Convolution is common in neural networks that work with images, either as classifiers or as generators. When designing such convolutional neural networks, the shape of data emerging from each convolution layer needs to be worked out.

In this appendix, we’ll see how this can be done step-by-step with configurations of convolution that we’re likely to see working with images.

In particular, transposed convolutions are seen as difficult to grasp. Here we’ll show that they’re not difficult at all by working through some examples which all follow a very simple recipe.

Example 1: Convolution with stride 1, no padding

In this first simple example, we apply a 2 by 2 kernel to an input of size 6 by 6, with stride 1.

Get hands-on with 1200+ tech skills courses.