add tf.compat.v1 for tf2 support

[SuryaThiru]

[itsmemala]

I've been using this fork and just wanted to note that in order to use the DeepExplain library with a model created with TF2 (without having to re-write existing compile and train code), I had to do the following steps first:

1. Save the model weights
2. Add the lines: tf.compat.v1.disable_v2_behavior() tf.compat.v1.disable_eager_execution()
3. Build the model using tf.compat.v1
4. Load the saved model weights

Might be worth adding to documentation as it might be useful to others...