GitLab

In order to help address issue #5987, I'm adding references to the evaluation loop example. I'm also making it more obvious that this is not the main TF-Slim page and adding another reference to that page in the introductory paragraph.

batch size for exported model. Defaults to None to allow for flexible
batching.

- 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.

* We do this because we want rules outside of slim to be able to depend on it in order to pull in slim models.

Also fixes some typos in other scripts.

--logtostderr causes the following error: E tensorflow/examples/label_image/main.cc:319] Unknown argument --logtostderr

* 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