Keypoint Detection Model¶
v3¶
Class: RoboflowKeypointDetectionModelBlockV3 (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@v3to 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 |
not available. | ✅ |
custom_confidence |
float |
not available. | ✅ |
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 v3.
- inputs:
Single-Label Classification Model,OpenAI,Anthropic Claude,SIFT,Multi-Label Classification Model,Halo Visualization,Google Gemini,Camera Focus,Image Convert Grayscale,SIFT Comparison,VLM As Detector,LMM For Classification,Template Matching,Detections List Roll-Up,Google Gemini,LMM,Email Notification,Color Visualization,Camera Calibration,SIFT Comparison,Background Subtraction,Polygon Visualization,Image Contours,Identify Outliers,Polygon Zone Visualization,Twilio SMS Notification,Roboflow Vision Events,Email Notification,Absolute Static Crop,Detections Consensus,PTZ Tracking (ONVIF),Label Visualization,Line Counter,Florence-2 Model,Llama 3.2 Vision,Object Detection Model,EasyOCR,Instance Segmentation Model,Crop Visualization,Roboflow Dataset Upload,Stitch OCR Detections,Bounding Box Visualization,Single-Label Classification Model,Heatmap Visualization,Icon Visualization,Anthropic Claude,Pixelate Visualization,Relative Static Crop,Camera Focus,Ellipse Visualization,Background Color Visualization,Qwen3.5-VL,Buffer,Dynamic Zone,Blur Visualization,Object Detection Model,Stitch Images,GLM-OCR,Contrast Equalization,Keypoint Detection Model,Perspective Correction,Triangle Visualization,Image Threshold,Halo Visualization,Trace Visualization,Classification Label Visualization,Florence-2 Model,Line Counter Visualization,OpenAI,VLM As Classifier,Detection Event Log,Keypoint Detection Model,Instance Segmentation Model,QR Code Generator,Text Display,Single-Label Classification Model,Slack Notification,OpenAI,Image Blur,Instance Segmentation Model,VLM As Classifier,Identify Changes,Multi-Label Classification Model,Mask Visualization,Anthropic Claude,Polygon Visualization,Dynamic Crop,Grid Visualization,VLM As Detector,Semantic Segmentation Model,Webhook Sink,Roboflow Custom Metadata,OpenAI,Image Slicer,Twilio SMS/MMS Notification,Circle Visualization,Object Detection Model,Local File Sink,JSON Parser,Stability AI Outpainting,Reference Path Visualization,Keypoint Detection Model,CogVLM,Dot Visualization,Dimension Collapse,Size Measurement,Model Monitoring Inference Aggregator,Pixel Color Count,Image Preprocessing,Clip Comparison,Stability AI Image Generation,Stability AI Inpainting,OCR Model,CSV Formatter,Stitch OCR Detections,Keypoint Visualization,Semantic Segmentation Model,Corner Visualization,Motion Detection,Morphological Transformation,Clip Comparison,Distance Measurement,Model Comparison Visualization,Roboflow Dataset Upload,Google Vision OCR,Google Gemini,Multi-Label Classification Model,Line Counter,Image Slicer,S3 Sink,Depth Estimation - outputs:
Single-Label Classification Model,Dot Visualization,Roboflow Dataset Upload,Multi-Label Classification Model,Bounding Box Visualization,SAM2 Video Tracker,Detections Classes Replacement,Model Monitoring Inference Aggregator,Single-Label Classification Model,Heatmap Visualization,SORT Tracker,Icon Visualization,ByteTrack Tracker,Detections Filter,Instance Segmentation Model,Pixelate Visualization,Ellipse Visualization,Background Color Visualization,Detections Transformation,Qwen3.5-VL,Detections List Roll-Up,Qwen3-VL,Multi-Label Classification Model,Blur Visualization,Keypoint Visualization,OC-SORT Tracker,Semantic Segmentation Model,Corner Visualization,Object Detection Model,Qwen2.5-VL,GLM-OCR,Color Visualization,Dynamic Crop,Model Comparison Visualization,Keypoint Detection Model,Triangle Visualization,Moondream2,Semantic Segmentation Model,Detection Offset,Webhook Sink,Roboflow Vision Events,Byte Tracker,Trace Visualization,Detections Consensus,Roboflow Custom Metadata,SmolVLM2,Florence-2 Model,Roboflow Dataset Upload,Label Visualization,SAM 3,Florence-2 Model,Multi-Label Classification Model,Detections Merge,Circle Visualization,Object Detection Model,Segment Anything 2 Model,SAM 3,SAM 3,Keypoint Detection Model,Keypoint Detection Model,Object Detection Model,Velocity,Instance Segmentation Model,Instance Segmentation Model,Crop Visualization,Single-Label Classification Model
Input and Output Bindings¶
The available connections depend on its binding kinds. Check what binding kinds
Keypoint Detection Model in version v3 has.
