iT邦幫忙

第 12 屆 iThome 鐵人賽

DAY 28
1
AI & Data

30天只學U-net系列 第 28

[day-28] U-net Conclusion

前言

要道尾聲了,Unet的結論對於這們短的論文來說,其實算是不太重要的(看了也是)。

Conclusion

The u-net architecture achieves very good performance on very different biomedical segmentation applications.

先商業自吹一下。

Thanks to data augmentation with elastic deformations, it only needs very few annotated images and has a very reasonable training time of only 10 hours on a NVidia Titan GPU (6 GB).

可以在GPU訓練 10 小時。

We provide the full Caffe[6]-based implementation and the trained network. We are sure that the u-net architecture can be applied easily to many more tasks.

提供了基於 caffe 實踐的開源程式碼,可以輕鬆實現。

Concusion

這是一個如果我寫出來會避不了業的結論。但是對方畢竟是很強的研究團隊,在短短12頁裡面受益良多,接下來就是實現部分,明天見。

Reference

[0] U-net


上一篇
[day-27] U-net Experiments (3) - performance 2
下一篇
[day-29] U-net code 說明
系列文
30天只學U-net30

尚未有邦友留言

立即登入留言