ResidualNetWorks总结

ResNets：即残差网络，能帮助解决由于网络结构过于deep而产生的梯度消失问题。

Two main types of blocks are used in a ResNet, depending mainly on whether the input/output dimensions are same or different:

The identity block is the standard block used in ResNets, and corresponds to the case where the input activation(say a[l]) has the same dimension as the output activation(say a[l+2]), here is an alternative diagram showing the individual steps:

 

　　　　　　　　　　　　　　　　 Figure 1 : Identity block . Skip connection "skip over" 2 layers.

 

                                                                 Figure 2 : Identity block . Skip connection "skip over" 3 layers.

 

                                                                                                                            Figure 3 : Convolutiional block . 

 

 

上述两种方式，代码实现起来也比较简单，可以参考deeplearning作业（这里用keras实现）：https://github.com/NumberFairy/deep_learning_answer/blob/master/test4_2_residualNetworks/residualNetworks/index.py

 

转载于:https://www.cnblogs.com/ZT-SummerRain/p/8193936.html