Keypoint Detection Model¶
v2¶
Class: RoboflowKeypointDetectionModelBlockV2 (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 keypoint 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_keypoint_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.. | ✅ |
keypoint_confidence |
float |
Confidence threshold to predict a keypoint as visible.. | ✅ |
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 Keypoint Detection Model in version v2.
- inputs:
Heatmap Visualization,Pixelate Visualization,Roboflow Custom Metadata,Halo Visualization,Anthropic Claude,Distance Measurement,Halo Visualization,Contrast Equalization,Trace Visualization,Grid Visualization,Ellipse Visualization,Model Monitoring Inference Aggregator,Local File Sink,Webhook Sink,Dynamic Crop,Detection Event Log,Image Convert Grayscale,Corner Visualization,Polygon Zone Visualization,Circle Visualization,Model Comparison Visualization,Florence-2 Model,Image Slicer,Stability AI Outpainting,Dynamic Zone,Keypoint Visualization,Text Display,Anthropic Claude,Size Measurement,Clip Comparison,Twilio SMS Notification,Stability AI Inpainting,Roboflow Dataset Upload,SIFT Comparison,Reference Path Visualization,Image Blur,VLM As Classifier,QR Code Generator,JSON Parser,Instance Segmentation Model,VLM As Detector,Object Detection Model,Image Slicer,Icon Visualization,Background Color Visualization,Absolute Static Crop,Google Gemini,Label Visualization,Image Preprocessing,Classification Label Visualization,SIFT,OpenAI,Mask Visualization,Line Counter,VLM As Classifier,Detections Consensus,Bounding Box Visualization,PTZ Tracking (ONVIF),OpenAI,Slack Notification,Google Gemini,Triangle Visualization,Dimension Collapse,Detections List Roll-Up,Dot Visualization,Email Notification,Roboflow Dataset Upload,Twilio SMS/MMS Notification,Image Contours,Anthropic Claude,Email Notification,Florence-2 Model,Background Subtraction,Camera Calibration,Image Threshold,Multi-Label Classification Model,VLM As Detector,Single-Label Classification Model,Clip Comparison,Relative Static Crop,Identify Changes,Keypoint Detection Model,Crop Visualization,Template Matching,Stitch Images,Blur Visualization,Perspective Correction,Motion Detection,Camera Focus,Camera Focus,Line Counter Visualization,Color Visualization,Morphological Transformation,Llama 3.2 Vision,Google Gemini,Line Counter,SIFT Comparison,Buffer,Identify Outliers,Pixel Color Count,OpenAI,Stability AI Image Generation,Depth Estimation,Polygon Visualization,Polygon Visualization - outputs:
Single-Label Classification Model,Heatmap Visualization,Roboflow Custom Metadata,Pixelate Visualization,Detections Consensus,Byte Tracker,Bounding Box Visualization,Detections Filter,Detection Offset,Triangle Visualization,Trace Visualization,Detections List Roll-Up,Dot Visualization,Keypoint Detection Model,Ellipse Visualization,Model Monitoring Inference Aggregator,Segment Anything 2 Model,Webhook Sink,Dynamic Crop,Corner Visualization,Instance Segmentation Model,Circle Visualization,Model Comparison Visualization,Florence-2 Model,Florence-2 Model,SAM 3,Keypoint Visualization,Detections Merge,Multi-Label Classification Model,Moondream2,Single-Label Classification Model,Qwen2.5-VL,Keypoint Detection Model,Crop Visualization,Detections Classes Replacement,Roboflow Dataset Upload,Blur Visualization,Instance Segmentation Model,Detections Transformation,Color Visualization,SAM 3,SmolVLM2,SAM 3,Object Detection Model,Icon Visualization,Background Color Visualization,Qwen3-VL,Multi-Label Classification Model,Label Visualization,Qwen3.5-VL,Roboflow Dataset Upload,Object Detection Model
Input and Output Bindings¶
The available connections depend on its binding kinds. Check what binding kinds
Keypoint 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..keypoint_confidence(float_zero_to_one): Confidence threshold to predict a keypoint as visible..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(keypoint_detection_prediction): Prediction with detected bounding boxes and detected keypoints in form of sv.Detections(...) object.model_id(roboflow_model_id): Roboflow model id.
Example JSON definition of step Keypoint Detection Model in version v2
{
"name": "<your_step_name_here>",
"type": "roboflow_core/roboflow_keypoint_detection_model@v2",
"images": "$inputs.image",
"model_id": "my_project/3",
"confidence": 0.3,
"keypoint_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: RoboflowKeypointDetectionModelBlockV1 (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 keypoint 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_keypoint_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.. | ✅ |
keypoint_confidence |
float |
Confidence threshold to predict a keypoint as visible.. | ✅ |
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 Keypoint Detection Model in version v1.
