CNN + FC snippet

The CNN + FC snippet is a basic convolutional neural network with an additional tabular data input. This means that the network takes two different features as inputs:

  • An image input feature that is fed into the convolutional layers

  • A tabular data set that is fed into the dense layers

This snippet is appropriate for getting started with the platform and starting to explore multi-input models.

CNN + FC snippet architecture

CNN + FC snippet used to solve the Predict California house prices tutorial
Figure 1. CNN + FC snippet used to solve the Predict California house prices tutorial

The CNN + FC snippet consists of the following types of blocks:

  • 2D Convolution. This block is used to detect spatial features in an image.

  • 2D Max pooling. This layer reduces the size of the data. You can say that 2D max pooling is similar to scaling down the size of an image.

  • Batch normalization. This normalizes all input features to a similar range of values which will speed up learning.

  • Concatenate. This block concatenates a list of inputs.

  • 2D Global average pooling. This block is used as an alternative to the Flatten block as it reduces the tensor of the last convolution layer from HxWx128 to a tensor of size 1x1x128.

  • Dense. This is a densely connected neural network layer.

Get started for free