v0.63.0
Browse filesSee https://github.com/qualcomm/ai-hub-models/releases/v0.63.0 for changelog.
- README.md +72 -78
- release_assets.json +11 -11
README.md
CHANGED
|
@@ -16,7 +16,7 @@ pipeline_tag: image-classification
|
|
| 16 |
SwinSmall is a machine learning model that can classify images from the Imagenet dataset. It can also be used as a backbone in building more complex models for specific use cases.
|
| 17 |
|
| 18 |
This is based on the implementation of Swin-Small found [here](https://github.com/pytorch/vision/blob/main/torchvision/models/swin_transformer.py).
|
| 19 |
-
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.
|
| 20 |
|
| 21 |
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.
|
| 22 |
|
|
@@ -29,25 +29,25 @@ Below are pre-exported model assets ready for deployment.
|
|
| 29 |
|
| 30 |
| Runtime | Precision | Chipset | SDK Versions | Download |
|
| 31 |
|---|---|---|---|---|
|
| 32 |
-
| ONNX | float | Universal | QAIRT 2.
|
| 33 |
-
| ONNX | w8a16 | Universal | QAIRT 2.
|
| 34 |
-
| QNN_DLC | float | Universal | QAIRT 2.
|
| 35 |
-
| QNN_DLC | w8a16 | Universal | QAIRT 2.
|
| 36 |
-
| TFLITE | float | Universal | QAIRT 2.
|
| 37 |
|
| 38 |
For more device-specific assets and performance metrics, visit **[Swin-Small on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/swin_small)**.
|
| 39 |
|
| 40 |
|
| 41 |
### Option 2: Export with Custom Configurations
|
| 42 |
|
| 43 |
-
Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.
|
| 44 |
- Custom weights (e.g., fine-tuned checkpoints)
|
| 45 |
- Custom input shapes
|
| 46 |
- Target device and runtime configurations
|
| 47 |
|
| 48 |
This option is ideal if you need to customize the model beyond the default configuration provided here.
|
| 49 |
|
| 50 |
-
See our repository for [Swin-Small on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.
|
| 51 |
|
| 52 |
## Model Details
|
| 53 |
|
|
@@ -63,82 +63,76 @@ See our repository for [Swin-Small on GitHub](https://github.com/qualcomm/ai-hub
|
|
| 63 |
## Performance Summary
|
| 64 |
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
|
| 65 |
|---|---|---|---|---|---|---
|
| 66 |
-
| Swin-Small | ONNX | float | Snapdragon®
|
| 67 |
-
| Swin-Small | ONNX | float | Snapdragon®
|
| 68 |
-
| Swin-Small | ONNX | float | Snapdragon®
|
| 69 |
-
| Swin-Small | ONNX | float | Snapdragon®
|
| 70 |
-
| Swin-Small | ONNX | float |
|
| 71 |
-
| Swin-Small | ONNX | float |
|
| 72 |
-
| Swin-Small | ONNX | float | Qualcomm®
|
| 73 |
-
| Swin-Small | ONNX | float | Qualcomm® Dragonwing™
|
| 74 |
-
| Swin-Small | ONNX | float | Qualcomm®
|
| 75 |
-
| Swin-Small | ONNX | float | Qualcomm® Dragonwing™
|
| 76 |
-
| Swin-Small | ONNX | float |
|
| 77 |
-
| Swin-Small | ONNX | float |
|
| 78 |
-
| Swin-Small | ONNX | w8a16 | Snapdragon®
|
| 79 |
-
| Swin-Small | ONNX | w8a16 | Snapdragon®
|
| 80 |
-
| Swin-Small | ONNX | w8a16 | Snapdragon®
|
| 81 |
-
| Swin-Small | ONNX | w8a16 | Snapdragon®
|
| 82 |
-
| Swin-Small | ONNX | w8a16 |
|
| 83 |
-
| Swin-Small | ONNX | w8a16 |
|
| 84 |
-
| Swin-Small | ONNX | w8a16 | Qualcomm® Dragonwing™
|
| 85 |
-
| Swin-Small | ONNX | w8a16 | Qualcomm®
|
| 86 |
-
| Swin-Small | ONNX | w8a16 | Qualcomm® Dragonwing™
|
| 87 |
-
| Swin-Small | ONNX | w8a16 | Qualcomm®
|
| 88 |
-
| Swin-Small | ONNX | w8a16 | Qualcomm® Dragonwing™
|
| 89 |
-
| Swin-Small | ONNX | w8a16 | Qualcomm® Dragonwing™
|
| 90 |
-
| Swin-Small | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-
|
| 91 |
-
| Swin-Small | ONNX | w8a16 |
|
| 92 |
-
| Swin-Small | ONNX | w8a16 |
|
| 93 |
-
| Swin-Small | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile |
|
| 94 |
-
| Swin-Small | QNN_DLC | float | Snapdragon®
|
| 95 |
-
| Swin-Small | QNN_DLC | float | Snapdragon®
|
| 96 |
-
| Swin-Small | QNN_DLC | float | Snapdragon®
|
| 97 |
-
| Swin-Small | QNN_DLC | float | Snapdragon®
|
| 98 |
-
| Swin-Small | QNN_DLC | float |
|
| 99 |
-
| Swin-Small | QNN_DLC | float |
|
| 100 |
-
| Swin-Small | QNN_DLC | float | Qualcomm®
|
|
|
|
| 101 |
| Swin-Small | QNN_DLC | float | Qualcomm® SA8650P | 17.421 ms | 1 - 593 MB | NPU
|
| 102 |
| Swin-Small | QNN_DLC | float | Qualcomm® SA8255P | 17.421 ms | 1 - 593 MB | NPU
|
| 103 |
-
| Swin-Small | QNN_DLC | float | Qualcomm® QCS8450 | 23.
