krystianity / Keras Serving
Licence: apache-2.0
bring keras-models to production with tensorflow-serving and nodejs + docker π
Stars: β 150
Projects that are alternatives of or similar to Keras Serving
Ovpm
OpenVPN Management Server - Effortless and free OpenVPN server administration
Stars: β 256 (+70.67%)
Mutual labels: grpc, network
Deep Learning In Production
In this repository, I will share some useful notes and references about deploying deep learning-based models in production.
Stars: β 3,104 (+1969.33%)
Mutual labels: serving, production
Core
Eru, a simple, stateless, flexible, production-ready orchestrator designed to easily integrate into existing workflows. Can run any virtualization things in long or short time.
Stars: β 147 (-2%)
Mutual labels: grpc, network
Flyte
Accelerate your ML and Data workflows to production. Flyte is a production grade orchestration system for your Data and ML workloads. It has been battle tested at Lyft, Spotify, freenome and others and truly open-source.
Stars: β 1,242 (+728%)
Mutual labels: grpc, production
Lc kicad lib
kicad production symbol and footprint library auto convert from JLC's integrate Altium Designer library
Stars: β 140 (-6.67%)
Mutual labels: production
Zeebe
Distributed Workflow Engine for Microservices Orchestration
Stars: β 2,165 (+1343.33%)
Mutual labels: grpc
Simplewall
Simple tool to configure Windows Filtering Platform (WFP) which can configure network activity on your computer.
Stars: β 2,505 (+1570%)
Mutual labels: network
Bodywork Core
Deploy machine learning projects developed in Python, to Kubernetes. Accelerated MLOps π
Stars: β 145 (-3.33%)
Mutual labels: serving
Boost Asio Study
Examples and toturials for C++ Boost Asio library.
Stars: β 144 (-4%)
Mutual labels: network
Go Micro Boilerplate
The boilerplate of the GoLang application with a clear microservices architecture.
Stars: β 147 (-2%)
Mutual labels: grpc
Pyfunceble
The tool to check the availability or syntax of domain, IP or URL.
Stars: β 143 (-4.67%)
Mutual labels: network
Gf Cli
GoFrame Command Line Interface, which is your helpmate for building GoFrame application with convenience.
Stars: β 143 (-4.67%)
Mutual labels: grpc
Networkgraph
εΊδΊD3.jsηNeo4jη½η»εΎε―θ§ε(Visualization of Neo4j Network Graph Based on D3.js
Stars: β 145 (-3.33%)
Mutual labels: network
keras-serving
keras->tensorflow+grpc+docker=>nodejs π³π₯
- 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
Overview
- XOR Setup below
- Face-Recog Setup
- BigQuery Setup
Workflow (Unix - testen on Ubuntu 16.04 64bit)
You will need
python
pip
docker (docker-compose)
1. Install Requirements
./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
2. Build, Train and Serialise Keras Model
python train.py
# results will be in (/result)
3. Load and export Model as Tensorflow Graph
python export.py
# results will be in (/export)
4. Build & Run Containers via docker-compose
./start-servers.sh
# ./stop-servers.sh
5. Test API via curl
curl -X POST \
http://localhost:8080/predict-xor \
-H 'cache-control: no-cache' \
-H 'content-type: application/json' \
-d '{"inputs": [0,1]}'
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].