Bindings
-
input
images(image): The image to infer on..model_id(roboflow_model_id): Roboflow model identifier..confidence_mode(string): not available.custom_confidence(float_zero_to_one): not available.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 v3
{
"name": "<your_step_name_here>",
"type": "roboflow_core/roboflow_keypoint_detection_model@v3",
"images": "$inputs.image",
"model_id": "my_project/3",
"confidence_mode": "<block_does_not_provide_example>",
"custom_confidence": "<block_does_not_provide_example>",
"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"
}
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:
Slack Notification,OpenAI,Anthropic Claude,SIFT,Multi-Label Classification Model,Halo Visualization,Google Gemini,Camera Focus,Image Convert Grayscale,Image Blur,SIFT Comparison,Instance Segmentation Model,VLM As Detector,Template Matching,VLM As Classifier,Identify Changes,Detections List Roll-Up,Multi-Label Classification Model,Google Gemini,Mask Visualization,Anthropic Claude,Polygon Visualization,Email Notification,Dynamic Crop,Camera Calibration,Color Visualization,SIFT Comparison,Background Subtraction,Grid Visualization,Polygon Visualization,Image Contours,Identify Outliers,Semantic Segmentation Model,Polygon Zone Visualization,VLM As Detector,Twilio SMS Notification,Webhook Sink,Roboflow Vision Events,Email Notification,Absolute Static Crop,Detections Consensus,PTZ Tracking (ONVIF),Roboflow Custom Metadata,Label Visualization,OpenAI,Image Slicer,Line Counter,Florence-2 Model,Twilio SMS/MMS Notification,Circle Visualization,Local File Sink,JSON Parser,Stability AI Outpainting,Reference Path Visualization,Llama 3.2 Vision,Object Detection Model,Instance Segmentation Model,Crop Visualization,Dot Visualization,Roboflow Dataset Upload,Dimension Collapse,Size Measurement,Bounding Box Visualization,Model Monitoring Inference Aggregator,Single-Label Classification Model,Heatmap Visualization,Pixel Color Count,Icon Visualization,Image Preprocessing,Stability AI Image Generation,Clip Comparison,Stability AI Inpainting,Anthropic Claude,Pixelate Visualization,Relative Static Crop,Camera Focus,Ellipse Visualization,Background Color Visualization,Buffer,Dynamic Zone,Blur Visualization,Keypoint Visualization,Semantic Segmentation Model,Corner Visualization,Object Detection Model,Stitch Images,Motion Detection,Clip Comparison,Morphological Transformation,Distance Measurement,Model Comparison Visualization,Contrast Equalization,Keypoint Detection Model,Perspective Correction,Triangle Visualization,Image Threshold,Halo Visualization,Trace Visualization,Classification Label Visualization,Florence-2 Model,Line Counter Visualization,Line Counter,Google Gemini,Roboflow Dataset Upload,OpenAI,Image Slicer,VLM As Classifier,Detection Event Log,S3 Sink,Keypoint Detection Model,QR Code Generator,Text Display,Depth Estimation,Single-Label Classification Model - outputs:
Single-Label Classification Model,Dot Visualization,Roboflow Dataset Upload,Multi-Label Classification Model,Bounding Box Visualization,SAM2 Video Tracker,Detections Classes Replacement,Model Monitoring Inference Aggregator,Single-Label Classification Model,Heatmap Visualization,SORT Tracker,Icon Visualization,ByteTrack Tracker,Detections Filter,Instance Segmentation Model,Pixelate Visualization,Ellipse Visualization,Background Color Visualization,Detections Transformation,Qwen3.5-VL,Detections List Roll-Up,Qwen3-VL,Multi-Label Classification Model,Blur Visualization,Keypoint Visualization,OC-SORT Tracker,Semantic Segmentation Model,Corner Visualization,Object Detection Model,Qwen2.5-VL,GLM-OCR,Color Visualization,Dynamic Crop,Model Comparison Visualization,Keypoint Detection Model,Triangle Visualization,Moondream2,Semantic Segmentation Model,Detection Offset,Webhook Sink,Roboflow Vision Events,Byte Tracker,Trace Visualization,Detections Consensus,Roboflow Custom Metadata,SmolVLM2,Florence-2 Model,Roboflow Dataset Upload,Label Visualization,SAM 3,Florence-2 Model,Multi-Label Classification Model,Detections Merge,Circle Visualization,Object Detection Model,Segment Anything 2 Model,SAM 3,SAM 3,Keypoint Detection Model,Keypoint Detection Model,Object Detection Model,Velocity,Instance Segmentation Model,Instance Segmentation Model,Crop Visualization,Single-Label Classification 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:
