SelfSupervisedLearningPretrainingPipeline<T>

Models & Types · AiDotNet.SelfSupervisedLearning

High-level pipeline for SSL pretraining.

For Beginners

This pipeline provides a simple, high-level interface for SSL pretraining. Just provide your encoder and data, and it handles the rest: method selection, augmentation, training loop, and evaluation.

How It Works

Example usage:

Constructors

Constructor Summary
SelfSupervisedLearningPretrainingPipeline(INeuralNetwork<T> encoder, int encoderOutputDim) Initializes a new SSL pretraining pipeline.

Methods

Method Summary
SelfSupervisedLearningPretrainingPipeline<T> WithConfig(Action<SelfSupervisedLearningConfig<T>> configure) Configures the training parameters.
SelfSupervisedLearningPretrainingPipeline<T> WithMethod(ISelfSupervisedLearningMethod<T> method) Sets the SSL method to use.
SelfSupervisedLearningResult<T> Train(Func<IEnumerable<Tensor<T>>> dataLoader, Tensor<T> validationData, int[] validationLabels) Trains the encoder using SSL.