|
| 104 |
-
| Swin-Small | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 17.
|
| 105 |
-
| Swin-Small | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 |
|
| 106 |
-
| Swin-Small | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 7.
|
| 107 |
-
| Swin-Small | QNN_DLC | float | Qualcomm®
|
| 108 |
-
| Swin-Small | QNN_DLC |
|
| 109 |
-
| Swin-Small | QNN_DLC |
|
| 110 |
-
| Swin-Small | QNN_DLC |
|
| 111 |
-
| Swin-Small | QNN_DLC | w8a16 | Snapdragon®
|
| 112 |
-
| Swin-Small | QNN_DLC | w8a16 | Snapdragon®
|
| 113 |
-
| Swin-Small | QNN_DLC | w8a16 |
|
| 114 |
-
| Swin-Small | QNN_DLC | w8a16 | Qualcomm® Dragonwing™
|
| 115 |
-
| Swin-Small | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 16.207 ms | 0 - 3 MB | NPU
|
| 116 |
-
| Swin-Small | QNN_DLC | w8a16 | Qualcomm® SA8775P | 16.763 ms | 0 - 638 MB | NPU
|
| 117 |
| Swin-Small | QNN_DLC | w8a16 | Qualcomm® SA8650P | 16.763 ms | 0 - 638 MB | NPU
|
| 118 |
| Swin-Small | QNN_DLC | w8a16 | Qualcomm® SA8255P | 16.763 ms | 0 - 638 MB | NPU
|
| 119 |
-
| Swin-Small | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 17.
|
| 120 |
-
| Swin-Small | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 17.
|
| 121 |
-
| Swin-Small | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-6690 |
|
| 122 |
-
| Swin-Small | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 17.
|
| 123 |
-
| Swin-Small | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-8750 |
|
| 124 |
-
| Swin-Small | QNN_DLC | w8a16 |
|
| 125 |
-
| Swin-Small |
|
| 126 |
-
| Swin-Small |
|
| 127 |
-
| Swin-Small |
|
| 128 |
-
| Swin-Small | TFLITE | float | Snapdragon® 8 Gen
|
| 129 |
-
| Swin-Small | TFLITE | float |
|
| 130 |
-
| Swin-Small | TFLITE | float | Qualcomm® Dragonwing™
|
| 131 |
-
| Swin-Small | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 15.589 ms | 0 - 4 MB | NPU
|
| 132 |
-
| Swin-Small | TFLITE | float | Qualcomm® SA8775P | 17.46 ms | 0 - 306 MB | NPU
|
| 133 |
| Swin-Small | TFLITE | float | Qualcomm® SA8650P | 17.46 ms | 0 - 306 MB | NPU
|
| 134 |
| Swin-Small | TFLITE | float | Qualcomm® SA8255P | 17.46 ms | 0 - 306 MB | NPU
|
| 135 |
-
| Swin-Small | TFLITE | float | Qualcomm® QCS8450 | 23.
|
| 136 |
-
| Swin-Small | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 |
|
| 137 |
-
| Swin-Small | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 7.
|
| 138 |
-
| Swin-Small | TFLITE | float | Qualcomm®
|
| 139 |
-
| Swin-Small | TFLITE | float | Qualcomm® SA8295P | 22.992 ms | 0 - 297 MB | NPU
|
| 140 |
-
| Swin-Small | TFLITE | float | Snapdragon® 8 Elite Mobile | 7.797 ms | 0 - 296 MB | NPU
|
| 141 |
-
| Swin-Small | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 6.599 ms | 0 - 320 MB | NPU
|
| 142 |
|
| 143 |
## License
|
| 144 |
* The license for the original implementation of Swin-Small can be found
|
|
|
|
| 16 |
SwinSmall is a machine learning model that can classify images from the Imagenet dataset. It can also be used as a backbone in building more complex models for specific use cases.
