Gaze Detection¶
Deprecated
This block is deprecated and may be removed in a future release.
Class: GazeBlockV1
Source: inference.core.workflows.core_steps.models.foundation.gaze.v1.GazeBlockV1
DEPRECATED. L2CS Gaze detection has been removed from inference along
with the MediaPipe dependency. Invoking this block raises
FeatureDeprecatedError (HTTP 410 Gone).
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.
Runtime compatibility¶
-
hard— runtimeself_hosted_cpu; executionlocal - Requires a GPU; run_locally() loads a model that needs CUDA.
Available Connections¶
Compatible Blocks
Check what blocks you can connect to Gaze Detection in version v1.
- inputs:
PLC Writer,Image Blur,Stability AI Outpainting,Blur Visualization,Frame Delay,Bounding Box Visualization,Absolute Static Crop,Crop Visualization,Reference Path Visualization,Roboflow Dataset Upload,Polygon Visualization,VLM As Detector,Roboflow Visual Search Classifier,Event Writer,Image Slicer,Image Convert Grayscale,VLM As Classifier,Email Notification,Webhook Sink,Contrast Enhancement,VLM As Classifier,Perspective Correction,Motion Detection,Halo Visualization,SIFT,Slack Notification,Label Visualization,Dynamic Crop,PLC Reader,Detections Consensus,Label Visualization,S3 Sink,Halo Visualization,Line Counter Visualization,Email Notification,Roboflow Asset Library Attributes,Background Subtraction,Ellipse Visualization,Stitch Images,OPC UA Writer Sink,Relative Static Crop,Corner Visualization,Triangle Visualization,Depth Estimation,SIFT Comparison,JSON Parser,Dot Visualization,Camera Calibration,Background Color Visualization,Polygon Zone Visualization,Image Contours,Roboflow Custom Metadata,Roboflow Dataset Upload,Camera Focus,Stability AI Inpainting,Contrast Equalization,Morphological Transformation,SIFT Comparison,Image Threshold,Trace Visualization,Color Visualization,Camera Focus,Local File Sink,Stability AI Image Generation,Circle Visualization,QR Code Generator,Morphological Transformation,Dynamic Zone,Model Monitoring Inference Aggregator,Roboflow Vision Events,Heatmap Visualization,Twilio SMS Notification,Auto Rotate on Edges,Polygon Visualization,Microsoft SQL Server Sink,MQTT Writer,Icon Visualization,Rich Label Visualization,Identify Changes,Twilio SMS/MMS Notification,Keypoint Visualization,Image Preprocessing,Image Slicer,Text Display,Grid Visualization,Model Comparison Visualization,PTZ Tracking (ONVIF),Identify Outliers,Mask Visualization,Classification Label Visualization,Pixelate Visualization,Roboflow Visual Search,VLM As Detector - outputs:
Track Class Lock,Blur Visualization,Frame Delay,Bounding Box Visualization,Mask Edge Snap,Roboflow Dataset Upload,Crop Visualization,OpenAI,Anthropic Claude,Google Gemini,Event Writer,Webhook Sink,Template Matching,Mask Area Measurement,SAM 3 Interactive,Detections List Roll-Up,OC-SORT Tracker,Label Visualization,MoonshotAI Kimi,Dynamic Crop,OpenRouter,Stitch OCR Detections,Detections Consensus,Label Visualization,GeoTag Detection,Per-Class Confidence Filter,Line Counter Visualization,Velocity,BoT-SORT Tracker,Detection Event Log,OPC UA Writer Sink,Ellipse Visualization,Corner Visualization,Triangle Visualization,Detection Offset,Qwen-VL,SAM 3,ByteTrack Tracker,Dot Visualization,Distance Measurement,Camera Calibration,Google Gemini,Florence-2 Model,Seg Preview,Background Color Visualization,Google Gemini,Roboflow Custom Metadata,Roboflow Dataset Upload,Segment Anything 2 Model,Qwen 3.5 API,MoonshotAI Kimi,Trace Visualization,Color Visualization,SAM 3,Llama 3.2 Vision,Llama 3.2 Vision,SAM3 Video Tracker,Circle Visualization,Dynamic Zone,Detections Merge,SAM2 Video Tracker,Continue If,Google Gemini,Detections Classes Replacement,Google Gemma API,Detections Filter,Roboflow Vision Events,Model Monitoring Inference Aggregator,Google Gemma,Heatmap Visualization,Auto Rotate on Edges,MQTT Writer,Icon Visualization,SAM 3,Detections Transformation,Rich Label Visualization,Anthropic Claude,SORT Tracker,Keypoint Visualization,OpenAI,Anthropic Claude,Text Display,Qwen 3.6 API,PTZ Tracking (ONVIF),Model Comparison Visualization,Florence-2 Model,Nearest Neighbor Detection Match,OpenAI,Byte Tracker,Pixelate Visualization,OpenAI-Compatible LLM
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>"
}