GitLab

* Add export inference_graph

* Update Readme.md to include export_inference_graph

* make slim_walkthrough ipython notebook python3 compatible

* make slim_walkthrough ipython notebook python3 compatible

For details see our paper:
"Speed/accuracy trade-offs for modern convolutional object detectors."
Huang J, Rathod V, Sun C, Zhu M, Korattikara A, Fathi A, Fischer I,
Wojna Z, Song Y, Guadarrama S, Murphy K, CVPR 2017
https://arxiv.org/abs/1611.10012

Fix slow down with only 1 GPU

This patch assigns dequeue node to inputs_device. And nolonger shows
"Ignoring device specification /device:GPU:X for node
'clone_X/fifo_queue_Dequeue'" message.

- 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

Corrected documentation word "cropt" -> "crop"

These scripts should exit immediately if a command exits with a non-zero status.

* Updated slim README.md to include links to ResNetv2 models.

* Change v1 to V1, v2 to V2, and other minor comments.

Variable summaries and the learning rate are added elsewhere in the
code.  A quick search also shows that this function is never called.

'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'

The flag description for the momentum flag states that it is `The
momentum for the MomentumOptimizer and RMSPropOptimizer`, however its
not actually used in the RMSPropOptimizer.  Instead, a separate
`rmsprop_momentum` flag was used.  This deletes that flag for
simplicity.  It was not referenced anywhere else in the repo.

* 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