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

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"
}