whq-48, docker, gpu
docker run -it gcr.io/tensorflow/tensorflow bash
iou2, docker, ryu, ovs, mininet
run command in mininet, to access node, use
s1 ovs-ofctl -O OpenFlow13 dump-flows “s1”
where s1 indicate the node you want to process, following the command, the objective name in the command needs quote.
rank-number of dimensions.
shape-list of dimensions.