- Energy Meter GSM with Arduino (part 2)Posted 4 days ago
- Energy Meter GSM with Arduino (part 1)Posted 1 week ago
- ARDULOCK: a keyboard with RFID modulePosted 1 month ago
- Autofocus Glasses/Phoropter Using Variable Focus Liquid LensPosted 3 months ago
- Home Automation & Lights controlling SystemPosted 3 months ago
- Solar TrackerPosted 3 months ago
- LTspice inverter simulation with thermal effectsPosted 3 months ago
- AI in LEGO EV3 Maze-Driving RobotPosted 3 months ago
- Temperature predicting using boltiotPosted 3 months ago
- Sparkly Air SensorPosted 3 months ago
Oracle Open Sourced Graphpipe to Improve the Deployment of Machine Learning Models
Oracle open-sourced Graphpipe, a tool created to make it easy to serve machine learning models in the cloud made by popular frameworks like TensorFlow, MXNet, Caffe2, and PyTorch.
GraphPipe is designed to solve three particular challenges: First, there’s no standard for model serving APIs, meaning business applications typically need a bespoke client to communicate with a deployed model. Next, building a model server is simply hard, and there are few out-of-the-box solutions for deployment. Lastly, the solutions that enterprises typically use now — like a python-JSON API — don’t provide the performance needed for critical business applications.
GraphPipe includes: a set of flatbuffer definitions, guidelines for serving models consistently according to the flatbuffer definitions, examples for serving models from various machine learning frameworks, and client libraries for querying models served via GraphPipe.
With these tools, a business should be able to deploy a model across multiple servers, or create an ensemble of models from different frameworks, with a common protocol. GraphPipe should also help deploy machine learning for IoT applications that rely on running models remotely.
The tool is available for free on Github and joins a series of open source tools launched in recent years for developers who want to use AI.