ObjectDetectionHead class

A simple object detection head for a ViT backbone.

This head takes the output features from the ViT backbone (e.g., the CLS token output or aggregated patch features) and predicts bounding box coordinates and class probabilities for a single object.

For multi-object detection, a more advanced architecture like DETR's Transformer Decoder or R-CNN style heads would be required.

Inheritance

Constructors

ObjectDetectionHead({required int embedSize, required int numClasses})

Properties

bboxRegressionHead Layer
final
classPredictionHead Layer
final
embedSize int
final
hashCode int
The hash code for this object.
no setterinherited
numClasses int
final
runtimeType Type
A representation of the runtime type of the object.
no setterinherited

Methods

forward(ValueVector backboneFeature) Map<String, ValueVector>
Forward pass for the object detection head.
noSuchMethod(Invocation invocation) → dynamic
Invoked when a nonexistent method or property is accessed.
inherited
parameters() List<Value>
override
toString() String
A string representation of this object.
inherited
zeroGrad() → void
inherited

Operators

operator ==(Object other) bool
The equality operator.
inherited

Constants

numBoxCoords → const int