[MrBuddyCasino]

I found it interesting that they are so close together in performance - I mean what are the odds that they end up within 2% of each other?

[jacksmith21006]

The TPUs are doing almost 2x the images for the same cost.

That is not all that close is it?

[elmarhaussmann]

Yeah, pretty big coincidence. However, this may change with the next TensorFlow versions, which supposedly has further speed improvements for the TPUv2.

Note also, that the ~2% performance difference is only on one model (ResNet-50) and cannot be generalized to all workloads/all of deep learning (at least not without further proof).