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:
Circle Visualization,Roboflow Asset Library Attributes,Twilio SMS Notification,Image Blur,S3 Sink,Email Notification,Reference Path Visualization,Camera Focus,SIFT Comparison,PTZ Tracking (ONVIF),Event Writer,Identify Changes,Slack Notification,Halo Visualization,VLM As Classifier,Dot Visualization,Image Slicer,Label Visualization,Background Color Visualization,Email Notification,Pixelate Visualization,Heatmap Visualization,JSON Parser,Stitch Images,Identify Outliers,Morphological Transformation,Blur Visualization,Trace Visualization,Camera Focus,Corner Visualization,Model Comparison Visualization,MQTT Writer,SIFT Comparison,Webhook Sink,Model Monitoring Inference Aggregator,Image Threshold,Image Contours,Local File Sink,Motion Detection,Polygon Visualization,Polygon Visualization,SIFT,Stability AI Image Generation,Classification Label Visualization,Line Counter Visualization,Relative Static Crop,Grid Visualization,Image Preprocessing,Keypoint Visualization,OPC UA Writer Sink,Icon Visualization,Color Visualization,Dynamic Zone,Triangle Visualization,QR Code Generator,Contrast Enhancement,Roboflow Dataset Upload,Absolute Static Crop,Dynamic Crop,Stability AI Inpainting,Background Subtraction,Bounding Box Visualization,Polygon Zone Visualization,Stability AI Outpainting,Crop Visualization,Image Convert Grayscale,Mask Visualization,Halo Visualization,Image Slicer,Perspective Correction,Twilio SMS/MMS Notification,Text Display,Morphological Transformation,Roboflow Vision Events,Microsoft SQL Server Sink,VLM As Classifier,Roboflow Dataset Upload,VLM As Detector,Depth Estimation,Detections Consensus,Roboflow Custom Metadata,Contrast Equalization,Camera Calibration,Ellipse Visualization,VLM As Detector - outputs:
SAM 3,Circle Visualization,MoonshotAI Kimi,PTZ Tracking (ONVIF),Event Writer,SAM2 Video Tracker,Google Gemma,Qwen 3.6 API,Dot Visualization,SAM 3,Label Visualization,Background Color Visualization,Llama 3.2 Vision,SAM 3 Interactive,Velocity,Pixelate Visualization,OpenAI-Compatible LLM,Mask Area Measurement,Heatmap Visualization,Google Gemini,Track Class Lock,Anthropic Claude,Google Gemma API,OpenAI,Trace Visualization,Blur Visualization,Llama 3.2 Vision,ByteTrack Tracker,Detection Event Log,Stitch OCR Detections,Detections List Roll-Up,Florence-2 Model,OpenAI,Google Gemini,Corner Visualization,OpenRouter,Model Comparison Visualization,MQTT Writer,Webhook Sink,SAM 3,Model Monitoring Inference Aggregator,Byte Tracker,Google Gemini,MoonshotAI Kimi,Segment Anything 2 Model,Mask Edge Snap,Line Counter Visualization,Per-Class Confidence Filter,Keypoint Visualization,Template Matching,Anthropic Claude,OPC UA Writer Sink,Icon Visualization,Color Visualization,Dynamic Zone,Triangle Visualization,Seg Preview,Roboflow Dataset Upload,Qwen 3.5 API,Dynamic Crop,Detections Transformation,BoT-SORT Tracker,Bounding Box Visualization,Crop Visualization,OC-SORT Tracker,Continue If,OpenAI,Detection Offset,Florence-2 Model,SORT Tracker,Distance Measurement,Qwen-VL,Roboflow Vision Events,Anthropic Claude,Text Display,Roboflow Dataset Upload,Detections Consensus,Roboflow Custom Metadata,Detections Filter,Camera Calibration,Ellipse Visualization,Detections Merge,Detections Classes Replacement,SAM3 Video Tracker
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>"
}