2d Convolution in expansive path in Unet from 256 to 128 feature maps

Research & Models
#1

Hi,
how does 2d Convolution in expansive path in Unet from 256 to 128 feature maps work?
I mean normally that happened if we want to extract more feature maps from an input.

Unbenannt
Unbenannt699×606 32.5 KB

#2

@samo_timy,

Welcome to the Tensorflow Forum!

The 2D convolution in the expansive path of Unet from 256 to 128 feature maps, works by increasing the spatial resolution while decreasing the number of feature maps, this allows the model to see more details of the input image and learn more fine-grained features.

Thank you!