Python Deep Learning - Second Edition

Model inputs and outputs

Unlike the end-to-end approach, which uses the raw sensor data (for example, camera images), here we'll use the so-called middle-level input. This is a series of top-down (birds-eye) view 400 × 400 images, similar to the images of the CarRacing-v0 environment but much more complex. One moment of time is represented by multiple images, where each one contains different elements of the environment.

We can see an example of a ChauffeurNet input/output combination in the following diagram:

ChauffeurNet inputs (source: https://arxiv.org/abs/1812.03079)

Let's discuss the input/output elements in alphabetical order:

• (a) ...