Instance Segmentation Model¶
v2¶
Class: RoboflowInstanceSegmentationModelBlockV2 (there are multiple versions of this block)
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:
Dynamic Crop,Motion Detection,OCR Model,Email Notification,Image Blur,Background Subtraction,SIFT Comparison,OpenAI,Google Gemini,Google Vision OCR,Image Preprocessing,Instance Segmentation Model,Object Detection Model,Local File Sink,Single-Label Classification Model,Bounding Box Visualization,Multi-Label Classification Model,Anthropic Claude,Model Monitoring Inference Aggregator,Multi-Label Classification Model,Keypoint Detection Model,Email Notification,Slack Notification,Camera Focus,Identify Outliers,Twilio SMS/MMS Notification,VLM As Detector,Dot Visualization,Florence-2 Model,Roboflow Dataset Upload,CSV Formatter,Camera Focus,Stitch OCR Detections,Depth Estimation,Polygon Visualization,Perspective Correction,OpenAI,PTZ Tracking (ONVIF),Line Counter,Camera Calibration,Corner Visualization,Icon Visualization,Image Slicer,Detections List Roll-Up,Line Counter Visualization,Heatmap Visualization,Morphological Transformation,Stability AI Image Generation,Google Gemini,Distance Measurement,Keypoint Visualization,VLM As Detector,Halo Visualization,Keypoint Detection Model,Background Color Visualization,Label Visualization,Detection Event Log,JSON Parser,Polygon Visualization,Pixelate Visualization,LMM,CogVLM,Single-Label Classification Model,Contrast Equalization,Triangle Visualization,Stability AI Outpainting,Dimension Collapse,Mask Visualization,VLM As Classifier,Color Visualization,Instance Segmentation Model,Text Display,Relative Static Crop,Line Counter,Reference Path Visualization,Stitch OCR Detections,Llama 3.2 Vision,OpenAI,Image Threshold,Clip Comparison,Classification Label Visualization,Clip Comparison,Webhook Sink,Circle Visualization,Polygon Zone Visualization,Image Contours,Image Convert Grayscale,Grid Visualization,VLM As Classifier,Florence-2 Model,Buffer,Roboflow Custom Metadata,Dynamic Zone,LMM For Classification,SIFT,Halo Visualization,Template Matching,Object Detection Model,Semantic Segmentation Model,Detections Consensus,Anthropic Claude,Google Gemini,Model Comparison Visualization,Blur Visualization,QR Code Generator,EasyOCR,Absolute Static Crop,Image Slicer,S3 Sink,Anthropic Claude,Stability AI Inpainting,Ellipse Visualization,Identify Changes,Crop Visualization,SIFT Comparison,Qwen3.5-VL,Trace Visualization,Twilio SMS Notification,Stitch Images,Size Measurement,OpenAI,Pixel Color Count,Roboflow Dataset Upload - outputs:
Dynamic Crop,Time in Zone,Qwen2.5-VL,Time in Zone,Instance Segmentation Model,Object Detection Model,Single-Label Classification Model,Model Monitoring Inference Aggregator,Bounding Box Visualization,Multi-Label Classification Model,Multi-Label Classification Model,Keypoint Detection Model,Detections Stitch,Dot Visualization,Florence-2 Model,Roboflow Dataset Upload,Camera Focus,SAM 3,Polygon Visualization,Perspective Correction,PTZ Tracking (ONVIF),Moondream2,Line Counter,Icon Visualization,Corner Visualization,Overlap Filter,Detections List Roll-Up,Qwen3.5-VL,Heatmap Visualization,Distance Measurement,Byte Tracker,Halo Visualization,Keypoint Detection Model,Background Color Visualization,Label Visualization,Detection Event Log,Polygon Visualization,Pixelate Visualization,Time in Zone,Single-Label Classification Model,Qwen3-VL,Triangle Visualization,Mask Visualization,Color Visualization,Instance Segmentation Model,Detections Combine,Detections Classes Replacement,Bounding Rectangle,Line Counter,Webhook Sink,Circle Visualization,Mask Area Measurement,Byte Tracker,Florence-2 Model,SmolVLM2,SAM 3,Roboflow Custom Metadata,Dynamic Zone,Velocity,Halo Visualization,Object Detection Model,Byte Tracker,Detections Consensus,Semantic Segmentation Model,Model Comparison Visualization,Blur Visualization,Detection Offset,Path Deviation,SAM 3,Detections Transformation,Ellipse Visualization,Stability AI Inpainting,Path Deviation,Crop Visualization,Trace Visualization,Segment Anything 2 Model,Size Measurement,Detections Stabilizer,Detections Filter,Detections Merge,Roboflow Dataset Upload
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)
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:
