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 1.24.3 | Download |
| ONNX | w8a16 | Universal | ONNX Runtime 1.24.3 | Download |
| QNN_DLC | float | Universal | QAIRT 2.45 | Download |
| TFLITE | float | Universal | 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 | 19.157 ms | 32 - 42 MB | CPU |
| EyeGaze | ONNX | float | Snapdragon® 8 Elite Mobile | 20.075 ms | 32 - 40 MB | CPU |
| EyeGaze | ONNX | float | Snapdragon® X2 Elite | 9.735 ms | 35 - 35 MB | CPU |
| EyeGaze | ONNX | float | Snapdragon® X Elite | 9.77 ms | 34 - 34 MB | CPU |
| EyeGaze | ONNX | float | Snapdragon® X Elite | 9.77 ms | 34 - 34 MB | CPU |
| EyeGaze | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 21.586 ms | 31 - 40 MB | CPU |
| EyeGaze | ONNX | float | Qualcomm® QCS8550 (Proxy) | 25.01 ms | 32 - 37 MB | CPU |
| EyeGaze | ONNX | float | Qualcomm® QCS9075 | 20.922 ms | 32 - 42 MB | CPU |
| EyeGaze | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 20.075 ms | 32 - 40 MB | CPU |
| EyeGaze | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 25.782 ms | 69 - 83 MB | CPU |
| EyeGaze | ONNX | w8a16 | Snapdragon® 8 Elite Mobile | 26.972 ms | 69 - 81 MB | CPU |
| EyeGaze | ONNX | w8a16 | Snapdragon® X2 Elite | 17.155 ms | 102 - 102 MB | CPU |
| EyeGaze | ONNX | w8a16 | Snapdragon® X Elite | 18.01 ms | 101 - 101 MB | CPU |
| EyeGaze | ONNX | w8a16 | Snapdragon® X Elite | 18.01 ms | 101 - 101 MB | CPU |
| EyeGaze | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 31.882 ms | 69 - 82 MB | CPU |
| EyeGaze | ONNX | w8a16 | Qualcomm® QCS6490 | 142.485 ms | 69 - 74 MB | CPU |
| EyeGaze | ONNX | w8a16 | Qualcomm® QCS8550 (Proxy) | 37.671 ms | 65 - 97 MB | CPU |
| EyeGaze | ONNX | w8a16 | Qualcomm® QCS9075 | 40.455 ms | 68 - 73 MB | CPU |
| EyeGaze | ONNX | w8a16 | Qualcomm® QCM6690 | 68.837 ms | 65 - 76 MB | CPU |
| EyeGaze | ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 26.972 ms | 69 - 81 MB | CPU |
| EyeGaze | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 60.345 ms | 62 - 73 MB | CPU |
| EyeGaze | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 60.345 ms | 62 - 73 MB | CPU |
| EyeGaze | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 12.54 ms | 10 - 25 MB | CPU |
| EyeGaze | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 14.351 ms | 11 - 27 MB | CPU |
| EyeGaze | QNN_DLC | float | Snapdragon® X2 Elite | 9.54 ms | 11 - 11 MB | CPU |
| EyeGaze | QNN_DLC | float | Snapdragon® X Elite | 13.704 ms | 11 - 11 MB | CPU |
| EyeGaze | QNN_DLC | float | Snapdragon® X Elite | 13.704 ms | 11 - 11 MB | CPU |
| EyeGaze | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 17.752 ms | 10 - 24 MB | CPU |
| EyeGaze | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 212.294 ms | 10 - 24 MB | CPU |
| EyeGaze | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 19.672 ms | 10 - 72 MB | CPU |
| EyeGaze | QNN_DLC | float | Qualcomm® SA8775P | 29.099 ms | 10 - 21 MB | CPU |
| EyeGaze | QNN_DLC | float | Qualcomm® SA8775P | 29.099 ms | 10 - 21 MB | CPU |
| EyeGaze | QNN_DLC | float | Qualcomm® SA8775P | 29.099 ms | 10 - 21 MB | CPU |
| EyeGaze | QNN_DLC | float | Qualcomm® QCS9075 | 67.911 ms | 61 - 134 MB | CPU |
| EyeGaze | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 28.217 ms | 11 - 25 MB | CPU |
| EyeGaze | QNN_DLC | float | Qualcomm® SA7255P | 212.294 ms | 10 - 24 MB | CPU |
| EyeGaze | QNN_DLC | float | Qualcomm® SA8295P | 22.729 ms | 10 - 20 MB | CPU |
| EyeGaze | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 14.351 ms | 11 - 27 MB | CPU |
| EyeGaze | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 10.837 ms | 2 - 11 MB | CPU |
| EyeGaze | TFLITE | float | Snapdragon® 8 Elite Mobile | 11.175 ms | 2 - 9 MB | CPU |
| EyeGaze | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 16.056 ms | 4 - 13 MB | CPU |
| EyeGaze | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 30.471 ms | 2 - 9 MB | CPU |
| EyeGaze | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 18.196 ms | 2 - 5 MB | CPU |
| EyeGaze | TFLITE | float | Qualcomm® SA8775P | 25.483 ms | 2 - 6 MB | CPU |
| EyeGaze | TFLITE | float | Qualcomm® SA8775P | 25.483 ms | 2 - 6 MB | CPU |
| EyeGaze | TFLITE | float | Qualcomm® SA8775P | 25.483 ms | 2 - 6 MB | CPU |
| EyeGaze | TFLITE | float | Qualcomm® QCS9075 | 25.329 ms | 2 - 43 MB | CPU |
| EyeGaze | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 21.084 ms | 2 - 14 MB | CPU |
| EyeGaze | TFLITE | float | Qualcomm® SA7255P | 30.471 ms | 2 - 9 MB | CPU |
| EyeGaze | TFLITE | float | Qualcomm® SA8295P | 16.771 ms | 2 - 6 MB | CPU |
| EyeGaze | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 11.175 ms | 2 - 9 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.