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 | ONNX Runtime 1.24.1 | Download |
| ONNX | w8a16 | Universal | ONNX Runtime 1.24.1 | Download |
| QNN_DLC | float | Universal | QAIRT 2.43 | Download |
| TFLITE | float | Universal | TFLite 2.17.0 | 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® X2 Elite | 8.981 ms | 35 - 35 MB | CPU |
| EyeGaze | ONNX | float | Snapdragon® X Elite | 9.533 ms | 34 - 34 MB | CPU |
| EyeGaze | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 21.778 ms | 31 - 41 MB | CPU |
| EyeGaze | ONNX | float | Qualcomm® QCS8550 (Proxy) | 31.181 ms | 32 - 46 MB | CPU |
| EyeGaze | ONNX | float | Qualcomm® QCS9075 | 21.033 ms | 32 - 42 MB | CPU |
| EyeGaze | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 19.985 ms | 32 - 40 MB | CPU |
| EyeGaze | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 18.935 ms | 32 - 42 MB | CPU |
| EyeGaze | ONNX | w8a16 | Snapdragon® X2 Elite | 17.195 ms | 102 - 102 MB | CPU |
| EyeGaze | ONNX | w8a16 | Snapdragon® X Elite | 17.537 ms | 101 - 101 MB | CPU |
| EyeGaze | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 31.803 ms | 69 - 83 MB | CPU |
| EyeGaze | ONNX | w8a16 | Qualcomm® QCS6490 | 146.93 ms | 68 - 74 MB | CPU |
| EyeGaze | ONNX | w8a16 | Qualcomm® QCS8550 (Proxy) | 38.244 ms | 70 - 74 MB | CPU |
| EyeGaze | ONNX | w8a16 | Qualcomm® QCS9075 | 40.879 ms | 68 - 74 MB | CPU |
| EyeGaze | ONNX | w8a16 | Qualcomm® QCM6690 | 68.17 ms | 69 - 80 MB | CPU |
| EyeGaze | ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 27.824 ms | 71 - 84 MB | CPU |
| EyeGaze | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 60.413 ms | 58 - 69 MB | CPU |
| EyeGaze | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 25.889 ms | 69 - 84 MB | CPU |
| EyeGaze | QNN_DLC | float | Snapdragon® X2 Elite | 40.969 ms | 14 - 14 MB | CPU |
| EyeGaze | QNN_DLC | float | Snapdragon® X Elite | 28.924 ms | 13 - 13 MB | CPU |
| EyeGaze | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 35.31 ms | 14 - 26 MB | CPU |
| EyeGaze | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 238.831 ms | 22 - 35 MB | CPU |
| EyeGaze | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 46.681 ms | 36 - 41 MB | CPU |
| EyeGaze | QNN_DLC | float | Qualcomm® SA8775P | 51.057 ms | 36 - 45 MB | CPU |
| EyeGaze | QNN_DLC | float | Qualcomm® QCS9075 | 56.177 ms | 76 - 149 MB | CPU |
| EyeGaze | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 61.833 ms | 11 - 25 MB | CPU |
| EyeGaze | QNN_DLC | float | Qualcomm® SA7255P | 238.831 ms | 22 - 35 MB | CPU |
| EyeGaze | QNN_DLC | float | Qualcomm® SA8295P | 42.662 ms | 34 - 42 MB | CPU |
| EyeGaze | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 38.838 ms | 33 - 43 MB | CPU |
| EyeGaze | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 26.141 ms | 37 - 51 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.