v0.59.0
Browse filesSee https://github.com/qualcomm/ai-hub-models/releases/v0.59.0 for changelog.
- README.md +89 -83
- release_assets.json +8 -9
README.md
CHANGED
|
@@ -15,7 +15,7 @@ pipeline_tag: keypoint-detection
|
|
| 15 |
6DRepNet predicts head pose (pitch, yaw, roll) from a face image using a RepVGG-B1g2 backbone and a continuous 6D rotation representation, achieving robust and accurate head pose estimation.
|
| 16 |
|
| 17 |
This is based on the implementation of SixDRepNet found [here](https://github.com/thohemp/6DRepNet).
|
| 18 |
-
This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.
|
| 19 |
|
| 20 |
Qualcomm AI Hub Models uses [Qualcomm AI Hub Workbench](https://workbench.aihub.qualcomm.com) to compile, profile, and evaluate this model. [Sign up](https://myaccount.qualcomm.com/signup) to run these models on a hosted Qualcomm® device.
|
| 21 |
|
|
@@ -28,23 +28,23 @@ Below are pre-exported model assets ready for deployment.
|
|
| 28 |
|
| 29 |
| Runtime | Precision | Chipset | SDK Versions | Download |
|
| 30 |
|---|---|---|---|---|
|
| 31 |
-
| ONNX | float | Universal | QAIRT 2.45, ONNX Runtime 1.
|
| 32 |
-
| QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/sixd_repnet/releases/v0.
|
| 33 |
-
| TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/sixd_repnet/releases/v0.
|
| 34 |
|
| 35 |
For more device-specific assets and performance metrics, visit **[SixDRepNet on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/sixd_repnet)**.
|
| 36 |
|
| 37 |
|
| 38 |
### Option 2: Export with Custom Configurations
|
| 39 |
|
| 40 |
-
Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.
|
| 41 |
- Custom weights (e.g., fine-tuned checkpoints)
|
| 42 |
- Custom input shapes
|
| 43 |
- Target device and runtime configurations
|
| 44 |
|
| 45 |
This option is ideal if you need to customize the model beyond the default configuration provided here.
|
| 46 |
|
| 47 |
-
See our repository for [SixDRepNet on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.
|
| 48 |
|
| 49 |
## Model Details
|
| 50 |
|
|
@@ -58,84 +58,90 @@ See our repository for [SixDRepNet on GitHub](https://github.com/qualcomm/ai-hub
|
|
| 58 |
## Performance Summary
|
| 59 |
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
|
| 60 |
|---|---|---|---|---|---|---
|
| 61 |
-
| face_detector | ONNX | float | Snapdragon® X2 Elite | 1.
|
| 62 |
-
| face_detector | ONNX | float | Snapdragon® X Elite | 3.
|
| 63 |
-
| face_detector | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 2.
|
| 64 |
-
| face_detector | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 6.
|
| 65 |
-
| face_detector | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 3.
|
| 66 |
-
| face_detector | ONNX | float | Qualcomm® QCS8450 | 6.
|
| 67 |
-
| face_detector | ONNX | float |
|
| 68 |
-
| face_detector | ONNX | float |
|
| 69 |
-
| face_detector | ONNX | float | Qualcomm® Dragonwing™
|
| 70 |
-
| face_detector | ONNX | float |
|
| 71 |
-
| face_detector | ONNX | float |
|
| 72 |
-
| face_detector | QNN_DLC | float | Snapdragon® X2 Elite | 5.
|
| 73 |
-
| face_detector | QNN_DLC | float | Snapdragon® X Elite | 16.
|
| 74 |
-
| face_detector | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 9.
|
| 75 |
-
| face_detector | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 24.
|
| 76 |
-
| face_detector | QNN_DLC | float | Qualcomm® QCS8275 | 28.
|
| 77 |
-
| face_detector | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 15.
