GitLab

- Corrects some formatting/lint issues.
- Adds seperable convolutions to inception v2.

- Set spatial squeeze to true for resnets
- Make activations configurable for resnets
- Make batch norm configurable for resnets
- Fix some bad comment wrapping in vgg.py.

- Add inception_resnet_v2_base
- Provide option to use SAME padding for all inception resnet v2
  layers. This is to align feature maps sizes.

Use a relative link instead

* MobileNet V1 commit

* updates to README

'xrange' was used in multiple places. In this setting it provided no measurable gain in terms of performance or memory, but broke python3 compatibility. It was replaced with 'range'

* Fixed model_deploy to correctly assign weights to variables_device

* Adding test for network_fn's arg_scope

* Style fix (double blank line)

* Add WORKSPACE file to models/slim so that imports work properly

Align model slim/resnet to slim/inception (set spatial_squeeze and default_image_size). Add a sample script for training resnet_v1_50 on flower set

The average pool is used but named 'MaxPool_0a_7x7'.
Change it to 'AvgPool_0a_7x7'.