Wei-Ching Wang

in the paper the object recognition experiment was setup using cifar-10, imagenet, would you consider using bench marking using coco data instead? would you be open source model network that...

ran uniform load with single arrival process sending one randomly generated color image of size 224x224 for every 120 seconds 

In TFS, here they set batching parameter to test model latency https://github.com/tensorflow/serving/issues/344 we know that clipper also use adaptive batching mechanism that is determined by https://github.com/ucbrise/clipper/blob/3c5a1cc6ce59e0ccd778f526a50808d0e7b2576f/src/libclipper/src/containers.cpp#L128 (https://github.com/ucbrise/clipper/issues/548) could you show...

@simon-mo @YogeshSomawar @agneeshdg I also tried to run on aws ec2 k8s but it failed on health check, have you guys had similiar problems? 

@withsmilo @xuguangzhao trying to start clipper on aws k8s still facing the Clipper still initilizing issue setting local proxy port 8080 followed steps to start k8s cluster: https://docs.aws.amazon.com/eks/latest/userguide/getting-started.html#vpc-create 

Hi @cwtan501 I tried to run your template from aws p2 instance but it failed to build docker image at Step 22/35 : RUN apt-get update && apt-get install -y...

@simon-mo @RehanSD I was using FROM tensorflow/tensorflow:latest-gpu-py3 this image seems to resolve issue with finding GPU:0 device

@simon-mo ran this new gpu container with following stats: recv: 0.000223 s, parse: 0.000013 s, handle: 0.157390 s check it out at docker pull wcwang07/test-gpu-container clipper_conn.register_application(name="hello-tf", input_type="int", default_output="this is default...