|
| 78 |
-
| face_detector | QNN_DLC | float | Qualcomm®
|
| 79 |
-
| face_detector | QNN_DLC | float |
|
| 80 |
-
| face_detector | QNN_DLC | float | Qualcomm®
|
| 81 |
-
| face_detector | QNN_DLC | float |
|
| 82 |
-
| face_detector | QNN_DLC | float | Qualcomm®
|
| 83 |
-
| face_detector | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-
|
| 84 |
-
| face_detector | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 6.
|
| 85 |
-
| face_detector | QNN_DLC | float | Qualcomm®
|
| 86 |
-
| face_detector |
|
| 87 |
-
| face_detector |
|
| 88 |
-
| face_detector |
|
| 89 |
-
| face_detector | TFLITE | float |
|
| 90 |
-
| face_detector | TFLITE | float |
|
| 91 |
-
| face_detector | TFLITE | float | Qualcomm®
|
| 92 |
-
| face_detector | TFLITE | float | Qualcomm®
|
| 93 |
-
| face_detector | TFLITE | float | Qualcomm®
|
| 94 |
-
| face_detector | TFLITE | float |
|
| 95 |
-
| face_detector | TFLITE | float | Qualcomm®
|
| 96 |
-
| face_detector | TFLITE | float |
|
| 97 |
-
| face_detector | TFLITE | float | Qualcomm®
|
| 98 |
-
| face_detector | TFLITE | float | Qualcomm® Dragonwing™
|
| 99 |
-
| face_detector | TFLITE | float | Qualcomm®
|
| 100 |
-
|
|
| 101 |
-
|
|
| 102 |
-
|
|
| 103 |
-
| pose_estimator | ONNX | float | Snapdragon®
|
| 104 |
-
| pose_estimator | ONNX | float |
|
| 105 |
-
| pose_estimator | ONNX | float |
|
| 106 |
-
| pose_estimator | ONNX | float | Snapdragon® 8
|
| 107 |
-
| pose_estimator | ONNX | float |
|
| 108 |
-
| pose_estimator | ONNX | float | Qualcomm®
|
| 109 |
-
| pose_estimator | ONNX | float | Qualcomm® Dragonwing™
|
| 110 |
-
| pose_estimator | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 2.
|
| 111 |
-
| pose_estimator |
|
| 112 |
-
| pose_estimator |
|
| 113 |
-
| pose_estimator |
|
| 114 |
-
| pose_estimator | QNN_DLC | float | Snapdragon®
|
| 115 |
-
| pose_estimator | QNN_DLC | float |
|
| 116 |
-
| pose_estimator | QNN_DLC | float |
|
| 117 |
-
| pose_estimator | QNN_DLC | float |
|
| 118 |
-
| pose_estimator | QNN_DLC | float |
|
| 119 |
-
| pose_estimator | QNN_DLC | float | Qualcomm®
|
| 120 |
-
| pose_estimator | QNN_DLC | float |
|
| 121 |
-
| pose_estimator | QNN_DLC | float | Qualcomm®
|
| 122 |
-
| pose_estimator | QNN_DLC | float | Qualcomm®
|
| 123 |
-
| pose_estimator | QNN_DLC | float | Qualcomm®
|
| 124 |
-
| pose_estimator | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-
|
| 125 |
-
| pose_estimator |
|
| 126 |
-
| pose_estimator |
|
| 127 |
-
| pose_estimator |
|
| 128 |
-
| pose_estimator |
|
| 129 |
-
| pose_estimator |
|
| 130 |
-
| pose_estimator |
|
| 131 |
-
| pose_estimator | TFLITE | float |
|
| 132 |
-
| pose_estimator | TFLITE | float |
|
| 133 |
-
| pose_estimator | TFLITE | float |
|
| 134 |
-
| pose_estimator | TFLITE | float | Qualcomm®
|
| 135 |
-
| pose_estimator | TFLITE | float |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 136 |
| pose_estimator | TFLITE | float | Qualcomm® SA7255P | 17.388 ms | 0 - 26 MB | NPU
|
| 137 |
-
| pose_estimator | TFLITE | float | Qualcomm®
|
| 138 |
-
| pose_estimator | TFLITE | float |
|
|
|
|
| 139 |
|
| 140 |
## License
|
| 141 |
* The license for the original implementation of SixDRepNet can be found
|
|
|
|
| 15 |
6DRepNet predicts head pose (pitch, yaw, roll) from a face image using a RepVGG-B1g2 backbone and a continuous 6D rotation representation, achieving robust and accurate head pose estimation.
