GitLab

Update the training schedule for better convergence. The current hyperparameters tend to diverge in Colab.

Loss -> Accuracy

Typo

Fix link to point to master

this won't even work in 1.10, so it will be a while before it should show up in guide/

Fix notebook text

Re-add regularization section, with weight distributions.

Autograph guide

Contribution to  Classification of crystallization outcomes using deep convolutional neural networks

processes all crystal growth images in directory and  sub directories and prints results to console, and a comma seperated file. Removes dependencies of google SDK(only dependent on tensorflow and python 2.7)

Bug in label discovered at OSCON.

Fix relative links in linear notebook

* Add callbacks

* Add readme

* update readme

* fix some comments

* Address all comments

* Update docstrings

* Add method docstrings

* Update callbacks

* Add comments on global_step initialization

* Some updates

* Address comments

Add clarifications 

Add notebook fixing "wide" tutorial.

Add autograph guide

Mark estimator wide 2

Correct prediction probabilities in custom training walkthrough

Correct the prediction probabilities for Iris setosa and Iris virginica 
to match the prediction values in the image