Gaze Detection¶
Class: GazeBlockV1
Source: inference.core.workflows.core_steps.models.foundation.gaze.v1.GazeBlockV1
Run L2CS Gaze detection model on faces in images.
This block can: 1. Detect faces in images and estimate their gaze direction 2. Estimate gaze direction on pre-cropped face images
The gaze direction is represented by yaw and pitch angles in degrees.
Type identifier¶
Use the following identifier in step "type" field: roboflow_core/gaze@v1to add the block as
as step in your workflow.
Properties¶
| Name | Type | Description | Refs |
|---|---|---|---|
name |
str |
Enter a unique identifier for this step.. | ❌ |
do_run_face_detection |
bool |
Whether to run face detection. Set to False if input images are pre-cropped face images.. | ✅ |
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 Gaze Detection in version v1.
- inputs:
Slack Notification,Image Slicer,Stability AI Inpainting,Pixelate Visualization,Perspective Correction,Relative Static Crop,Roboflow Custom Metadata,Detections Consensus,Twilio SMS Notification,VLM as Classifier,SIFT Comparison,Roboflow Dataset Upload,Grid Visualization,Ellipse Visualization,SIFT,Model Comparison Visualization,VLM as Detector,Halo Visualization,Image Contours,JSON Parser,Crop Visualization,Absolute Static Crop,Camera Focus,Image Blur,Trace Visualization,Circle Visualization,Image Preprocessing,VLM as Detector,Background Color Visualization,Dot Visualization,Identify Outliers,Polygon Zone Visualization,Roboflow Dataset Upload,Identify Changes,VLM as Classifier,Classification Label Visualization,Bounding Box Visualization,Corner Visualization,Local File Sink,Image Slicer,Dynamic Crop,Reference Path Visualization,Label Visualization,Mask Visualization,Stitch Images,Triangle Visualization,Stability AI Image Generation,Image Threshold,Line Counter Visualization,Keypoint Visualization,Model Monitoring Inference Aggregator,Color Visualization,Email Notification,Blur Visualization,Webhook Sink,SIFT Comparison,Image Convert Grayscale,Polygon Visualization - outputs:
Segment Anything 2 Model,Detections Filter,Pixelate Visualization,Roboflow Custom Metadata,Detections Consensus,Detection Offset,Roboflow Dataset Upload,Google Gemini,Ellipse Visualization,Model Comparison Visualization,Crop Visualization,Trace Visualization,Distance Measurement,Circle Visualization,Velocity,Background Color Visualization,Dot Visualization,Roboflow Dataset Upload,Florence-2 Model,Llama 3.2 Vision,Corner Visualization,Florence-2 Model,Bounding Box Visualization,Dynamic Crop,Label Visualization,Triangle Visualization,Line Counter Visualization,Template Matching,Dynamic Zone,Detections Transformation,Keypoint Visualization,Model Monitoring Inference Aggregator,Color Visualization,Blur Visualization,Anthropic Claude,Webhook Sink,Detections Classes Replacement,OpenAI
Input and Output Bindings¶
The available connections depend on its binding kinds. Check what binding kinds
Gaze Detection in version v1 has.
Bindings
-
input
-
output
face_predictions(keypoint_detection_prediction): Prediction with detected bounding boxes and detected keypoints in form of sv.Detections(...) object.yaw_degrees(float): Float value.pitch_degrees(float): Float value.
Example JSON definition of step Gaze Detection in version v1
{
"name": "<your_step_name_here>",
"type": "roboflow_core/gaze@v1",
"images": "$inputs.image",
"do_run_face_detection": "<block_does_not_provide_example>"
}