Object Detection Model¶
v2¶
Class: RoboflowObjectDetectionModelBlockV2 (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 object-detection 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_object_detection_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.. | ✅ |
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 Object Detection Model in version v2.
- inputs:
Email Notification,Contrast Equalization,PTZ Tracking (ONVIF),Grid Visualization,S3 Sink,Stability AI Image Generation,Model Comparison Visualization,Identify Changes,Absolute Static Crop,Keypoint Visualization,SIFT,Trace Visualization,Roboflow Dataset Upload,Twilio SMS/MMS Notification,QR Code Generator,Buffer,Model Monitoring Inference Aggregator,Reference Path Visualization,Halo Visualization,SIFT Comparison,VLM As Classifier,VLM As Detector,Image Preprocessing,Crop Visualization,OpenAI,Identify Outliers,Label Visualization,Classification Label Visualization,Pixelate Visualization,OpenAI,Local File Sink,Twilio SMS Notification,Email Notification,Corner Visualization,Stitch Images,Background Subtraction,Morphological Transformation,Line Counter,Clip Comparison,Image Threshold,Background Color Visualization,Single-Label Classification Model,Anthropic Claude,Google Gemini,Camera Calibration,Halo Visualization,Stability AI Outpainting,Roboflow Custom Metadata,OpenAI,Ellipse Visualization,Dynamic Zone,VLM As Classifier,Heatmap Visualization,Image Convert Grayscale,Detections Consensus,Triangle Visualization,Semantic Segmentation Model,Image Blur,Depth Estimation,Size Measurement,Dimension Collapse,Color Visualization,SIFT Comparison,Camera Focus,Text Display,Anthropic Claude,Dot Visualization,Image Slicer,Template Matching,Polygon Visualization,Florence-2 Model,Motion Detection,Circle Visualization,Blur Visualization,Google Gemini,Slack Notification,Icon Visualization,Detections List Roll-Up,Camera Focus,Stability AI Inpainting,Polygon Visualization,Detection Event Log,Webhook Sink,Polygon Zone Visualization,Perspective Correction,Instance Segmentation Model,Florence-2 Model,Anthropic Claude,Mask Visualization,Google Gemini,Image Contours,Dynamic Crop,Clip Comparison,Llama 3.2 Vision,Distance Measurement,Roboflow Dataset Upload,JSON Parser,Keypoint Detection Model,Object Detection Model,Pixel Color Count,VLM As Detector,Image Slicer,Line Counter Visualization,Relative Static Crop,Multi-Label Classification Model,Line Counter,Bounding Box Visualization - outputs:
Detections Classes Replacement,Byte Tracker,Instance Segmentation Model,PTZ Tracking (ONVIF),ByteTrack Tracker,Model Comparison Visualization,Roboflow Dataset Upload,Trace Visualization,SAM 3,Model Monitoring Inference Aggregator,GLM-OCR,Time in Zone,Detections Stabilizer,SORT Tracker,Crop Visualization,Label Visualization,Pixelate Visualization,Qwen3.5-VL,Stitch OCR Detections,Corner Visualization,Time in Zone,Mask Area Measurement,Time in Zone,Stitch OCR Detections,Qwen2.5-VL,SAM 3,Path Deviation,Line Counter,Single-Label Classification Model,Background Color Visualization,Roboflow Custom Metadata,Single-Label Classification Model,Ellipse Visualization,Detections Stitch,Heatmap Visualization,Velocity,Detections Consensus,Triangle Visualization,Semantic Segmentation Model,Size Measurement,Detections Filter,Detections Transformation,Color Visualization,Overlap Filter,Dot Visualization,SmolVLM2,SAM 3,Keypoint Detection Model,Detections Combine,Florence-2 Model,Circle Visualization,Blur Visualization,Qwen3-VL,Multi-Label Classification Model,Detections Merge,Icon Visualization,Detections List Roll-Up,Camera Focus,Detection Offset,Line Counter,Detection Event Log,Webhook Sink,Florence-2 Model,Perspective Correction,Instance Segmentation Model,Moondream2,Roboflow Dataset Upload,Distance Measurement,Byte Tracker,Dynamic Crop,Keypoint Detection Model,Object Detection Model,Object Detection Model,Byte Tracker,Path Deviation,Multi-Label Classification Model,OC-SORT Tracker,Bounding Box Visualization,Segment Anything 2 Model
Input and Output Bindings¶
The available connections depend on its binding kinds. Check what binding kinds
Object Detection 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..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(object_detection_prediction): Prediction with detected bounding boxes in form of sv.Detections(...) object.model_id(roboflow_model_id): Roboflow model id.
Example JSON definition of step Object Detection Model in version v2
{
"name": "<your_step_name_here>",
"type": "roboflow_core/roboflow_object_detection_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,
"disable_active_learning": true,
"active_learning_target_dataset": "my_project"
}
v1¶
Class: RoboflowObjectDetectionModelBlockV1 (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 object-detection 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_object_detection_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.. | ✅ |
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 Object Detection Model in version v1.
