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: QR Code Generator, Qwen3-VL, Image Convert Grayscale, Google Gemini, QR Code Detection, Velocity, SIFT Comparison, Detection Offset, Blur Visualization, SIFT, Bounding Box Visualization, Stability AI Outpainting, Trace Visualization, Instance Segmentation Model, Pixel Color Count, Ellipse Visualization, Dimension Collapse, Model Comparison Visualization, OpenAI, Triangle Visualization, SAM 3, Distance Measurement, Byte Tracker, Environment Secrets Store, Stability AI Image Generation, Path Deviation, VLM as Detector, CLIP Embedding Model, Florence-2 Model, Single-Label Classification Model, Email Notification, Continue If, Google Gemini, Camera Focus, VLM as Classifier, Corner Visualization, Color Visualization, Twilio SMS/MMS Notification, Multi-Label Classification Model, Image Slicer, OpenAI, Property Definition, Buffer, Line Counter, Detections Transformation, SAM 3, Dot Visualization, Roboflow Custom Metadata, Data Aggregator, Image Threshold, Model Monitoring Inference Aggregator, Classification Label Visualization, OCR Model, Byte Tracker, Time in Zone, Roboflow Dataset Upload, Mask Visualization, Detections List Roll-Up, Pixelate Visualization, Line Counter, Keypoint Detection Model, Size Measurement, Detections Consensus, Webhook Sink, Stability AI Inpainting, Template Matching, Line Counter Visualization, Crop Visualization, OpenAI, Llama 3.2 Vision, Icon Visualization, Clip Comparison, Time in Zone, Background Subtraction, Delta Filter, LMM For Classification, SAM 3, Object Detection Model, CogVLM, Roboflow Dataset Upload, Overlap Filter, Cache Get, Detections Stitch, Detections Combine, Seg Preview, Byte Tracker, YOLO-World Model, Dynamic Crop, First Non Empty Or Default, Identify Changes, Camera Focus, Slack Notification, Keypoint Visualization, Polygon Visualization, Cache Set, Dominant Color, Anthropic Claude, Local File Sink, Qwen2.5-VL, Polygon Zone Visualization, Halo Visualization, LMM, Time in Zone, Circle Visualization, Detections Stabilizer, Google Vision OCR, Motion Detection, Clip Comparison, Cosine Similarity, Detections Classes Replacement, Anthropic Claude, Detections Filter, Object Detection Model, Instance Segmentation Model, Perspective Correction, Perception Encoder Embedding Model, CSV Formatter, Reference Path Visualization, EasyOCR, Stitch OCR Detections, Camera Calibration, Image Blur, SmolVLM2, VLM as Detector, Rate Limiter, Expression, Morphological Transformation, Label Visualization, Background Color Visualization, Keypoint Detection Model, Path Deviation, Dynamic Zone, Absolute Static Crop, PTZ Tracking (ONVIF).md), Moondream2, Grid Visualization, Contrast Equalization, Image Preprocessing, Google Gemini, Relative Static Crop, Barcode Detection, Image Contours, OpenAI, Stitch Images, JSON Parser, Bounding Rectangle, SIFT Comparison, Gaze Detection, Identify Outliers, Depth Estimation, Twilio SMS Notification, Single-Label Classification Model, VLM as Classifier, Florence-2 Model, Detections Merge, Multi-Label Classification Model, Segment Anything 2 Model, Image Slicer, Email Notification
• outputs: Seg Preview, YOLO-World Model, Google Gemini, Bounding Box Visualization, Keypoint Visualization, Trace Visualization, Instance Segmentation Model, Polygon Visualization, Cache Set, Ellipse Visualization, OpenAI, Anthropic Claude, Triangle Visualization, SAM 3, Polygon Zone Visualization, Halo Visualization, Time in Zone, Path Deviation, VLM as Detector, Florence-2 Model, Circle Visualization, Email Notification, Motion Detection, Google Gemini, Clip Comparison, Anthropic Claude, Object Detection Model, Instance Segmentation Model, Perspective Correction, VLM as Classifier, Reference Path Visualization, Corner Visualization, Color Visualization, Twilio SMS/MMS Notification, OpenAI, Line Counter, Buffer, VLM as Detector, SAM 3, Dot Visualization, Label Visualization, Time in Zone, Classification Label Visualization, Keypoint Detection Model, Roboflow Dataset Upload, Path Deviation, Mask Visualization, Detections List Roll-Up, Line Counter, Keypoint Detection Model, Size Measurement, Detections Consensus, Webhook Sink, Grid Visualization, Google Gemini, Line Counter Visualization, Crop Visualization, OpenAI, Llama 3.2 Vision, Clip Comparison, VLM as Classifier, Time in Zone, Florence-2 Model, LMM For Classification, SAM 3, Object Detection Model, Roboflow Dataset Upload, Email Notification

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"
}