|
| 16 |
|
| 17 |
This is based on the implementation of SixDRepNet found [here](https://github.com/thohemp/6DRepNet).
|
| 18 |
+
This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.59.0/src/qai_hub_models/models/sixd_repnet) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
|
| 19 |
|
| 20 |
Qualcomm AI Hub Models uses [Qualcomm AI Hub Workbench](https://workbench.aihub.qualcomm.com) to compile, profile, and evaluate this model. [Sign up](https://myaccount.qualcomm.com/signup) to run these models on a hosted Qualcomm® device.
|
| 21 |
|
|
|
|
| 28 |
|
| 29 |
| Runtime | Precision | Chipset | SDK Versions | Download |
|
| 30 |
|---|---|---|---|---|
|
| 31 |
+
| ONNX | float | Universal | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/sixd_repnet/releases/v0.59.0/sixd_repnet-onnx-float.zip)
|
| 32 |
+
| QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/sixd_repnet/releases/v0.59.0/sixd_repnet-qnn_dlc-float.zip)
|
| 33 |
+
| TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/sixd_repnet/releases/v0.59.0/sixd_repnet-tflite-float.zip)
|
| 34 |
|
| 35 |
For more device-specific assets and performance metrics, visit **[SixDRepNet on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/sixd_repnet)**.
|
| 36 |
|
| 37 |
|
| 38 |
### Option 2: Export with Custom Configurations
|
| 39 |
|
| 40 |
+
Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.59.0/src/qai_hub_models/models/sixd_repnet) Python library to compile and export the model with your own:
|
| 41 |
- Custom weights (e.g., fine-tuned checkpoints)
|
| 42 |
- Custom input shapes
|
| 43 |
- Target device and runtime configurations
|
| 44 |
|
| 45 |
This option is ideal if you need to customize the model beyond the default configuration provided here.
|
| 46 |
|
| 47 |
+
See our repository for [SixDRepNet on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.59.0/src/qai_hub_models/models/sixd_repnet) for usage instructions.
|
| 48 |
|
| 49 |
## Model Details
|
| 50 |
|
|
|
|
| 58 |
## Performance Summary
|
| 59 |
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
|
| 60 |
|---|---|---|---|---|---|---
|
| 61 |
+
| face_detector | ONNX | float | Snapdragon® X2 Elite | 1.91 ms | 5 - 5 MB | NPU
|
| 62 |
+
| face_detector | ONNX | float | Snapdragon® X Elite | 3.66 ms | 5 - 5 MB | NPU
|
| 63 |
+
| face_detector | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 2.163 ms | 0 - 174 MB | NPU
|
| 64 |
+
| face_detector | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 6.801 ms | 7 - 176 MB | NPU
|
| 65 |
+
| face_detector | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 3.504 ms | 0 - 5 MB | NPU
|
| 66 |
+
| face_detector | ONNX | float | Qualcomm® QCS8450 | 6.801 ms | 7 - 176 MB | NPU
|
| 67 |
+
| face_detector | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 4.087 ms | 5 - 12 MB | NPU
|
| 68 |
+
| face_detector | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 3.66 ms | 5 - 5 MB | NPU
|
| 69 |
+
| face_detector | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 1.734 ms | 0 - 164 MB | NPU
|
| 70 |
+
| face_detector | ONNX | float | Snapdragon® 8 Elite Mobile | 1.734 ms | 0 - 164 MB | NPU
|
| 71 |
+
