ITextDetectionTrainingModel<T>

Interfaces · AiDotNet.Interfaces

A text detector that trains on text polygons, using its paper’s target assignment and loss (DBNet’s shrunk-kernel and border maps, CRAFT’s character and affinity heatmaps, EAST’s score and geometry maps).

Known implementations: TextDetectorBase<T>

Methods

Method Summary
void TrainTextDetections(Tensor<T> images, TextDetectionTrainingBatch targets) One training step on page images and the text regions annotated on each.