keras->tensorflow+grpc+docker=>nodejs 🐳🔥

• example of bringing a keras model to production using tensorflow serving
• using custom XOR model with tensor.proto dimensions example
• building & training of the model works with python2.7 on the workstation
• exported model is served via grpc in a C++ server using a Docker-Container
• a nodejs server wraps the grpc api for a simple http POST endpoint
• also ships an advanced multi-model face (emotion, gender) detection example /face-recog
• and and advanced google bigquery (as dataaset) example /bigquery

• XOR Setup below
• Face-Recog Setup
• BigQuery Setup

python
pip
docker (docker-compose)

./prepare.sh
# installs python dependencies via pip
# builds the docker image for tensorflow_serving (takes a while ~ 30 minutes)
# image size ~ 3.5 GB

checkout build troubleshoot if you are having trouble

python train.py
# results will be in (/result)

python export.py
# results will be in (/export)

./start-servers.sh
# ./stop-servers.sh

curl -X POST \
  http://localhost:8080/predict \
  -H 'cache-control: no-cache' \
  -H 'content-type: application/json' \
  -d '{"inputs": [0,1]}'