ML.net Add New Data to Exist Generated Model [closed]

问题

Closed. This question needs to be more focused. It is not currently accepting answers.

---

Want to improve this question? Update the question so it focuses on one problem only by editing this post.

Closed 9 months ago.

i generated a ML Model Using ML.Net V 0.7.0 last version

i need to add a new learning data to this existing Model without regenerated it with the new and old data

as i have a large data set that exceed 100 Million Record

and i need to add 100 record without reload all last data set to generate the new model

any ideas please

this is critical for me

best regards

回答1:

Some trainers in ML.NET support training with an initial predictor, which means you can use an existing predictor as the starting point for training with new data.

A test showing this can be found here with the relevant code being:

// Train the first predictor.
var trainer = ml.BinaryClassification.Trainers.StochasticDualCoordinateAscent("Label", "Features",advancedSettings: s => s.NumThreads = 1);
var firstModel = trainer.Fit(trainData);

// Train the second predictor on the same data.
var secondTrainer = ml.BinaryClassification.Trainers.AveragedPerceptron("Label","Features");

var trainRoles = new RoleMappedData(trainData, label: "Label", feature: "Features");
var finalModel = secondTrainer.Train(new TrainContext(trainRoles, initialPredictor: firstModel.Model));

来源：https://stackoverflow.com/questions/53318863/ml-net-add-new-data-to-exist-generated-model