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