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