Is the Image Classification benchmark ResNet-50 v1 or ResNet-50 v1.5?

[matthew-frank]

https://github.com/mlcommons/training/blob/master/image_classification/README.md#1-problem says

This benchmark uses resnet v1.5 to classify images ...

While https://github.com/mlcommons/training/blob/master/image_classification/README.md#structure--loss says

In brief, this is a 50 layer v1 RNN ...

Please clarify in the README.md whether this is actually a v1 or a v1.5 ResNet-50? Perhaps it would help to move the discussion from https://github.com/mlcommons/training/tree/master/image_classification/tensorflow/official/resnet into this top level document?

As I understand it, the difference between "v1" and "v1.5" is typically that in the bottleneck blocks with downsampling v1 puts the stride 2 convolution in the first 1x1 convolution of the bottleneck, while v1.5 puts the stride 2 into the 3x3 convolution of the bottleneck. If this really is a v1.5 network then I believe a better reference for the modification to the v1 network described in Kaiming He's 2015 paper is the blogpost http://torch.ch/blog/2016/02/04/resnets.html.

[johntran-nv]

It's v1.5. @sgpyc could you update the appropriate documentation?

[itayhubara]

I create PR: https://github.com/mlcommons/training/pull/605

[matthew-frank]

I believe PR https://github.com/mlcommons/training/pull/590 (earlier https://github.com/mlcommons/training/pull/516) also addresses this issue.

[ShriyaPalsamudram]

Closing as the benchmark is dropped from Training benchmark suite