Instance Segmentation Model

v2

Class: RoboflowInstanceSegmentationModelBlockV2 (there are multiple versions of this block)

Source: inference.core.workflows.core_steps.models.roboflow.instance_segmentation.v2.RoboflowInstanceSegmentationModelBlockV2

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 an instance segmentation 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_instance_segmentation_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..	✅
class_filter	List[str]	List of accepted classes. Classes must exist in the model's training set..	✅
iou_threshold	float	Minimum overlap threshold between boxes to combine them into a single detection, used in NMS. Learn more..	✅
max_detections	int	Maximum number of detections to return..	✅
class_agnostic_nms	bool	Boolean flag to specify if NMS is to be used in class-agnostic mode..	✅
max_candidates	int	Maximum number of candidates as NMS input to be taken into account..	✅
mask_decode_mode	str	Parameter of mask decoding in prediction post-processing..	✅
tradeoff_factor	float	Post-processing parameter to dictate tradeoff between fast and accurate..	✅
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 Instance Segmentation Model in version v2.

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

Input and Output Bindings

The available connections depend on its binding kinds. Check what binding kinds Instance Segmentation 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..
  • class_filter (list_of_values): List of accepted classes. Classes must exist in the model's training set..
  • iou_threshold (float_zero_to_one): Minimum overlap threshold between boxes to combine them into a single detection, used in NMS. Learn more..
  • max_detections (integer): Maximum number of detections to return..
  • class_agnostic_nms (boolean): Boolean flag to specify if NMS is to be used in class-agnostic mode..
  • max_candidates (integer): Maximum number of candidates as NMS input to be taken into account..
  • mask_decode_mode (string): Parameter of mask decoding in prediction post-processing..
  • tradeoff_factor (float_zero_to_one): Post-processing parameter to dictate tradeoff between fast and accurate..
  • 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

  • inference_id (inference_id): Inference identifier.
  • predictions (instance_segmentation_prediction): Prediction with detected bounding boxes and segmentation masks in form of sv.Detections(...) object.
  • model_id (roboflow_model_id): Roboflow model id.

Example JSON definition of step Instance Segmentation Model in version v2

{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/roboflow_instance_segmentation_model@v2",
    "images": "$inputs.image",
    "model_id": "my_project/3",
    "confidence": 0.3,
    "class_filter": [
        "a",
        "b",
        "c"
    ],
    "iou_threshold": 0.4,
    "max_detections": 300,
    "class_agnostic_nms": true,
    "max_candidates": 3000,
    "mask_decode_mode": "accurate",
    "tradeoff_factor": 0.3,
    "disable_active_learning": true,
    "active_learning_target_dataset": "my_project"
}

v1

Class: RoboflowInstanceSegmentationModelBlockV1 (there are multiple versions of this block)

Source: inference.core.workflows.core_steps.models.roboflow.instance_segmentation.v1.RoboflowInstanceSegmentationModelBlockV1

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 an instance segmentation 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_instance_segmentation_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..	✅
class_filter	List[str]	List of accepted classes. Classes must exist in the model's training set..	✅
iou_threshold	float	Minimum overlap threshold between boxes to combine them into a single detection, used in NMS. Learn more..	✅
max_detections	int	Maximum number of detections to return..	✅
class_agnostic_nms	bool	Boolean flag to specify if NMS is to be used in class-agnostic mode..	✅
max_candidates	int	Maximum number of candidates as NMS input to be taken into account..	✅
mask_decode_mode	str	Parameter of mask decoding in prediction post-processing..	✅
tradeoff_factor	float	Post-processing parameter to dictate tradeoff between fast and accurate..	✅
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 Instance Segmentation Model in version v1.

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

Input and Output Bindings

The available connections depend on its binding kinds. Check what binding kinds Instance Segmentation 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..
  • class_filter (list_of_values): List of accepted classes. Classes must exist in the model's training set..
  • iou_threshold (float_zero_to_one): Minimum overlap threshold between boxes to combine them into a single detection, used in NMS. Learn more..
  • max_detections (integer): Maximum number of detections to return..
  • class_agnostic_nms (boolean): Boolean flag to specify if NMS is to be used in class-agnostic mode..
  • max_candidates (integer): Maximum number of candidates as NMS input to be taken into account..
  • mask_decode_mode (string): Parameter of mask decoding in prediction post-processing..
  • tradeoff_factor (float_zero_to_one): Post-processing parameter to dictate tradeoff between fast and accurate..
  • 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

  • inference_id (string): String value.
  • predictions (instance_segmentation_prediction): Prediction with detected bounding boxes and segmentation masks in form of sv.Detections(...) object.

Example JSON definition of step Instance Segmentation Model in version v1

{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/roboflow_instance_segmentation_model@v1",
    "images": "$inputs.image",
    "model_id": "my_project/3",
    "confidence": 0.3,
    "class_filter": [
        "a",
        "b",
        "c"
    ],
    "iou_threshold": 0.4,
    "max_detections": 300,
    "class_agnostic_nms": true,
    "max_candidates": 3000,
    "mask_decode_mode": "accurate",
    "tradeoff_factor": 0.3,
    "disable_active_learning": true,
    "active_learning_target_dataset": "my_project"
}