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

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"
}