The documentation is generated based on the sources available at dotnet/machinelearning and released under MIT License.

Type: command Aliases: SaveOnnx Namespace: Microsoft.ML.Runtime.Model.Onnx Assembly: Microsoft.ML.Onnx.dll Microsoft Documentation: Save ONNX


Given a data model, write out the corresponding ONNX.


Name Short name Default Description
dataFile data   The data file
domain     The ‘domain’ property in the output ONNX.
inputModelFile in   Model file to load
inputsToDrop idrop   Comma delimited list of input column names to drop
json     The path to write the output JSON to.
loadPredictor pred   Whether we should attempt to load the predictor and attach the scorer to the pipeline if one is present.
loadTransforms loadTrans   Load transforms from model file?
loader     The data loader
name     The ‘name’ property in the output ONNX. By default this will be the ONNX extension-less name.
onnx     The path to write the output ONNX to.
onnxVersion   Stable The targeted ONNX version. It can be either “Stable” or “Experimental”. If “Experimental” is used, produced model can contain components that is not officially supported in ONNX standard.
outputModelFile out   Model file to save
outputsToDrop odrop   Comma delimited list of output column names to drop
parallel n   Desired degree of parallelism in the data pipeline
randomSeed seed   Random seed
server     The web server to publish the RESTful API
transform xf   Transform
verbose v   Verbose?