ModelObjectDetection class
Model wrapper for PyTorch object detection tasks.
Provides methods for running object detection predictions with configurable confidence thresholds and result filtering. Also includes functionality to render detection results on images.
Constructors
Properties
- hashCode → int
-
The hash code for this object.
no setterinherited
- imageHeight → int
-
final
- imageWidth → int
-
final
-
labels
→ List<
String> -
final
- runtimeType → Type
-
A representation of the runtime type of the object.
no setterinherited
Methods
-
getImagePrediction(
Uint8List imageAsBytes, {double minimumScore = 0.5, double IOUThershold = 0.5, int boxesLimit = 10}) → Future< List< ResultObjectDetection?> > - Runs object detection and returns filtered results.
-
getImagePredictionFromBytesList(
List< Uint8List> imageAsBytesList, int imageWidth, int imageHeight, {double minimumScore = 0.5, double IOUThershold = 0.5, int boxesLimit = 10}) → Future<List< ResultObjectDetection?> > - Runs batch object detection and returns filtered results.
-
getImagePredictionList(
Uint8List imageAsBytes, {double minimumScore = 0.5, double IOUThershold = 0.5, int boxesLimit = 10}) → Future< List< ResultObjectDetection?> > - Runs object detection and returns raw results.
-
getImagePredictionListFromBytesList(
List< Uint8List> imageAsBytesList, int imageWidth, int imageHeight, {double minimumScore = 0.5, double IOUThershold = 0.5, int boxesLimit = 10}) → Future<List< ResultObjectDetection?> > - Runs batch object detection and returns raw results.
-
noSuchMethod(
Invocation invocation) → dynamic -
Invoked when a nonexistent method or property is accessed.
inherited
-
renderBoxesOnImage(
File image, List< ResultObjectDetection?> recognitions, {Color? boxesColor, bool showPercentage = true}) → Widget - Renders object detection results as an overlay on the original image.
-
toString(
) → String -
A string representation of this object.
inherited
Operators
-
operator ==(
Object other) → bool -
The equality operator.
inherited