GitLab

Explicitly specify checkpoint version.

Fix simple errors in synthetic examples in lfads.

change to lfads to allow training of encoder weights only

TF Saver now requires specifying the checkpoint version even when restoring to avoid errors when we specify
a path to a checkpoint file instead of a directory.

change to lfads to allow training of encoder weights only

Update generate_cifar10_tfrecords.py

The change you added did not work with python2, it does not have encoding in .log.  This fixes it. feel free to test on Python3.  I tested python2 and I am really sue this works fine for python3.  Good catch.  sorry for not having it fixed earlier.

Allow users to pass in num_classes to ResNet

Fix mnist_tpu.py which was giving unknown shape errors

Add a note about tf.image.convert_image_dtype

Update ISSUE_TEMPLATE.md

Return datasets directly from input_fns for TF1.5

change cPickle to pickle for python3
specify  encoding='latin1' when call pickle.load()

Use the short path for TPUClusterResolver

The long path doesn't work for TensorFlow 1.6 because the .python package under cluster_resolver doesn't exist.

Add ClusterResolver capability to mnist_tpu.py

* Refactoring input function

* Updating name of variable

Removed "coming soon' in "Image Compression" title

lfads: Adding do_train_readin option allowing fixed readin matrices

Fix typo

Return dataset from input_fn

Fix tensorflow/models gan typos. fixes #3295

Fix file reading issue for python3 code

Fix wrong reference in ptb_word_lm.py

tcn: Fix undefined 'v' in Python 3