- inputs:
Email Notification,Contrast Equalization,PTZ Tracking (ONVIF),Grid Visualization,S3 Sink,Stability AI Image Generation,Model Comparison Visualization,Identify Changes,Absolute Static Crop,Keypoint Visualization,SIFT,Trace Visualization,Roboflow Dataset Upload,Twilio SMS/MMS Notification,QR Code Generator,Buffer,Model Monitoring Inference Aggregator,Reference Path Visualization,Halo Visualization,SIFT Comparison,VLM As Classifier,VLM As Detector,Image Preprocessing,Crop Visualization,OpenAI,Identify Outliers,Label Visualization,Classification Label Visualization,Pixelate Visualization,OpenAI,Local File Sink,Twilio SMS Notification,Email Notification,Corner Visualization,Stitch Images,Background Subtraction,Morphological Transformation,Line Counter,Clip Comparison,Image Threshold,Background Color Visualization,Single-Label Classification Model,Anthropic Claude,Google Gemini,Camera Calibration,Halo Visualization,Stability AI Outpainting,Roboflow Custom Metadata,OpenAI,Ellipse Visualization,Dynamic Zone,VLM As Classifier,Heatmap Visualization,Image Convert Grayscale,Detections Consensus,Triangle Visualization,Semantic Segmentation Model,Image Blur,Depth Estimation,Size Measurement,Dimension Collapse,Color Visualization,SIFT Comparison,Camera Focus,Text Display,Anthropic Claude,Dot Visualization,Image Slicer,Template Matching,Polygon Visualization,Florence-2 Model,Motion Detection,Circle Visualization,Blur Visualization,Google Gemini,Slack Notification,Icon Visualization,Detections List Roll-Up,Camera Focus,Stability AI Inpainting,Polygon Visualization,Detection Event Log,Webhook Sink,Polygon Zone Visualization,Perspective Correction,Instance Segmentation Model,Florence-2 Model,Anthropic Claude,Mask Visualization,Google Gemini,Image Contours,Dynamic Crop,Clip Comparison,Llama 3.2 Vision,Distance Measurement,Roboflow Dataset Upload,JSON Parser,Keypoint Detection Model,Object Detection Model,Pixel Color Count,VLM As Detector,Image Slicer,Line Counter Visualization,Relative Static Crop,Multi-Label Classification Model,Line Counter,Bounding Box Visualization - outputs:
Detections Classes Replacement,Instance Segmentation Model,PTZ Tracking (ONVIF),Google Vision OCR,Contrast Equalization,ByteTrack Tracker,Trace Visualization,Twilio SMS/MMS Notification,QR Code Generator,SAM 3,GLM-OCR,SORT Tracker,Perception Encoder Embedding Model,OpenAI,OpenAI,Label Visualization,Pixelate Visualization,Twilio SMS Notification,Email Notification,Corner Visualization,Mask Area Measurement,Time in Zone,Morphological Transformation,SAM 3,Path Deviation,Line Counter,OpenAI,Clip Comparison,Background Color Visualization,Stability AI Outpainting,Ellipse Visualization,Detections Stitch,Heatmap Visualization,Velocity,Detections Consensus,Cache Get,Size Measurement,Detections Filter,Color Visualization,SAM 3,Detections Combine,Polygon Visualization,Blur Visualization,LMM,Slack Notification,Stability AI Inpainting,Detection Event Log,Florence-2 Model,Perspective Correction,Instance Segmentation Model,Anthropic Claude,Mask Visualization,Moondream2,YOLO-World Model,Byte Tracker,Pixel Color Count,Dynamic Crop,Path Deviation,Line Counter,Byte Tracker,Email Notification,S3 Sink,Stability AI Image Generation,Model Comparison Visualization,Keypoint Visualization,Roboflow Dataset Upload,CLIP Embedding Model,Model Monitoring Inference Aggregator,Reference Path Visualization,Cache Set,Halo Visualization,SIFT Comparison,Time in Zone,Detections Stabilizer,Image Preprocessing,Crop Visualization,Classification Label Visualization,Local File Sink,Stitch OCR Detections,Time in Zone,Stitch OCR Detections,LMM For Classification,Image Threshold,Anthropic Claude,Google Gemini,Halo Visualization,CogVLM,Roboflow Custom Metadata,OpenAI,Triangle Visualization,Image Blur,Depth Estimation,Detections Transformation,Overlap Filter,Text Display,Anthropic Claude,Dot Visualization,Florence-2 Model,Circle Visualization,Google Gemini,Detections Merge,Icon Visualization,Detections List Roll-Up,Camera Focus,Detection Offset,Polygon Visualization,Webhook Sink,Polygon Zone Visualization,Google Gemini,Roboflow Dataset Upload,Llama 3.2 Vision,Distance Measurement,Seg Preview,Byte Tracker,Line Counter Visualization,OC-SORT Tracker,Bounding Box Visualization,Segment Anything 2 Model
Input and Output Bindings¶
The available connections depend on its binding kinds. Check what binding kinds
Object Detection 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..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(object_detection_prediction): Prediction with detected bounding boxes in form of sv.Detections(...) object.
Example JSON definition of step Object Detection Model in version v1
{
"name": "<your_step_name_here>",
"type": "roboflow_core/roboflow_object_detection_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,
"disable_active_learning": true,
"active_learning_target_dataset": "my_project"
}