Add lite version of the license plate reader example

[RobertLucian]

A lite version of the license plate reader example is added in this PR.

The motive behind this is to provide a low barrier for experimentation for anyone that has an interest in it. It's useful because only one GPU is required.

The changes that need to be brought to cortex-examples bucket are:

1. Rename the existing folder containing the SavedModel for YOLOv3 from yolov3 to yolov3_tf.
2. Place this keras model at s3://cortex-examples/tensorflow/license-plate-reader/yolov3_keras/model.h5.

---

checklist:

• run make test and make lint
• test manually (i.e. build/push all images, restart operator, and re-deploy APIs)
• update examples
• update docs and add any new files to summary.md (view in gitbook after merging)