Using Predictors
Machine Learning on Device
NatML provides extensive infrastructure for making on-device predictions with predictors.
Users are billed a flat monthly subscription for Edge predictor usage. View our pricing plans.
Creating a Session
The first step in making a prediction is creating a Session
. The session provides the model graph, along with supplementary data needed to make predictions. The mutation requires an input
argument:
The createSession
mutation requires specifying an authorization header populated with your NatML access key:
{ "Authorization": "Bearer <HUB_ACCESS_KEY>
" }
See the Inspecting the Platform section of the Session
type for more information on the platform
.
See the Using the Predictor section of the Predictor
type for more information on the framework
.
If a format
is not specified, then it is inferred from the platform
.
Fetching the Model Graph
See the Fetching the Model Graph section of the Session
type. Once the graph is fetched, you can then create an on-device inference session with NatML SDK for your development framework.
You can cache the model graph on-device, but note that a specific model graph is only ever guaranteed to work on the exact device that created the Session
.
Last updated