Tuesday, December 24, 2019

ResNet-D

ResNet-D

2019/11/12

前言:

論文《Deep networks with stochastic depth》,我將其命名為 ResNet-D,取其名稱中的 depth。此外,論文裡的實驗隨機丟棄一些殘差層來訓練網路,使用的技巧是 dropout。經由這樣的設計,也可將原始的殘差網路從一百層提升到一千層。

-----


// Review  Stochastic Depth (Image Classification) - Towards Data Science

-----


// Review  Stochastic Depth (Image Classification) - Towards Data Science

-----


// Review  Stochastic Depth (Image Classification) - Towards Data Science

-----


// Review  Stochastic Depth (Image Classification) - Towards Data Science

-----


# ResNet-D

-----


# ResNet-D

-----


# ResNet-D

-----


# ResNet-D

-----



# ResNet-D

-----


# ResNet-D

-----


# ResNet-D

-----


# ResNet-D

-----


# ResNet-D

-----


# ResNet-D

-----


# ResNet-D

-----


# ResNet-D

-----


# ResNet-D

-----

References

◎ 論文 

# ResNet-D
Huang, Gao, et al. "Deep networks with stochastic depth." European conference on computer vision. Springer, Cham, 2016.
https://arxiv.org/pdf/1603.09382.pdf 

-----

◎ 英文參考資料

Review  Stochastic Depth (Image Classification) - Towards Data Science
https://towardsdatascience.com/review-stochastic-depth-image-classification-a4e225807f4a

-----

◎ 簡體中文參考資料

Deep Networks with Stochastic Depth
https://bingning.wang/research/Article/?id=59

No comments: