zhangfeng.1/137

Batchnorm is not in eval mode

5

When using batchnorm , in pix2pixHD_model.py, line 216 of inference function. I think we should use eval mode. But now it use batchnorm in a train mode.

u280 container.

2

https://www.xilinx.com/member/forms/download/eula-xef.html?filename=xilinx-ml-suite-ubuntu-16.04-xrt-2018.2-tensorflow-1.12.0-mls-1.5.tar.gz I have just bought a u280 card, but i find that the docker container of tensorflow and caffe is only supporting u200 and u250, and it is a 2018.2...

这里是不是应该 *= 啊。