Sync Batch norm not used?

[dragen1860]

Dear author:
Thanks for your re-implementation, it's helpful!
When I tried to train with multi gpus, I noticed you have not convert the batch norm to synced batch norm. I wonder if you realized it or not？ Thank you.

[daa233]

@dragen1860 Thanks for your attention!

The synced batch norm is not used in this repo. The original tensorflow implementation of deep fill v1 uses only 1 gpu to train the model. I extended this repo to support multiple gpus but not synced batch norm. You are welcomed to contribute the code!