| face_detector | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.804 ms | 1 - 166 MB | NPU
|
| 72 |
+
| face_detector | QNN_DLC | float | Snapdragon® X2 Elite | 5.846 ms | 5 - 5 MB | NPU
|
| 73 |
+
| face_detector | QNN_DLC | float | Snapdragon® X Elite | 16.748 ms | 5 - 5 MB | NPU
|
| 74 |
+
| face_detector | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 9.379 ms | 5 - 174 MB | NPU
|
| 75 |
+
| face_detector | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 24.412 ms | 5 - 178 MB | NPU
|
| 76 |
+
| face_detector | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8275 | 28.202 ms | 0 - 150 MB | NPU
|
| 77 |
+
| face_detector | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 15.625 ms | 5 - 86 MB | NPU
|
| 78 |
+
| face_detector | QNN_DLC | float | Qualcomm® SA8775P | 16.528 ms | 2 - 153 MB | NPU
|
| 79 |
+
| face_detector | QNN_DLC | float | Qualcomm® SA8650P | 16.528 ms | 2 - 153 MB | NPU
|
| 80 |
+
| face_detector | QNN_DLC | float | Qualcomm® SA8255P | 16.528 ms | 2 - 153 MB | NPU
|
| 81 |
+
| face_detector | QNN_DLC | float | Qualcomm® QCS8450 | 24.412 ms | 5 - 178 MB | NPU
|
| 82 |
+
| face_detector | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 17.407 ms | 5 - 12 MB | NPU
|
| 83 |
+
| face_detector | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 16.748 ms | 5 - 5 MB | NPU
|
| 84 |
+
| face_detector | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 6.92 ms | 0 - 154 MB | NPU
|
| 85 |
+
| face_detector | QNN_DLC | float | Qualcomm® SA7255P | 28.202 ms | 0 - 150 MB | NPU
|
| 86 |
+
| face_detector | QNN_DLC | float | Qualcomm® SA8295P | 20.611 ms | 1 - 151 MB | NPU
|
| 87 |
+
| face_detector | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 6.92 ms | 0 - 154 MB | NPU
|
| 88 |
+
| face_detector | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 5.445 ms | 4 - 157 MB | NPU
|
| 89 |
+
| face_detector | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 9.25 ms | 2 - 169 MB | NPU
|
| 90 |
+
| face_detector | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 24.502 ms | 0 - 172 MB | NPU
|
| 91 |
+
| face_detector | TFLITE | float | Qualcomm® Dragonwing™ QCS8275 | 28.303 ms | 1 - 151 MB | NPU
|
| 92 |
+
| face_detector | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 15.719 ms | 1 - 3 MB | NPU
|
| 93 |
+
| face_detector | TFLITE | float | Qualcomm® SA8775P | 16.517 ms | 1 - 154 MB | NPU
|
| 94 |
+
| face_detector | TFLITE | float | Qualcomm® SA8650P | 16.517 ms | 1 - 154 MB | NPU
|
| 95 |
+
| face_detector | TFLITE | float | Qualcomm® SA8255P | 16.517 ms | 1 - 154 MB | NPU
|
| 96 |
+
| face_detector | TFLITE | float | Qualcomm® QCS8450 | 24.502 ms | 0 - 172 MB | NPU
|
| 97 |
+
| face_detector | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 16.905 ms | 0 - 9 MB | NPU
|
| 98 |
+
| face_detector | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 6.932 ms | 0 - 152 MB | NPU
|
| 99 |
+
| face_detector | TFLITE | float | Qualcomm® SA7255P | 28.303 ms | 1 - 151 MB | NPU
|
| 100 |
+
| face_detector | TFLITE | float | Qualcomm® SA8295P | 20.655 ms | 1 - 151 MB | NPU
|
| 101 |
+
| face_detector | TFLITE | float | Snapdragon® 8 Elite Mobile | 6.932 ms | 0 - 152 MB | NPU
