Dimension Collapse

Class: DimensionCollapseBlockV1

Source: inference.core.workflows.core_steps.fusion.dimension_collapse.v1.DimensionCollapseBlockV1

Takes multiple step outputs at data depth level n, concatenate them into list and reduce dimensionality to level n-1.

Useful in scenarios like: * aggregation of classification results for dynamically cropped images * aggregation of OCR results for dynamically cropped images

Type identifier

Use the following identifier in step "type" field: roboflow_core/dimension_collapse@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

Compatible Blocks

Check what blocks you can connect to Dimension Collapse in version v1.

• inputs: Image Convert Grayscale, Detections Stitch, YOLO-World Model, Dynamic Zone, Pixelate Visualization, SmolVLM2, Circle Visualization, Dynamic Crop, Dot Visualization, Absolute Static Crop, Keypoint Visualization, Byte Tracker, Roboflow Custom Metadata, LMM For Classification, Template Matching, Time in Zone, Detections Consensus, Roboflow Dataset Upload, Clip Comparison, Google Gemini, VLM as Classifier, Local File Sink, Bounding Rectangle, Gaze Detection, Florence-2 Model, Path Deviation, Path Deviation, Qwen2.5-VL, Camera Focus, Depth Estimation, Perspective Correction, Property Definition, Google Vision OCR, Single-Label Classification Model, Detections Stabilizer, Camera Calibration, Line Counter Visualization, Multi-Label Classification Model, VLM as Detector, Data Aggregator, OpenAI, Object Detection Model, Email Notification, Color Visualization, SIFT, Detections Classes Replacement, Pixel Color Count, Clip Comparison, Grid Visualization, Stitch Images, Reference Path Visualization, Detections Merge, SIFT Comparison, Velocity, Line Counter, Rate Limiter, JSON Parser, First Non Empty Or Default, Classification Label Visualization, Delta Filter, Blur Visualization, Polygon Zone Visualization, Identify Changes, Bounding Box Visualization, Cosine Similarity, SIFT Comparison, Segment Anything 2 Model, Keypoint Detection Model, Byte Tracker, VLM as Classifier, VLM as Detector, Image Threshold, Polygon Visualization, CogVLM, Time in Zone, Identify Outliers, Slack Notification, Model Comparison Visualization, Background Color Visualization, Cache Set, QR Code Detection, Byte Tracker, Cache Get, Expression, LMM, Detection Offset, Single-Label Classification Model, Florence-2 Model, Label Visualization, Image Slicer, Keypoint Detection Model, Triangle Visualization, Anthropic Claude, Corner Visualization, Stability AI Inpainting, Image Contours, Llama 3.2 Vision, Size Measurement, OCR Model, Line Counter, Model Monitoring Inference Aggregator, Instance Segmentation Model, Distance Measurement, Detections Transformation, Continue If, Moondream2, Image Slicer, Barcode Detection, Mask Visualization, Twilio SMS Notification, Crop Visualization, Relative Static Crop, Instance Segmentation Model, Overlap Filter, Buffer, Webhook Sink, Stitch OCR Detections, Ellipse Visualization, Dominant Color, Image Blur, Multi-Label Classification Model, Image Preprocessing, Roboflow Dataset Upload, OpenAI, Detections Filter, CLIP Embedding Model, Dimension Collapse, Object Detection Model, Trace Visualization, Halo Visualization, Stability AI Image Generation, Environment Secrets Store, CSV Formatter
• outputs: Instance Segmentation Model, Keypoint Detection Model, VLM as Classifier, Perspective Correction, VLM as Detector, Polygon Visualization, Line Counter Visualization, YOLO-World Model, VLM as Detector, Object Detection Model, Email Notification, Color Visualization, Time in Zone, Circle Visualization, Dot Visualization, Cache Set, Mask Visualization, Keypoint Visualization, Crop Visualization, Grid Visualization, Clip Comparison, LMM For Classification, Time in Zone, Florence-2 Model, Detections Consensus, Clip Comparison, Google Gemini, Bounding Box Visualization, Instance Segmentation Model, Buffer, Webhook Sink, Ellipse Visualization, VLM as Classifier, Reference Path Visualization, Label Visualization, Line Counter, Keypoint Detection Model, Triangle Visualization, Anthropic Claude, Florence-2 Model, Corner Visualization, OpenAI, Classification Label Visualization, Path Deviation, Path Deviation, Llama 3.2 Vision, Polygon Zone Visualization, Size Measurement, Object Detection Model, Trace Visualization, Halo Visualization, Line Counter

Input and Output Bindings

The available connections depend on its binding kinds. Check what binding kinds Dimension Collapse in version v1 has.

Bindings

• input

  • data (*): Reference to step outputs at depth level n to be concatenated and moved into level n-1..

• output

  • output (list_of_values): List of values of any type.

Example JSON definition of step Dimension Collapse in version v1

{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/dimension_collapse@v1",
    "data": "$steps.ocr_step.results"
}