GitLab

Asking which model this issue is about

* Updating TF submodule to latest and adding a Dockerfile example.

* Extra \n in ./configure.

* Updating Dockerfile to use bazel 0.2.2b.

* Replacing a mention of treebank_union with PMP in the README.

* doc: Add instructions on installing numpy

* fix typo

fix "we processes" typo

fix typo

Typos

* Modified the way the output size is specified.
* Added support for batches of inputs.

Tentative fix for issue #47

* improve image processing performance for Inception.

Implements a distributed trainer for Inception.

Updated to the latest version of TF-Slim

Update ops.py

Make sure range create a list, otherwise this won't create a list in Python 3.

Add collections_test

update inception slim.

Fix issue in neural_gpu.py where TypeError is raised.

* `python neural_gpu_trainer.py --task=rev` raises the following TypeError:

  File “..models/neural_gpu/neural_gpu.py", line 26, in conv_linear
    assert args
  File “..tensorflow/python/framework/ops.py", line 475, in __nonzero__
    raise TypeError("Using a `tf.Tensor` as a Python `bool` is not allowed. "
TypeError: Using a `tf.Tensor` as a Python `bool` is not allowed. Use `if t is not None:` instead of `if t:` to test if a tensor is defined, and use the logical TensorFlow ops to test the value of a tensor.

Adding Spatial Transformer to Models

Shorten STN summary in README

relinked to data files

adding license header, editing AUTHORS file

adding tensorflow version

Using a `tf.Tensor` as a Python `bool` is not allowed

raise TypeError("Using a `tf.Tensor` as a Python `bool` is not allowed. "
TypeError: Using a `tf.Tensor` as a Python `bool` is not allowed. Use `if t is not None:` instead of `if t:` to test if a tensor is defined, and use the logical TensorFlow ops to test the value of a tensor.

The ILSVRC original image url somehow changed, use the new one if failed

Fix typo in inception/README.md

update broken code links