Enhancement for Google Colab

Hi,

I am new to Deep Learning, TF, and tools. I am trying out the examples using Google Colab. One thing I am noticing with the Ch. 3 examples is that I am getting a "placeholder not set" kind of error after I have run the notebook once:
> InvalidArgumentError: You must feed a value for placeholder tensor

One workaround is to select _Runtime > Restart Runtime..._ from the menu which is a bit cumbersome and time consuming if you want to experiment with the example and run it many times.

A better approach would be to call `tf.reset_default_graph()` in the beginning of the program or right before the placeholders are created. I think this would make things easier for people relying on the Google Colab or similar environments.

Thank you,
Andrey

Start with the Chapter 3 examples and reproduce the placeholder error by running the relevant example twice in Google Colab. Identify the notebook or program that creates the placeholders, then verify that repeated execution no longer requires restarting the runtime and that the examples still run successfully.

Written by the indexing model from the issue text.