|
| 102 |
+
| face_detector | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 5.532 ms | 1 - 157 MB | NPU
|
| 103 |
+
| pose_estimator | ONNX | float | Snapdragon® X2 Elite | 1.293 ms | 2 - 2 MB | NPU
|
| 104 |
+
| pose_estimator | ONNX | float | Snapdragon® X Elite | 2.625 ms | 76 - 76 MB | NPU
|
| 105 |
+
| pose_estimator | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 2.087 ms | 0 - 37 MB | NPU
|
| 106 |
+
| pose_estimator | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 5.55 ms | 0 - 40 MB | NPU
|
| 107 |
+
| pose_estimator | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 2.707 ms | 1 - 3 MB | NPU
|
| 108 |
+
| pose_estimator | ONNX | float | Qualcomm® QCS8450 | 5.55 ms | 0 - 40 MB | NPU
|
| 109 |
+
| pose_estimator | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 4.498 ms | 0 - 4 MB | NPU
|
| 110 |
+
| pose_estimator | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 2.625 ms | 76 - 76 MB | NPU
|
| 111 |
+
| pose_estimator | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 1.662 ms | 0 - 24 MB | NPU
|
| 112 |
+
| pose_estimator | ONNX | float | Snapdragon® 8 Elite Mobile | 1.662 ms | 0 - 24 MB | NPU
|
| 113 |
+
| pose_estimator | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.337 ms | 0 - 26 MB | NPU
|
| 114 |
+
| pose_estimator | QNN_DLC | float | Snapdragon® X2 Elite | 1.527 ms | 1 - 1 MB | NPU
|
| 115 |
+
| pose_estimator | QNN_DLC | float | Snapdragon® X Elite | 2.869 ms | 1 - 1 MB | NPU
|
| 116 |
+
| pose_estimator | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 2.236 ms | 0 - 39 MB | NPU
|
| 117 |
+
| pose_estimator | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 6.536 ms | 0 - 40 MB | NPU
|
| 118 |
+
| pose_estimator | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8275 | 17.831 ms | 1 - 25 MB | NPU
|
| 119 |
+
| pose_estimator | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 2.775 ms | 1 - 173 MB | NPU
|
| 120 |
+
| pose_estimator | QNN_DLC | float | Qualcomm® SA8775P | 4.828 ms | 1 - 26 MB | NPU
|
| 121 |
+
| pose_estimator | QNN_DLC | float | Qualcomm® SA8650P | 4.828 ms | 1 - 26 MB | NPU
|
| 122 |
+
| pose_estimator | QNN_DLC | float | Qualcomm® SA8255P | 4.828 ms | 1 - 26 MB | NPU
|
| 123 |
+
| pose_estimator | QNN_DLC | float | Qualcomm® QCS8450 | 6.536 ms | 0 - 40 MB | NPU
|
| 124 |
+
| pose_estimator | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 4.647 ms | 1 - 3 MB | NPU
|
| 125 |
+
| pose_estimator | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 2.869 ms | 1 - 1 MB | NPU
|
| 126 |
+
| pose_estimator | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 1.684 ms | 1 - 27 MB | NPU
|
| 127 |
+
| pose_estimator | QNN_DLC | float | Qualcomm® SA7255P | 17.831 ms | 1 - 25 MB | NPU
|
| 128 |
+
| pose_estimator | QNN_DLC | float | Qualcomm® SA8295P | 5.393 ms | 1 - 27 MB | NPU
|
| 129 |
+
| pose_estimator | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 1.684 ms | 1 - 27 MB | NPU
|
| 130 |
+
| pose_estimator | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.429 ms | 1 - 28 MB | NPU
|
| 131 |
+
| pose_estimator | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 2.244 ms | 0 - 44 MB | NPU
