InceptionResnetV2 comments

Hi guys,

First thanks very much for the package! I found it very easy to use and am very grateful that you guys put in the effort to make this.

I was looking into the implementation of InceptionResnetv2 and comparing it to Google's [description](https://ai.googleblog.com/2016/08/improving-inception-and-image.html). I see 3 areas where I can't quite match up the code to the online description, and I wondered what you thought about them. The 3 issues are annotated on this image:


1) Branch (1) in block 8 is three 2d convolutions rather than two. I suspect this was on purpose given the kernel sizing of the second two convolutions [(1,3) then (3,1)] but I wanted to check.

2) I cannot find the dropout layer at the end of the network between avgpool_1a and last_linear

3) I cannot see the extra branch that comes out of the middle of the network (between repeat/sequential/Block17 and mixed_7a in your implementation). I also guess this was on purpose, is this intended for the user to implement?

Thanks for your help!

EDIT: I see that 1) has a direct analogy in the [TensorFlow repo](https://github.com/tensorflow/models/blob/master/research/slim/nets/inception_resnet_v2.py) . 3) is, I think relevant to the "create_aux_logits" check in the TF repo.

Start with the InceptionResnetV2 implementation and compare block 8, avgpool_1a/last_linear, and the Block17-to-mixed_7a path against the linked TensorFlow reference. Check the create_aux_logits behavior and determine the intended status of each reported difference; the issue names no local file or test, so completion would require a clear conclusion and follow-up change scope.

Written by the indexing model from the issue text.