being finetuned on imagenet1k.