Detections Transformation¶
Version v1¶
Block changes detected Bounding Boxes in a way specified in configuration.
It supports such operations as changing the size of Bounding Boxes.
Type identifier¶
Use the following identifier in step "type" field: roboflow_core/detections_transformation@v1to add the block as
as step in your workflow.
Properties¶
| Name | Type | Description | Refs |
|---|---|---|---|
name |
str |
The unique name of this step.. | ❌ |
operations |
List[Union[ClassificationPropertyExtract, DetectionsFilter, DetectionsOffset, DetectionsPropertyExtract, DetectionsRename, DetectionsSelection, DetectionsShift, Divide, ExtractDetectionProperty, ExtractImageProperty, LookupTable, Multiply, NumberRound, NumericSequenceAggregate, RandomNumber, SequenceAggregate, SequenceApply, SequenceLength, SequenceMap, SortDetections, StringMatches, StringSubSequence, StringToLowerCase, StringToUpperCase, ToBoolean, ToNumber, ToString]] |
Definition of transformations to be applied on detections. | ❌ |
The Refs column marks possibility to parametrise the property with dynamic values available
in workflow runtime. See Bindings for more info.
Available Connections¶
Check what blocks you can connect to Detections Transformation in version v1.
- inputs:
Color Visualization,Continue If,Detections Filter,Detections Consensus,Image Preprocessing,Mask Visualization,Model Comparison Visualization,Byte Tracker,Image Slicer,Keypoint Detection Model,OCR Model,Label Visualization,Time in zone,Detections Classes Replacement,Relative Static Crop,Polygon Visualization,Camera Focus,Florence-2 Model,LMM For Classification,Crop Visualization,Dimension Collapse,Multi-Label Classification Model,Line Counter,Line Counter,Google Vision OCR,Clip Comparison,Roboflow Dataset Upload,Barcode Detection,Path deviation,Circle Visualization,SIFT Comparison,JSON Parser,CogVLM,Anthropic Claude,Object Detection Model,OpenAI,Image Convert Grayscale,Pixel Color Count,Perspective Correction,Line Counter Visualization,Background Color Visualization,Detections Stitch,Bounding Box Visualization,Polygon Zone Visualization,Dynamic Zone,Pixelate Visualization,Triangle Visualization,Bounding Rectangle,VLM as Classifier,Blur Visualization,Image Contours,Path deviation,Dot Visualization,Corner Visualization,Detection Offset,Clip Comparison,Image Blur,Expression,Dynamic Crop,YOLO-World Model,Halo Visualization,Segment Anything 2 Model,First Non Empty Or Default,Image Threshold,QR Code Detection,SIFT,LMM,OpenAI,VLM as Detector,SIFT Comparison,Google Gemini,Byte Tracker,Size Measurement,Stability AI Inpainting,Detections Transformation,Absolute Static Crop,Distance Measurement,Property Definition,Dominant Color,Template Matching,Ellipse Visualization,Time in zone,Roboflow Dataset Upload,Instance Segmentation Model,Single-Label Classification Model,Roboflow Custom Metadata,Stitch Images - outputs:
Color Visualization,Detections Filter,Detections Consensus,Path deviation,Model Comparison Visualization,Mask Visualization,Dot Visualization,Corner Visualization,Byte Tracker,Detection Offset,Label Visualization,Time in zone,Detections Classes Replacement,Florence-2 Model,Polygon Visualization,Dynamic Crop,Halo Visualization,Segment Anything 2 Model,Crop Visualization,Line Counter,Line Counter,Roboflow Dataset Upload,Path deviation,Circle Visualization,Byte Tracker,Size Measurement,Stability AI Inpainting,Detections Transformation,Perspective Correction,Background Color Visualization,Distance Measurement,Detections Stitch,Property Definition,Bounding Box Visualization,Ellipse Visualization,Pixelate Visualization,Dynamic Zone,Time in zone,Triangle Visualization,Roboflow Dataset Upload,Roboflow Custom Metadata,Bounding Rectangle,Blur Visualization
The available connections depend on its binding kinds. Check what binding kinds
Detections Transformation in version v1 has.
Bindings
-
input
predictions(Union[object_detection_prediction,keypoint_detection_prediction,instance_segmentation_prediction]): Reference to detection-like predictions.operations_parameters(Union[image,*]): References to additional parameters that may be provided in runtime to parameterize operations.
-
output
predictions(Union[object_detection_prediction,instance_segmentation_prediction,keypoint_detection_prediction]): Prediction with detected bounding boxes in form of sv.Detections(...) object ifobject_detection_predictionor Prediction with detected bounding boxes and segmentation masks in form of sv.Detections(...) object ifinstance_segmentation_predictionor Prediction with detected bounding boxes and detected keypoints in form of sv.Detections(...) object ifkeypoint_detection_prediction.
Example JSON definition of step Detections Transformation in version v1
{
"name": "<your_step_name_here>",
"type": "roboflow_core/detections_transformation@v1",
"predictions": "$steps.object_detection_model.predictions",
"operations": [
{
"filter_operation": {
"statements": [
{
"comparator": {
"type": "in (Sequence)"
},
"left_operand": {
"operations": [
{
"property_name": "class_name",
"type": "ExtractDetectionProperty"
}
],
"type": "DynamicOperand"
},
"right_operand": {
"operand_name": "classes",
"type": "DynamicOperand"
},
"type": "BinaryStatement"
}
],
"type": "StatementGroup"
},
"type": "DetectionsFilter"
}
],
"operations_parameters": {
"classes": "$inputs.classes"
}
}