Classification Label Visualization

Class: ClassificationLabelVisualizationBlockV1

Source: inference.core.workflows.core_steps.visualizations.classification_label.v1.ClassificationLabelVisualizationBlockV1

Visualizes classification predictions with customizable labels and positioning options. Perfect for creating clear, informative displays of model predictions!

How It Works

This visualization processes classification predictions by:

1. 🎯 Analyzing predictions based on task type (single-label or multi-label)

2. 📊 Organizing results by confidence score

3. 🎨 Rendering labels with customizable positioning and styling

Parameters

• task_type: Specifies how to handle predictions. Available options:

  • "single-label": Shows only the highest confidence prediction

  • "multi-label": Displays all predictions above threshold

• text_position: Controls label placement with 9 options:

  • Top: LEFT, CENTER, RIGHT
  • Center: LEFT, CENTER, RIGHT
  • Bottom: LEFT, CENTER, RIGHT

• text: Determines what information to display:

  • "Class": Only show class names
  • "Confidence": Only show confidence scores
  • "Class and Confidence": Show both

• text_padding: Controls spacing between labels and from image edges

Why Use This Visualization?

This is especially useful for:

• 🏷️ Creating clear, professional-looking prediction displays

• 📱 Supporting different UI layouts with flexible positioning

• 🎨 Customizing appearance for different use cases

• 📊 Showing prediction confidence in an intuitive way

Example Usage

Use this visualization after any classification model to display predictions in a clean, organized format. Perfect for both single predictions and multiple class probabilities.

Type identifier

Use the following identifier in step "type" field: roboflow_core/classification_label_visualization@v1to add the block as as step in your workflow.

Properties

Name	Type	Description	Refs
name	str	Enter a unique identifier for this step..	❌
copy_image	bool	Enable this option to create a copy of the input image for visualization, preserving the original. Use this when stacking multiple visualizations..	✅
color_palette	str	Select a color palette for the visualised elements..	✅
palette_size	int	Specify the number of colors in the palette. This applies when using custom or Matplotlib palettes..	✅
custom_colors	List[str]	Define a list of custom colors for bounding boxes in HEX format..	✅
color_axis	str	Choose how bounding box colors are assigned..	✅
text	str	The data to display in the text labels..	✅
text_position	str	The anchor position for placing the label..	✅
text_color	str	Color of the text..	✅
text_scale	float	Scale of the text..	✅
text_thickness	int	Thickness of the text characters..	✅
text_padding	int	Padding around the text in pixels..	✅
border_radius	int	Radius of the label in pixels..	✅

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 Classification Label Visualization in version v1.

