Hyperparameters: Difference between revisions

 
(One intermediate revision by the same user not shown)
Line 34: Line 34:
==CNNs==
==CNNs==
===Kernel Size===
===Kernel Size===
Historically, people used larger kernels like 27x27. 
Since VGGnet, people now use smaller kernels like 3x3 or 4x4 along with more layers.
===Stride===
===Stride===
Strided convolution is good for decreasing the resolution and increasing the receptive field. 
Typically, you can choose between using a strided convolution or using pooling to drop the resolution of images or increase the receptive field. 
The alternative to strided convolutions is to use dilated convolutions, like in Atrous Spatial Pyramid Pooling (ASPP).


==Activation functions==
==Activation functions==