Semantic Segmentation Model¶
v2¶
Class: RoboflowSemanticSegmentationModelBlockV2 (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 a semantic segmentation model hosted on or uploaded to Roboflow.
Semantic segmentation assigns a class label to every pixel in the image, producing a dense segmentation mask rather than per-object bounding boxes or instance masks.
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_semantic_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_mode |
str |
How confidence thresholds are determined.. | ✅ |
custom_confidence |
float |
Custom confidence threshold for predictions.. | ✅ |
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 Semantic Segmentation Model in version v2.
- inputs:
VLM As Classifier,MoonshotAI Kimi,Stability AI Image Generation,Trace Visualization,Anthropic Claude,Icon Visualization,SIFT Comparison,Morphological Transformation,Color Visualization,LMM For Classification,Single-Label Classification Model,Perspective Correction,Corner Visualization,Roboflow Custom Metadata,Halo Visualization,Keypoint Detection Model,Qwen-VL,Email Notification,Halo Visualization,Object Detection Model,Google Gemma,Background Color Visualization,Ellipse Visualization,Email Notification,Twilio SMS/MMS Notification,Text Display,Polygon Visualization,Crop Visualization,Absolute Static Crop,Image Preprocessing,Model Monitoring Inference Aggregator,Relative Static Crop,OpenRouter,OpenAI,Florence-2 Model,OpenAI,Heatmap Visualization,OCR Model,Blur Visualization,Depth Estimation,Instance Segmentation Model,Stability AI Outpainting,Anthropic Claude,Google Gemini,Clip Comparison,Google Gemini,Background Subtraction,Keypoint Visualization,CSV Formatter,Webhook Sink,Stitch Images,Florence-2 Model,Current Time,Contrast Equalization,OpenAI,VLM As Detector,Google Gemini,Triangle Visualization,Slack Notification,SIFT,Multi-Label Classification Model,Local File Sink,Image Contours,Keypoint Detection Model,GLM-OCR,Roboflow Asset Library Attributes,Image Slicer,Polygon Zone Visualization,Contrast Enhancement,Google Gemma API,Semantic Segmentation Model,Stitch OCR Detections,Image Threshold,Line Counter Visualization,Semantic Segmentation Model,Multi-Label Classification Model,Camera Calibration,QR Code Generator,S3 Sink,Microsoft SQL Server Sink,Google Vision OCR,Twilio SMS Notification,Image Blur,Morphological Transformation,Camera Focus,Roboflow Vision Events,Stability AI Inpainting,Classification Label Visualization,Stitch OCR Detections,Event Writer,Grid Visualization,Qwen3.5-VL,Mask Visualization,Llama 3.2 Vision,Reference Path Visualization,Image Slicer,Label Visualization,Identify Outliers,OPC UA Writer Sink,Dot Visualization,Identify Changes,Dynamic Crop,Circle Visualization,Llama 3.2 Vision,Camera Focus,OpenAI-Compatible LLM,MoonshotAI Kimi,Single-Label Classification Model,CogVLM,Object Detection Model,Qwen 3.6 API,Detections Consensus,Bounding Box Visualization,Multi-Label Classification Model,LMM,OpenAI,Image Convert Grayscale,Instance Segmentation Model,Roboflow Visual Search,EasyOCR,Roboflow Dataset Upload,Instance Segmentation Model,Pixelate Visualization,Keypoint Detection Model,Instance Segmentation Model,Roboflow Dataset Upload,PLC Writer,Qwen 3.5 API,Anthropic Claude,Object Detection Model,MQTT Writer,Polygon Visualization,Model Comparison Visualization,Single-Label Classification Model - outputs:
Single-Label Classification Model,Semantic Segmentation Model,Semantic Segmentation Model,Qwen3.5,Qwen2.5-VL,Multi-Label Classification Model,Object Detection Model,Instance Segmentation Model,SmolVLM2,Webhook Sink,Single-Label Classification Model,Multi-Label Classification Model,SAM 3,Qwen-VL,Instance Segmentation Model,Keypoint Detection Model,Qwen3-VL,Moondream2,Object Detection Model,SAM2 Video Tracker,SAM 3,Instance Segmentation Model,Qwen3.5-VL,Mask Visualization,Keypoint Detection Model,Instance Segmentation Model,Multi-Label Classification Model,Object Detection Model,Keypoint Detection Model,Model Monitoring Inference Aggregator,GLM-OCR,SAM3 Video Tracker,SAM 3,Single-Label Classification Model
Input and Output Bindings¶
The available connections depend on its binding kinds. Check what binding kinds
Semantic Segmentation Model in version v2 has.