- inputs:
Heatmap Visualization,Pixelate Visualization,Roboflow Custom Metadata,Halo Visualization,Anthropic Claude,Distance Measurement,Halo Visualization,Contrast Equalization,Trace Visualization,Grid Visualization,Ellipse Visualization,Model Monitoring Inference Aggregator,Local File Sink,Webhook Sink,Dynamic Crop,Detection Event Log,Image Convert Grayscale,Corner Visualization,Polygon Zone Visualization,Circle Visualization,Model Comparison Visualization,Florence-2 Model,Image Slicer,Stability AI Outpainting,Dynamic Zone,Keypoint Visualization,Text Display,Anthropic Claude,Size Measurement,Clip Comparison,Twilio SMS Notification,Stability AI Inpainting,Roboflow Dataset Upload,SIFT Comparison,Reference Path Visualization,Image Blur,VLM As Classifier,QR Code Generator,JSON Parser,Instance Segmentation Model,VLM As Detector,Object Detection Model,Image Slicer,Icon Visualization,Background Color Visualization,Absolute Static Crop,Google Gemini,Label Visualization,Image Preprocessing,Classification Label Visualization,SIFT,OpenAI,Mask Visualization,Line Counter,VLM As Classifier,Detections Consensus,Bounding Box Visualization,PTZ Tracking (ONVIF),OpenAI,Slack Notification,Google Gemini,Triangle Visualization,Dimension Collapse,Detections List Roll-Up,Dot Visualization,Email Notification,Roboflow Dataset Upload,Twilio SMS/MMS Notification,Image Contours,Anthropic Claude,Email Notification,Florence-2 Model,Background Subtraction,Camera Calibration,Image Threshold,Multi-Label Classification Model,VLM As Detector,Single-Label Classification Model,Clip Comparison,Relative Static Crop,Identify Changes,Keypoint Detection Model,Crop Visualization,Template Matching,Stitch Images,Blur Visualization,Perspective Correction,Motion Detection,Camera Focus,Camera Focus,Line Counter Visualization,Color Visualization,Morphological Transformation,Llama 3.2 Vision,Google Gemini,Line Counter,SIFT Comparison,Buffer,Identify Outliers,Pixel Color Count,OpenAI,Stability AI Image Generation,Depth Estimation,Polygon Visualization,Polygon Visualization - outputs:
Heatmap Visualization,Roboflow Custom Metadata,Pixelate Visualization,Time in Zone,Anthropic Claude,OpenAI,Halo Visualization,Distance Measurement,Halo Visualization,Contrast Equalization,Trace Visualization,Ellipse Visualization,Local File Sink,Webhook Sink,Model Monitoring Inference Aggregator,Dynamic Crop,Corner Visualization,Polygon Zone Visualization,Circle Visualization,Model Comparison Visualization,Florence-2 Model,Stability AI Outpainting,Keypoint Visualization,Text Display,Google Vision OCR,Time in Zone,Moondream2,Anthropic Claude,Size Measurement,Twilio SMS Notification,Stability AI Inpainting,Roboflow Dataset Upload,SIFT Comparison,Stitch OCR Detections,Image Blur,Reference Path Visualization,QR Code Generator,CogVLM,Instance Segmentation Model,LMM For Classification,Icon Visualization,Background Color Visualization,Google Gemini,OpenAI,Label Visualization,Classification Label Visualization,Image Preprocessing,Mask Visualization,Stability AI Image Generation,Path Deviation,Line Counter,Detections Stitch,YOLO-World Model,Bounding Box Visualization,Detections Consensus,Byte Tracker,PTZ Tracking (ONVIF),Slack Notification,OpenAI,Detections Filter,Roboflow Dataset Upload,Triangle Visualization,Detection Offset,Perception Encoder Embedding Model,Email Notification,Dot Visualization,Detections List Roll-Up,Twilio SMS/MMS Notification,Segment Anything 2 Model,Anthropic Claude,Instance Segmentation Model,Email Notification,Seg Preview,Stitch OCR Detections,LMM,Cache Get,Florence-2 Model,SAM 3,Image Threshold,Detections Merge,Clip Comparison,Crop Visualization,Detections Classes Replacement,Blur Visualization,Perspective Correction,Path Deviation,Llama 3.2 Vision,Line Counter Visualization,Color Visualization,Morphological Transformation,Google Gemini,Line Counter,Detections Transformation,SAM 3,SAM 3,Time in Zone,Pixel Color Count,CLIP Embedding Model,OpenAI,Cache Set,Google Gemini,Depth Estimation,Polygon Visualization,Polygon Visualization
Input and Output Bindings¶
The available connections depend on its binding kinds. Check what binding kinds
Keypoint 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..keypoint_confidence(float_zero_to_one): Confidence threshold to predict a keypoint as visible..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(keypoint_detection_prediction): Prediction with detected bounding boxes and detected keypoints in form of sv.Detections(...) object.
Example JSON definition of step Keypoint Detection Model in version v1
{
"name": "<your_step_name_here>",
"type": "roboflow_core/roboflow_keypoint_detection_model@v1",
"images": "$inputs.image",
"model_id": "my_project/3",
"confidence": 0.3,
"keypoint_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"
}