GitLab

Fixed minor bug in STEVE which sometimes prevented resuming experiments.

* Add more arguments

* Add eager mode

* Add notes for eager mode

* Address the comments

* Fix argument typos

* Add warning for eager and multi-gpu

* Fix typo

* Fix notes

* Fix pylint

Add autograph keras layers example

Update model zoo quantized model links.

[official/mnist]: Avoid some now unnecessary 'tfe' symbols.

 Update the training schedule for better convergence

Mark daoust patch 1

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.