Bindings
-
input
images(image): The image to infer on..model_id(roboflow_model_id): Roboflow model identifier..confidence_mode(string): How confidence thresholds are determined..custom_confidence(float_zero_to_one): Custom confidence threshold for predictions..
-
output
inference_id(inference_id): Inference identifier.predictions(semantic_segmentation_prediction): Prediction with per-pixel class label and confidence for semantic segmentation.model_id(roboflow_model_id): Roboflow model id.
Example JSON definition of step Semantic Segmentation Model in version v2
{
"name": "<your_step_name_here>",
"type": "roboflow_core/roboflow_semantic_segmentation_model@v2",
"images": "$inputs.image",
"model_id": "my_project/3",
"confidence_mode": "<block_does_not_provide_example>",
"custom_confidence": 0.3
}
v1¶
Class: RoboflowSemanticSegmentationModelBlockV1 (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 a semantic segmentation model hosted on or uploaded to Roboflow.
Semantic segmentation assigns a class label to every pixel in the image, producing a dense segmentation mask rather than per-object bounding boxes or instance masks.
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_semantic_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.. | ✅ |
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 Semantic Segmentation Model in version v1.
- inputs:
Heatmap Visualization,Image Slicer,Polygon Zone Visualization,Contrast Enhancement,Semantic Segmentation Model,Stability AI Image Generation,Image Threshold,Line Counter Visualization,Trace Visualization,Semantic Segmentation Model,Multi-Label Classification Model,Blur Visualization,Object Detection Model,Camera Calibration,Depth Estimation,QR Code Generator,Stability AI Outpainting,Icon Visualization,SIFT Comparison,Morphological Transformation,Background Subtraction,Keypoint Visualization,Color Visualization,Single-Label Classification Model,Perspective Correction,Bounding Box Visualization,Corner Visualization,Stitch Images,Halo Visualization,Image Blur,Image Convert Grayscale,Morphological Transformation,Keypoint Detection Model,Camera Focus,Instance Segmentation Model,Contrast Equalization,Halo Visualization,Stability AI Inpainting,Object Detection Model,Roboflow Visual Search,Classification Label Visualization,Triangle Visualization,Instance Segmentation Model,Grid Visualization,Background Color Visualization,Mask Visualization,Ellipse Visualization,Pixelate Visualization,Keypoint Detection Model,Instance Segmentation Model,Reference Path Visualization,SIFT,Label Visualization,Image Slicer,Text Display,Multi-Label Classification Model,Dot Visualization,Polygon Visualization,Crop Visualization,Dynamic Crop,Absolute Static Crop,Circle Visualization,Image Contours,Image Preprocessing,Polygon Visualization,Relative Static Crop,Camera Focus,Model Comparison Visualization,Single-Label Classification Model - outputs:
Single-Label Classification Model,Semantic Segmentation Model,Semantic Segmentation Model,Qwen3.5,Qwen2.5-VL,Multi-Label Classification Model,Object Detection Model,Instance Segmentation Model,SmolVLM2,Webhook Sink,Single-Label Classification Model,Multi-Label Classification Model,SAM 3,Qwen-VL,Instance Segmentation Model,Keypoint Detection Model,Qwen3-VL,Moondream2,Object Detection Model,SAM2 Video Tracker,SAM 3,Instance Segmentation Model,Qwen3.5-VL,Mask Visualization,Keypoint Detection Model,Instance Segmentation Model,Multi-Label Classification Model,Object Detection Model,Keypoint Detection Model,Model Monitoring Inference Aggregator,GLM-OCR,SAM3 Video Tracker,SAM 3,Single-Label Classification Model
Input and Output Bindings¶
The available connections depend on its binding kinds. Check what binding kinds
Semantic Segmentation Model in version v1 has.
Bindings
-
input
images(image): The image to infer on..model_id(roboflow_model_id): Roboflow model identifier..
-
output
inference_id(inference_id): Inference identifier.predictions(semantic_segmentation_prediction): Prediction with per-pixel class label and confidence for semantic segmentation.model_id(roboflow_model_id): Roboflow model id.
Example JSON definition of step Semantic Segmentation Model in version v1
{
"name": "<your_step_name_here>",
"type": "roboflow_core/roboflow_semantic_segmentation_model@v1",
"images": "$inputs.image",
"model_id": "my_project/3"
}