O'Reilly logo

Deep Learning with PyTorch by Vishnu Subramanian

Stay ahead with the world's most comprehensive technology and business learning platform.

With Safari, you learn the way you learn best. Get unlimited access to videos, live online training, learning paths, books, tutorials, and more.

Start Free Trial

No credit card required

ResNet 

ResNet solves these problems by explicitly letting the layers in the network fit a residual mapping by adding a shortcut connection. The following image shows how ResNet works:

In all the networks we have seen, we try to find a function that maps the input (x) to its output (H(x)) by stacking different layers. But the authors of ResNet proposed a fix; instead of trying to learn an underlying mapping from x to H(x), we learn the difference between the two, or the residual. Then, to calculate H(x), we can just add the residual to the input. Say the residual is F(x) = H(x) - x; instead of trying to learn H(x) directly, we try to learn ...

With Safari, you learn the way you learn best. Get unlimited access to videos, live online training, learning paths, books, interactive tutorials, and more.

Start Free Trial

No credit card required