Dynamic Crop,Motion Detection,OCR Model,Email Notification,Image Blur,Background Subtraction,SIFT Comparison,OpenAI,Google Gemini,Google Vision OCR,Image Preprocessing,Instance Segmentation Model,Object Detection Model,Local File Sink,Single-Label Classification Model,Bounding Box Visualization,Multi-Label Classification Model,Anthropic Claude,Model Monitoring Inference Aggregator,Multi-Label Classification Model,Keypoint Detection Model,Email Notification,Slack Notification,Camera Focus,Identify Outliers,Twilio SMS/MMS Notification,VLM As Detector,Dot Visualization,Florence-2 Model,Roboflow Dataset Upload,CSV Formatter,Camera Focus,Stitch OCR Detections,Depth Estimation,Polygon Visualization,Perspective Correction,OpenAI,PTZ Tracking (ONVIF),Line Counter,Camera Calibration,Corner Visualization,Icon Visualization,Image Slicer,Detections List Roll-Up,Line Counter Visualization,Heatmap Visualization,Morphological Transformation,Stability AI Image Generation,Google Gemini,Distance Measurement,Keypoint Visualization,VLM As Detector,Halo Visualization,Keypoint Detection Model,Background Color Visualization,Label Visualization,Detection Event Log,JSON Parser,Polygon Visualization,Pixelate Visualization,LMM,CogVLM,Single-Label Classification Model,Contrast Equalization,Triangle Visualization,Stability AI Outpainting,Dimension Collapse,Mask Visualization,VLM As Classifier,Color Visualization,Instance Segmentation Model,Text Display,Relative Static Crop,Line Counter,Reference Path Visualization,Stitch OCR Detections,Llama 3.2 Vision,OpenAI,Image Threshold,Clip Comparison,Classification Label Visualization,Clip Comparison,Webhook Sink,Circle Visualization,Polygon Zone Visualization,Image Contours,Image Convert Grayscale,Grid Visualization,VLM As Classifier,Florence-2 Model,Buffer,Roboflow Custom Metadata,Dynamic Zone,LMM For Classification,SIFT,Halo Visualization,Template Matching,Object Detection Model,Semantic Segmentation Model,Detections Consensus,Anthropic Claude,Google Gemini,Model Comparison Visualization,Blur Visualization,QR Code Generator,EasyOCR,Absolute Static Crop,Image Slicer,S3 Sink,Anthropic Claude,Stability AI Inpainting,Ellipse Visualization,Identify Changes,Crop Visualization,SIFT Comparison,Qwen3.5-VL,Trace Visualization,Twilio SMS Notification,Stitch Images,Size Measurement,OpenAI,Pixel Color Count,Roboflow Dataset Upload - outputs:
Dynamic Crop,Image Blur,Google Vision OCR,Google Gemini,Image Preprocessing,Local File Sink,Bounding Box Visualization,Model Monitoring Inference Aggregator,Dot Visualization,Florence-2 Model,Roboflow Dataset Upload,Depth Estimation,Polygon Visualization,OpenAI,Line Counter,Detections List Roll-Up,Line Counter Visualization,Heatmap Visualization,Google Gemini,Stability AI Image Generation,Morphological Transformation,Distance Measurement,Keypoint Visualization,Background Color Visualization,Label Visualization,Polygon Visualization,LMM,CogVLM,Time in Zone,Triangle Visualization,Stability AI Outpainting,Mask Visualization,Color Visualization,Detections Combine,Text Display,Bounding Rectangle,Reference Path Visualization,OpenAI,Llama 3.2 Vision,Image Threshold,Clip Comparison,Classification Label Visualization,Polygon Zone Visualization,Roboflow Custom Metadata,LMM For Classification,Dynamic Zone,Velocity,Halo Visualization,Blur Visualization,Path Deviation,Anthropic Claude,SAM 3,Detections Transformation,Ellipse Visualization,Crop Visualization,Path Deviation,Trace Visualization,Twilio SMS Notification,Size Measurement,Detections Stabilizer,Detections Merge,Time in Zone,Email Notification,OpenAI,SIFT Comparison,Seg Preview,Time in Zone,Instance Segmentation Model,Anthropic Claude,Email Notification,Slack Notification,Twilio SMS/MMS Notification,Detections Stitch,Cache Set,Camera Focus,SAM 3,Stitch OCR Detections,Perspective Correction,PTZ Tracking (ONVIF),Moondream2,Icon Visualization,Corner Visualization,Overlap Filter,Byte Tracker,Halo Visualization,Detection Event Log,Pixelate Visualization,Contrast Equalization,Instance Segmentation Model,Detections Classes Replacement,Line Counter,Stitch OCR Detections,Webhook Sink,Circle Visualization,Mask Area Measurement,Byte Tracker,Florence-2 Model,SAM 3,Perception Encoder Embedding Model,Cache Get,YOLO-World Model,Byte Tracker,Detections Consensus,Anthropic Claude,Google Gemini,Model Comparison Visualization,Detection Offset,QR Code Generator,S3 Sink,CLIP Embedding Model,Stability AI Inpainting,Segment Anything 2 Model,OpenAI,Pixel Color Count,Detections Filter,Roboflow Dataset Upload
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"
}