Multi-Label Classification Model

v2

Class: RoboflowMultiLabelClassificationModelBlockV2 (there are multiple versions of this block)

Source: inference.core.workflows.core_steps.models.roboflow.multi_label_classification.v2.RoboflowMultiLabelClassificationModelBlockV2

Warning: This block has multiple versions. Please refer to the specific version for details. You can learn more about how versions work here: Versioning

Run inference on a multi-label classification model hosted on or uploaded to Roboflow.

You can query any model that is private to your account, or any public model available on Roboflow Universe.

You will need to set your Roboflow API key in your Inference environment to use this block. To learn more about setting your Roboflow API key, refer to the Inference documentation.

Type identifier

Use the following identifier in step "type" field: roboflow_core/roboflow_multi_label_classification_model@v2to add the block as as step in your workflow.

Properties

Name	Type	Description	Refs
name	str	Enter a unique identifier for this step..	❌
model_id	str	Roboflow model identifier..	✅
confidence	float	Confidence threshold for predictions..	✅
disable_active_learning	bool	Boolean flag to disable project-level active learning for this block..	✅
active_learning_target_dataset	str	Target dataset for active learning, if enabled..	✅

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 Multi-Label Classification Model in version v2.

• inputs: Background Color Visualization, Detections Consensus, Circle Visualization, Polygon Visualization, Polygon Zone Visualization, Stability AI Outpainting, Grid Visualization, Image Slicer, Reference Path Visualization, Roboflow Custom Metadata, Single-Label Classification Model, Identify Changes, Color Visualization, Dynamic Crop, Image Contours, VLM as Detector, Blur Visualization, Model Monitoring Inference Aggregator, Stability AI Inpainting, SIFT Comparison, Relative Static Crop, Bounding Box Visualization, Absolute Static Crop, Identify Outliers, Multi-Label Classification Model, Trace Visualization, Halo Visualization, Classification Label Visualization, Crop Visualization, Camera Calibration, Stitch Images, Image Convert Grayscale, Camera Focus, Line Counter Visualization, Email Notification, Corner Visualization, Ellipse Visualization, VLM as Classifier, JSON Parser, Mask Visualization, Roboflow Dataset Upload, Perspective Correction, Dynamic Zone, Object Detection Model, Triangle Visualization, Model Comparison Visualization, Image Blur, Dot Visualization, Stability AI Image Generation, Depth Estimation, Instance Segmentation Model, Keypoint Visualization, Clip Comparison, VLM as Classifier, Webhook Sink, Twilio SMS Notification, VLM as Detector, Image Threshold, Image Preprocessing, Roboflow Dataset Upload, SIFT, SIFT Comparison, Local File Sink, Label Visualization, PTZ Tracking (ONVIF).md), Image Slicer, Pixelate Visualization, Keypoint Detection Model, Slack Notification
• outputs: Roboflow Custom Metadata, Single-Label Classification Model, Roboflow Dataset Upload, Moondream2, Multi-Label Classification Model, Object Detection Model, Single-Label Classification Model, Object Detection Model, Qwen2.5-VL, Instance Segmentation Model, Model Monitoring Inference Aggregator, Detections Classes Replacement, Keypoint Detection Model, Webhook Sink, Instance Segmentation Model, Roboflow Dataset Upload, SmolVLM2, Multi-Label Classification Model, Classification Label Visualization, Keypoint Detection Model

Input and Output Bindings

The available connections depend on its binding kinds. Check what binding kinds Multi-Label Classification Model in version v2 has.

Bindings

• input

  • images (image): The image to infer on..
  • model_id (roboflow_model_id): Roboflow model identifier..
  • confidence (float_zero_to_one): Confidence threshold for predictions..
  • disable_active_learning (boolean): Boolean flag to disable project-level active learning for this block..
  • active_learning_target_dataset (roboflow_project): Target dataset for active learning, if enabled..

• output

  • predictions (classification_prediction): Predictions from classifier.
  • inference_id (inference_id): Inference identifier.
  • model_id (roboflow_model_id): Roboflow model id.

Example JSON definition of step Multi-Label Classification Model in version v2

{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/roboflow_multi_label_classification_model@v2",
    "images": "$inputs.image",
    "model_id": "my_project/3",
    "confidence": 0.3,
    "disable_active_learning": true,
    "active_learning_target_dataset": "my_project"
}

v1

Class: RoboflowMultiLabelClassificationModelBlockV1 (there are multiple versions of this block)

Source: inference.core.workflows.core_steps.models.roboflow.multi_label_classification.v1.RoboflowMultiLabelClassificationModelBlockV1

Warning: This block has multiple versions. Please refer to the specific version for details. You can learn more about how versions work here: Versioning

Run inference on a multi-label classification model hosted on or uploaded to Roboflow.

You can query any model that is private to your account, or any public model available on Roboflow Universe.

You will need to set your Roboflow API key in your Inference environment to use this block. To learn more about setting your Roboflow API key, refer to the Inference documentation.

Type identifier

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

Properties

Name	Type	Description	Refs
name	str	Enter a unique identifier for this step..	❌
model_id	str	Roboflow model identifier..	✅
confidence	float	Confidence threshold for predictions..	✅
disable_active_learning	bool	Boolean flag to disable project-level active learning for this block..	✅
active_learning_target_dataset	str	Target dataset for active learning, if enabled..	✅

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 Multi-Label Classification Model in version v1.

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

Input and Output Bindings

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

Bindings

• input

  • images (image): The image to infer on..
  • model_id (roboflow_model_id): Roboflow model identifier..
  • confidence (float_zero_to_one): Confidence threshold for predictions..
  • disable_active_learning (boolean): Boolean flag to disable project-level active learning for this block..
  • active_learning_target_dataset (roboflow_project): Target dataset for active learning, if enabled..

• output

  • predictions (classification_prediction): Predictions from classifier.
  • inference_id (string): String value.

Example JSON definition of step Multi-Label Classification Model in version v1

{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/roboflow_multi_label_classification_model@v1",
    "images": "$inputs.image",
    "model_id": "my_project/3",
    "confidence": 0.3,
    "disable_active_learning": true,
    "active_learning_target_dataset": "my_project"
}