|
| 132 |
+
| pose_estimator | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 6.505 ms | 0 - 46 MB | NPU
|
| 133 |
+
| pose_estimator | TFLITE | float | Qualcomm® Dragonwing™ QCS8275 | 17.388 ms | 0 - 26 MB | NPU
|
| 134 |
+
| pose_estimator | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 2.849 ms | 0 - 3 MB | NPU
|
| 135 |
+
| pose_estimator | TFLITE | float | Qualcomm® SA8775P | 4.831 ms | 0 - 28 MB | NPU
|
| 136 |
+
| pose_estimator | TFLITE | float | Qualcomm® SA8650P | 4.831 ms | 0 - 28 MB | NPU
|
| 137 |
+
| pose_estimator | TFLITE | float | Qualcomm® SA8255P | 4.831 ms | 0 - 28 MB | NPU
|
| 138 |
+
| pose_estimator | TFLITE | float | Qualcomm® QCS8450 | 6.505 ms | 0 - 46 MB | NPU
|
| 139 |
+
| pose_estimator | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 4.649 ms | 0 - 78 MB | NPU
|
| 140 |
+
| pose_estimator | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 1.707 ms | 0 - 31 MB | NPU
|
| 141 |
| pose_estimator | TFLITE | float | Qualcomm® SA7255P | 17.388 ms | 0 - 26 MB | NPU
|
| 142 |
+
| pose_estimator | TFLITE | float | Qualcomm® SA8295P | 5.349 ms | 0 - 22 MB | NPU
|
| 143 |
+
| pose_estimator | TFLITE | float | Snapdragon® 8 Elite Mobile | 1.707 ms | 0 - 31 MB | NPU
|
| 144 |
+
| pose_estimator | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.378 ms | 0 - 27 MB | NPU
|
| 145 |
|
| 146 |
## License
|
| 147 |
* The license for the original implementation of SixDRepNet can be found
|
release_assets.json
CHANGED
|
@@ -1,27 +1,26 @@
|
|
| 1 |
{
|
| 2 |
-
"version": "0.
|
| 3 |
"precisions": {
|
| 4 |
"float": {
|
| 5 |
"universal_assets": {
|
| 6 |
-
"
|
| 7 |
"tool_versions": {
|
| 8 |
"qairt": "2.45.0.260326154327",
|
| 9 |
-
"
|
| 10 |
},
|
| 11 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/sixd_repnet/releases/v0.
|
| 12 |
},
|
| 13 |
"qnn_dlc": {
|
| 14 |
"tool_versions": {
|
| 15 |
"qairt": "2.45.0.260326154327"
|
| 16 |
},
|
| 17 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/sixd_repnet/releases/v0.
|
| 18 |
},
|
| 19 |
-
"
|
| 20 |
"tool_versions": {
|
| 21 |
-
"qairt": "2.45.0.260326154327"
|
| 22 |
-
"onnx_runtime": "1.25.0"
|
| 23 |
},
|
| 24 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/sixd_repnet/releases/v0.
|
| 25 |
}
|
| 26 |
}
|
| 27 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"version": "0.59.0",
|
| 3 |
"precisions": {
|
| 4 |
"float": {
|
| 5 |
"universal_assets": {
|
| 6 |
+
"onnx": {
|
| 7 |
"tool_versions": {
|
| 8 |
"qairt": "2.45.0.260326154327",
|
| 9 |
+
"onnx_runtime": "1.27.1"
|
| 10 |
},
|
| 11 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/sixd_repnet/releases/v0.59.0/sixd_repnet-onnx-float.zip"
|
| 12 |
},
|
| 13 |
"qnn_dlc": {
|
| 14 |
"tool_versions": {
|
| 15 |
"qairt": "2.45.0.260326154327"
|
| 16 |
},
|
| 17 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/sixd_repnet/releases/v0.59.0/sixd_repnet-qnn_dlc-float.zip"
|
| 18 |
},
|
| 19 |
+
"tflite": {
|
| 20 |
"tool_versions": {
|
| 21 |
+
"qairt": "2.45.0.260326154327"
|
|
|
|
| 22 |
},
|
| 23 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/sixd_repnet/releases/v0.59.0/sixd_repnet-tflite-float.zip"
|
| 24 |
}
|
| 25 |
}
|
| 26 |
}
|