EyeGaze
Eye gaze estimation from cropped eye images.
Predicts gaze direction (pitch, yaw) from 96x160 grayscale eye images using the EyeNet model.
Technical Details
Model checkpoint:checkpoint.pt
Input resolution:96x160
Number of parameters:2.58M
Model size (float):9.6MB
Model size (w8a16):3.3 MB
Applicable Scenarios
- Incabinet driver monitoring
- Phone unlocking
- Building access control
License
Model:BSD-3-CLAUSE
Tags
- real-time
Supported IoT Devices
- Dragonwing Q-6690 MTP
- Dragonwing RB3 Gen 2 Vision Kit
- QCS8250 (Proxy)
- QCS8550 (Proxy)
- RB5 (Proxy)
Supported IoT Chipsets
- Qualcomm® Qcm6690
- Qualcomm® QCS6490
- Qualcomm® QCS8250 (Proxy)
- Qualcomm® QCS8550 (Proxy)
Looking for more? See models created by industry leaders.
Discover Model Makers