YAML Metadata Warning:The pipeline tag "gaze-estimation" is not in the official list: text-classification, token-classification, table-question-answering, question-answering, zero-shot-classification, translation, summarization, feature-extraction, text-generation, fill-mask, sentence-similarity, text-to-speech, text-to-audio, automatic-speech-recognition, audio-to-audio, audio-classification, audio-text-to-text, voice-activity-detection, depth-estimation, image-classification, object-detection, image-segmentation, text-to-image, image-to-text, image-to-image, image-to-video, unconditional-image-generation, video-classification, reinforcement-learning, robotics, tabular-classification, tabular-regression, tabular-to-text, table-to-text, multiple-choice, text-ranking, text-retrieval, time-series-forecasting, text-to-video, image-text-to-text, image-text-to-image, image-text-to-video, visual-question-answering, document-question-answering, zero-shot-image-classification, graph-ml, mask-generation, zero-shot-object-detection, text-to-3d, image-to-3d, image-feature-extraction, video-text-to-text, keypoint-detection, visual-document-retrieval, any-to-any, video-to-video, other
EyeGaze: Optimized for Qualcomm Devices
Predicts gaze direction (pitch, yaw) from 96x160 grayscale eye images using the EyeNet model.
This is based on the implementation of EyeGaze found here. This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the Qualcomm® AI Hub Models library to export with custom configurations. More details on model performance across various devices, can be found here.
Qualcomm AI Hub Models uses Qualcomm AI Hub Workbench to compile, profile, and evaluate this model. Sign up to run these models on a hosted Qualcomm® device.
Getting Started
There are two ways to deploy this model on your device:
Option 1: Download Pre-Exported Models
Below are pre-exported model assets ready for deployment.
| Runtime | Precision | Chipset | SDK Versions | Download |
|---|---|---|---|---|
| ONNX | float | Universal | QAIRT 2.42, ONNX Runtime 1.24.3 | Download |
| ONNX | w8a16 | Universal | QAIRT 2.42, ONNX Runtime 1.24.3 | Download |
| QNN_DLC | float | Universal | QAIRT 2.43 | Download |
For more device-specific assets and performance metrics, visit EyeGaze on Qualcomm® AI Hub.
Option 2: Export with Custom Configurations
Use the Qualcomm® AI Hub Models Python library to compile and export the model with your own:
- Custom weights (e.g., fine-tuned checkpoints)
- Custom input shapes
- Target device and runtime configurations
This option is ideal if you need to customize the model beyond the default configuration provided here.
See our repository for EyeGaze on GitHub for usage instructions.
Model Details
Model Type: Model_use_case.gaze_estimation
Model Stats:
- Model checkpoint: checkpoint.pt
- Input resolution: 96x160
- Number of parameters: 2.58M
- Model size (float): 9.6MB
- Model size (w8a16): 3.3 MB
Performance Summary
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit |
|---|---|---|---|---|---|---|
| EyeGaze | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 19.041 ms | 32 - 43 MB | CPU |
| EyeGaze | ONNX | float | Snapdragon® X2 Elite | 9.487 ms | 34 - 34 MB | CPU |
| EyeGaze | ONNX | float | Snapdragon® X Elite | 9.465 ms | 34 - 34 MB | CPU |
| EyeGaze | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 21.944 ms | 31 - 40 MB | CPU |
| EyeGaze | ONNX | float | Qualcomm® QCS8550 (Proxy) | 25.309 ms | 32 - 34 MB | CPU |
| EyeGaze | ONNX | float | Qualcomm® QCS9075 | 20.969 ms | 33 - 43 MB | CPU |
| EyeGaze | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 19.834 ms | 32 - 45 MB | CPU |
| EyeGaze | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 25.798 ms | 69 - 84 MB | CPU |
| EyeGaze | ONNX | w8a16 | Snapdragon® X2 Elite | 17.491 ms | 102 - 102 MB | CPU |
| EyeGaze | ONNX | w8a16 | Snapdragon® X Elite | 18.149 ms | 101 - 101 MB | CPU |
| EyeGaze | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 31.907 ms | 72 - 87 MB | CPU |
| EyeGaze | ONNX | w8a16 | Qualcomm® QCS6490 | 144.355 ms | 69 - 74 MB | CPU |
| EyeGaze | ONNX | w8a16 | Qualcomm® QCS8550 (Proxy) | 37.184 ms | 66 - 75 MB | CPU |
| EyeGaze | ONNX | w8a16 | Qualcomm® QCS9075 | 40.659 ms | 70 - 75 MB | CPU |
| EyeGaze | ONNX | w8a16 | Qualcomm® QCM6690 | 68.553 ms | 70 - 81 MB | CPU |
| EyeGaze | ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 28.397 ms | 71 - 83 MB | CPU |
| EyeGaze | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 60.053 ms | 61 - 72 MB | CPU |
| EyeGaze | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 27.449 ms | 36 - 50 MB | CPU |
| EyeGaze | QNN_DLC | float | Snapdragon® X2 Elite | 34.26 ms | 14 - 14 MB | CPU |
| EyeGaze | QNN_DLC | float | Snapdragon® X Elite | 31.643 ms | 13 - 13 MB | CPU |
| EyeGaze | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 37.026 ms | 11 - 23 MB | CPU |
| EyeGaze | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 235.625 ms | 18 - 30 MB | CPU |
| EyeGaze | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 45.399 ms | 36 - 97 MB | CPU |
| EyeGaze | QNN_DLC | float | Qualcomm® SA8775P | 51.911 ms | 34 - 42 MB | CPU |
| EyeGaze | QNN_DLC | float | Qualcomm® QCS9075 | 56.398 ms | 61 - 133 MB | CPU |
| EyeGaze | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 66.918 ms | 11 - 24 MB | CPU |
| EyeGaze | QNN_DLC | float | Qualcomm® SA7255P | 235.625 ms | 18 - 30 MB | CPU |
| EyeGaze | QNN_DLC | float | Qualcomm® SA8295P | 42.762 ms | 33 - 42 MB | CPU |
| EyeGaze | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 38.387 ms | 33 - 43 MB | CPU |
License
- The license for the original implementation of EyeGaze can be found here.
References
Community
- Join our AI Hub Slack community to collaborate, post questions and learn more about on-device AI.
- For questions or feedback please reach out to us.