Slack Notification,OpenAI,Anthropic Claude,SIFT,Multi-Label Classification Model,Halo Visualization,Google Gemini,Camera Focus,Image Convert Grayscale,Image Blur,SIFT Comparison,Instance Segmentation Model,VLM As Detector,Template Matching,VLM As Classifier,Identify Changes,Detections List Roll-Up,Multi-Label Classification Model,Google Gemini,Mask Visualization,Anthropic Claude,Polygon Visualization,Email Notification,Dynamic Crop,Camera Calibration,Color Visualization,SIFT Comparison,Background Subtraction,Grid Visualization,Polygon Visualization,Image Contours,Identify Outliers,Semantic Segmentation Model,Polygon Zone Visualization,VLM As Detector,Twilio SMS Notification,Webhook Sink,Roboflow Vision Events,Email Notification,Absolute Static Crop,Detections Consensus,PTZ Tracking (ONVIF),Roboflow Custom Metadata,Label Visualization,OpenAI,Image Slicer,Line Counter,Florence-2 Model,Twilio SMS/MMS Notification,Circle Visualization,Local File Sink,JSON Parser,Stability AI Outpainting,Reference Path Visualization,Llama 3.2 Vision,Object Detection Model,Instance Segmentation Model,Crop Visualization,Dot Visualization,Roboflow Dataset Upload,Dimension Collapse,Size Measurement,Bounding Box Visualization,Model Monitoring Inference Aggregator,Single-Label Classification Model,Heatmap Visualization,Pixel Color Count,Icon Visualization,Image Preprocessing,Stability AI Image Generation,Clip Comparison,Stability AI Inpainting,Anthropic Claude,Pixelate Visualization,Relative Static Crop,Camera Focus,Ellipse Visualization,Background Color Visualization,Buffer,Dynamic Zone,Blur Visualization,Keypoint Visualization,Semantic Segmentation Model,Corner Visualization,Object Detection Model,Stitch Images,Motion Detection,Clip Comparison,Morphological Transformation,Distance Measurement,Model Comparison Visualization,Contrast Equalization,Keypoint Detection Model,Perspective Correction,Triangle Visualization,Image Threshold,Halo Visualization,Trace Visualization,Classification Label Visualization,Florence-2 Model,Line Counter Visualization,Line Counter,Google Gemini,Roboflow Dataset Upload,OpenAI,Image Slicer,VLM As Classifier,Detection Event Log,S3 Sink,Keypoint Detection Model,QR Code Generator,Text Display,Depth Estimation,Single-Label Classification Model - outputs:
Slack Notification,OpenAI,OpenAI,Anthropic Claude,Multi-Label Classification Model,Halo Visualization,Google Gemini,Detections Classes Replacement,SAM2 Video Tracker,SORT Tracker,Image Blur,ByteTrack Tracker,Instance Segmentation Model,Detections Filter,LMM For Classification,Detections Transformation,Detections List Roll-Up,Google Gemini,Mask Visualization,Anthropic Claude,OC-SORT Tracker,Polygon Visualization,Cache Get,LMM,Email Notification,Color Visualization,Dynamic Crop,SIFT Comparison,Moondream2,Polygon Visualization,Twilio SMS Notification,Polygon Zone Visualization,Detection Offset,Time in Zone,Roboflow Vision Events,Webhook Sink,Byte Tracker,Email Notification,Detections Consensus,PTZ Tracking (ONVIF),Roboflow Custom Metadata,SAM 3,Label Visualization,OpenAI,Line Counter,Florence-2 Model,Twilio SMS/MMS Notification,Circle Visualization,YOLO-World Model,Segment Anything 2 Model,SAM 3,Path Deviation,Local File Sink,Stability AI Outpainting,CLIP Embedding Model,Reference Path Visualization,Llama 3.2 Vision,Object Detection Model,Instance Segmentation Model,Crop Visualization,CogVLM,Dot Visualization,Roboflow Dataset Upload,Stitch OCR Detections,Cache Set,Size Measurement,Bounding Box Visualization,Model Monitoring Inference Aggregator,Heatmap Visualization,Pixel Color Count,Icon Visualization,Image Preprocessing,Stability AI Image Generation,Stability AI Inpainting,Anthropic Claude,Pixelate Visualization,Ellipse Visualization,Background Color Visualization,Blur Visualization,Stitch OCR Detections,Keypoint Visualization,Semantic Segmentation Model,Corner Visualization,GLM-OCR,Time in Zone,Morphological Transformation,Distance Measurement,Model Comparison Visualization,Contrast Equalization,Time in Zone,Triangle Visualization,Perspective Correction,Clip Comparison,Path Deviation,Image Threshold,Halo Visualization,Trace Visualization,Classification Label Visualization,Florence-2 Model,Line Counter Visualization,Roboflow Dataset Upload,Perception Encoder Embedding Model,Google Vision OCR,Google Gemini,Line Counter,OpenAI,Detections Merge,Detections Stitch,SAM 3,Seg Preview,S3 Sink,Instance Segmentation Model,Keypoint Detection Model,Velocity,QR Code Generator,Text Display,Depth Estimation,Single-Label Classification Model
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"
}