bring keras-models to production with tensorflow-serving and nodejs + docker :pizza:
keras->tensorflow+grpc+docker=>nodejs :whale::fire:
/face-recog
/bigquery
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-xor \
-H 'cache-control: no-cache' \
-H 'content-type: application/json' \
-d '{"inputs": [0,1]}'