GitLab

* Sentiment analysis implmenttion in pure Keras.

- This is an update for the sentiment analysis model's pure Keras version.
-- Converting it from the version using Tensorflow's estimator, as it has a issue that affects the accuracy of the model negatively.
- The implementation is with the reference to paddle version.
-- Adjustment of the hyperparameters was done to achieve the accuracy of ~90%

* addressing comments

* addressig comments

also adding

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

for each module as it seemingly is a standard in the repo.

* addressing the final comment.

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.

Autograph guide

Contribution to  Classification of crystallization outcomes using deep convolutional neural networks