Viewed 3 times
The vary famous UNet model has three parts: 1 Encoder, 2 Decoder, and 3 Bottleneck.
As far as I understand …
Encoder does the contextual feature extraction.
Decoder does the localization of features
but I do not understand the role of bottleneck… I want to know that is there any specific role of bottleneck layer in the UNet model ?? Anyone please make me understand. Please correct me for encoder and decoder as well if I am wrong…
… … Thank you everyone