In the lecture, Laurence talks about defining custom Model classes for recurring building blocks / sub-networks in a larger model architecture. But in the ResNet-like example, he uses Layer as base class for CNNResidual and DNNResidual. At first sight, I found a Layer containing itself potentially m…

Inheriting from Layer vs Model for recurring building blocks

gent.spah March 15, 2022, 9:36am 4

This is a similar question to the one we have a bit further down on this page:

Topic		Replies	Views
When to use Layers or Model as parent class Custom Models, Layers and Loss Functions with TF	6	289	November 21, 2021
Help with building custom model Custom Models, Layers and Loss Functions with TF week-3	8	479	August 24, 2023
Using factory functions or Class implementations. Just a matter of style? Custom Models, Layers and Loss Functions with TF week-2	2	358	November 18, 2023
What exactly does this command do. model2.layers[4] Convolutional Neural Networks	2	625	April 2, 2022
Residual network in Tensorflow advance Techniques Custom Models, Layers and Loss Functions with TF week-4	3	597	August 5, 2023