• inputs: Detections Consensus, Circle Visualization, Polygon Zone Visualization, Image Slicer, Reference Path Visualization, Single-Label Classification Model, Image Contours, Dynamic Crop, Size Measurement, Distance Measurement, VLM as Detector, Blur Visualization, Stability AI Inpainting, SIFT Comparison, OpenAI, LMM For Classification, Instance Segmentation Model, Absolute Static Crop, Trace Visualization, Classification Label Visualization, Crop Visualization, Camera Calibration, Stitch Images, Line Counter Visualization, Email Notification, Corner Visualization, VLM as Classifier, Google Vision OCR, Dimension Collapse, Line Counter, Multi-Label Classification Model, Perspective Correction, Object Detection Model, Triangle Visualization, Image Blur, Pixel Color Count, Clip Comparison, Webhook Sink, Twilio SMS Notification, VLM as Detector, Image Preprocessing, CSV Formatter, Pixelate Visualization, Anthropic Claude, Buffer, JSON Parser, Background Color Visualization, Roboflow Custom Metadata, Polygon Visualization, Stability AI Outpainting, Grid Visualization, CogVLM, Identify Changes, Color Visualization, Google Gemini, Model Monitoring Inference Aggregator, Relative Static Crop, Bounding Box Visualization, Llama 3.2 Vision, Identify Outliers, Multi-Label Classification Model, Halo Visualization, Florence-2 Model, Image Convert Grayscale, Camera Focus, Template Matching, Clip Comparison, Single-Label Classification Model, Ellipse Visualization, OpenAI, OpenAI, Mask Visualization, Roboflow Dataset Upload, Dynamic Zone, Model Comparison Visualization, Line Counter, Dot Visualization, Stability AI Image Generation, Depth Estimation, Keypoint Visualization, LMM, VLM as Classifier, Keypoint Detection Model, OCR Model, Stitch OCR Detections, Image Threshold, Roboflow Dataset Upload, SIFT Comparison, SIFT, Local File Sink, PTZ Tracking (ONVIF).md), Label Visualization, Florence-2 Model, Image Slicer, Slack Notification
• outputs: Circle Visualization, Polygon Zone Visualization, Reference Path Visualization, Image Slicer, Single-Label Classification Model, Image Contours, Dynamic Crop, Qwen2.5-VL, VLM as Detector, Perception Encoder Embedding Model, Blur Visualization, Gaze Detection, Stability AI Inpainting, SIFT Comparison, OpenAI, LMM For Classification, Instance Segmentation Model, Absolute Static Crop, Trace Visualization, Classification Label Visualization, Crop Visualization, Segment Anything 2 Model, Camera Calibration, Stitch Images, Line Counter Visualization, Corner Visualization, Time in Zone, CLIP Embedding Model, VLM as Classifier, Google Vision OCR, Moondream2, Multi-Label Classification Model, Perspective Correction, Object Detection Model, Triangle Visualization, Image Blur, Pixel Color Count, Clip Comparison, VLM as Detector, Image Preprocessing, Pixelate Visualization, Anthropic Claude, Keypoint Detection Model, Buffer, Background Color Visualization, Polygon Visualization, Stability AI Outpainting, Byte Tracker, CogVLM, Color Visualization, Dominant Color, Google Gemini, Relative Static Crop, Bounding Box Visualization, Llama 3.2 Vision, SmolVLM2, Multi-Label Classification Model, YOLO-World Model, Halo Visualization, Florence-2 Model, Camera Focus, Image Convert Grayscale, Template Matching, QR Code Detection, Clip Comparison, OpenAI, Ellipse Visualization, Single-Label Classification Model, OpenAI, Mask Visualization, Roboflow Dataset Upload, Object Detection Model, Model Comparison Visualization, Dot Visualization, Stability AI Image Generation, Depth Estimation, Instance Segmentation Model, Keypoint Visualization, LMM, VLM as Classifier, Keypoint Detection Model, Barcode Detection, OCR Model, Image Threshold, Roboflow Dataset Upload, Florence-2 Model, SIFT, Label Visualization, Image Slicer, Detections Stabilizer, Detections Stitch

Input and Output Bindings

The available connections depend on its binding kinds. Check what binding kinds Classification Label Visualization in version v1 has.

Bindings

• input

  • image (image): The image to visualize on..
  • copy_image (boolean): Enable this option to create a copy of the input image for visualization, preserving the original. Use this when stacking multiple visualizations..
  • predictions (classification_prediction): Classification predictions..
  • color_palette (string): Select a color palette for the visualised elements..
  • palette_size (integer): Specify the number of colors in the palette. This applies when using custom or Matplotlib palettes..
  • custom_colors (list_of_values): Define a list of custom colors for bounding boxes in HEX format..
  • color_axis (string): Choose how bounding box colors are assigned..
  • text (string): The data to display in the text labels..
  • text_position (string): The anchor position for placing the label..
  • text_color (string): Color of the text..
  • text_scale (float): Scale of the text..
  • text_thickness (integer): Thickness of the text characters..
  • text_padding (integer): Padding around the text in pixels..
  • border_radius (integer): Radius of the label in pixels..

• output

  • image (image): Image in workflows.

Example JSON definition of step Classification Label Visualization in version v1

{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/classification_label_visualization@v1",
    "image": "$inputs.image",
    "copy_image": true,
    "predictions": "$steps.classification_model.predictions",
    "color_palette": "DEFAULT",
    "palette_size": 10,
    "custom_colors": [
        "#FF0000",
        "#00FF00",
        "#0000FF"
    ],
    "color_axis": "CLASS",
    "text": "LABEL",
    "text_position": "CENTER",
    "text_color": "WHITE",
    "text_scale": 1.0,
    "text_thickness": 1,
    "text_padding": 10,
    "border_radius": 0
}