Detections Classes Replacement¶
Combine results of detection model with classification results performed separately for each and every bounding box.
Bounding boxes without top class predicted by classification model are discarded, for multi-label classification results, most confident label is taken as bounding box class.
Type identifier¶
Use the following identifier in step "type" field: roboflow_core/detections_classes_replacement@v1to add the block as
as step in your workflow.
Properties¶
| Name | Type | Description | Refs |
|---|---|---|---|
name |
str |
Enter a unique identifier for this step.. | ❌ |
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 Classes Replacement in version v1.
- inputs:
Detection Offset,YOLO-World Model,Google Vision OCR,Time in Zone,Object Detection Model,Detections Transformation,VLM as Detector,Detections Stitch,Bounding Rectangle,Multi-Label Classification Model,Time in Zone,VLM as Detector,Path Deviation,Object Detection Model,Keypoint Detection Model,Detections Filter,Single-Label Classification Model,VLM as Classifier,Clip Comparison,Detections Stabilizer,Detections Classes Replacement,VLM as Classifier,Byte Tracker,Byte Tracker,Segment Anything 2 Model,Template Matching,Detections Consensus,Instance Segmentation Model,Byte Tracker,Instance Segmentation Model,Keypoint Detection Model,Gaze Detection,Path Deviation,Multi-Label Classification Model,Single-Label Classification Model,Perspective Correction,Line Counter - outputs:
Detection Offset,Line Counter,Trace Visualization,Polygon Visualization,Detections Stitch,Distance Measurement,Time in Zone,Halo Visualization,Path Deviation,Triangle Visualization,Detections Filter,Florence-2 Model,Background Color Visualization,Keypoint Visualization,Byte Tracker,Segment Anything 2 Model,Corner Visualization,Mask Visualization,Roboflow Dataset Upload,Dynamic Zone,Dot Visualization,Perspective Correction,Roboflow Dataset Upload,Dynamic Crop,Time in Zone,Detections Transformation,Stitch OCR Detections,Stability AI Inpainting,Bounding Rectangle,Bounding Box Visualization,Color Visualization,Circle Visualization,Model Monitoring Inference Aggregator,Florence-2 Model,Blur Visualization,Detections Stabilizer,Detections Classes Replacement,Label Visualization,Pixelate Visualization,Byte Tracker,Ellipse Visualization,Crop Visualization,Roboflow Custom Metadata,Detections Consensus,Size Measurement,Byte Tracker,Model Comparison Visualization,Path Deviation,Line Counter
Input and Output Bindings¶
The available connections depend on its binding kinds. Check what binding kinds
Detections Classes Replacement in version v1 has.
Bindings
-
input
object_detection_predictions(Union[keypoint_detection_prediction,instance_segmentation_prediction,object_detection_prediction]): The output of a detection model describing the bounding boxes that will have classes replaced..classification_predictions(classification_prediction): The output of classification model for crops taken based on RoIs pointed as the other parameter.
-
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 Classes Replacement in version v1
{
"name": "<your_step_name_here>",
"type": "roboflow_core/detections_classes_replacement@v1",
"object_detection_predictions": "$steps.my_object_detection_model.predictions",
"classification_predictions": "$steps.my_classification_model.predictions"
}