The DenseNet model


DenseNet is an extension of ResNet proposed by Huang et al. ( In ResNet blocks, the previous layer is merged into the future layer by summation. In DenseNet, the previous layer is merged into the future layer by concatenation. DenseNet connects all the layers to the previous layers and the current layer to the following layers.

In the following diagram, it can be seen how the feature maps are supplied as input to the other layers: 

This way, it provides several advantages such as smoother gradients, feature transformation and so on. This also reduces the number of parameters:


We have covered all the latest algorithms for the image classification task. Any of the architectures can be used for an image classification task.  In the next section, we will see how to train a model to predict pets, using these advanced architectures and improve the accuracy. 

The Core Concepts of Model-Based Design

Model based design in Simulink


There are no reviews yet.

Be the first to review “The DenseNet model”

Your email address will not be published. Required fields are marked *