|
| 17 |
|
| 18 |
This is based on the implementation of Swin-Small found [here](https://github.com/pytorch/vision/blob/main/torchvision/models/swin_transformer.py).
|
| 19 |
+
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/v0.63.0/src/qai_hub_models/models/swin_small) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
|
| 20 |
|
| 21 |
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.
|
| 22 |
|
|
|
|
| 29 |
|
| 30 |
| Runtime | Precision | Chipset | SDK Versions | Download |
|
| 31 |
|---|---|---|---|---|
|
| 32 |
+
| ONNX | float | Universal | QAIRT 2.50, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/swin_small/releases/v0.63.0/swin_small-onnx-float.zip)
|
| 33 |
+
| ONNX | w8a16 | Universal | QAIRT 2.50, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/swin_small/releases/v0.63.0/swin_small-onnx-w8a16.zip)
|
| 34 |
+
| QNN_DLC | float | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/swin_small/releases/v0.63.0/swin_small-qnn_dlc-float.zip)
|
| 35 |
+
| QNN_DLC | w8a16 | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/swin_small/releases/v0.63.0/swin_small-qnn_dlc-w8a16.zip)
|
| 36 |
+
| TFLITE | float | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/swin_small/releases/v0.63.0/swin_small-tflite-float.zip)
|
| 37 |
|
| 38 |
For more device-specific assets and performance metrics, visit **[Swin-Small on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/swin_small)**.
|
| 39 |
|
| 40 |
|
| 41 |
### Option 2: Export with Custom Configurations
|
| 42 |
|
| 43 |
+
Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.63.0/src/qai_hub_models/models/swin_small) Python library to compile and export the model with your own:
|
| 44 |
- Custom weights (e.g., fine-tuned checkpoints)
|
| 45 |
- Custom input shapes
|
| 46 |
- Target device and runtime configurations
|
| 47 |
|
| 48 |
This option is ideal if you need to customize the model beyond the default configuration provided here.
|
| 49 |
|
| 50 |
+
See our repository for [Swin-Small on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.63.0/src/qai_hub_models/models/swin_small) for usage instructions.
|
| 51 |
|
| 52 |
## Model Details
|
| 53 |
|
|
|
|
| 63 |
## Performance Summary
|
| 64 |
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
|
| 65 |
|---|---|---|---|---|---|---
|
| 66 |
+
| Swin-Small | ONNX | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 6.249 ms | 1 - 320 MB | NPU
|
| 67 |
+
| Swin-Small | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 7.642 ms | 1 - 307 MB | NPU
|
| 68 |
+
| Swin-Small | ONNX | float | Snapdragon® X2 Elite | 6.437 ms | 2 - 2 MB | NPU
|
| 69 |
+
| Swin-Small | ONNX | float | Snapdragon® X Elite | 15.714 ms | 101 - 101 MB | NPU
|
| 70 |
+
| Swin-Small | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 9.971 ms | 0 - 438 MB | NPU
|
| 71 |
+
| Swin-Small | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 23.356 ms | 0 - 425 MB | NPU
|
| 72 |
+
| Swin-Small | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 15.275 ms | 0 - 5 MB | NPU
|
| 73 |
+
| Swin-Small | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 15.184 ms | 0 - 114 MB | NPU
|
| 74 |
+
| Swin-Small | ONNX | float | Qualcomm® QCS8450 | 23.356 ms | 0 - 425 MB | NPU
|
| 75 |
+
| Swin-Small | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 16.724 ms | 1 - 5 MB | NPU
|
| 76 |
+
| Swin-Small | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 15.714 ms | 101 - 101 MB | NPU
|
| 77 |
+
| Swin-Small | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 7.642 ms | 1 - 307 MB | NPU
|
| 78 |
+
| Swin-Small | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 5.153 ms | 0 - 340 MB | NPU
|
| 79 |
+
| Swin-Small | ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 6.605 ms | 0 - 330 MB | NPU
|
| 80 |
+
| Swin-Small | ONNX | w8a16 | Snapdragon® X2 Elite | 5.364 ms | 1 - 1 MB | NPU
|
| 81 |
+
| Swin-Small | ONNX | w8a16 | Snapdragon® X Elite | 13.505 ms | 54 - 54 MB | NPU
|
| 82 |
+
| Swin-Small | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 8.856 ms | 0 - 444 MB | NPU
|
| 83 |
+
| Swin-Small | ONNX | w8a16 | Snapdragon® 8 Gen 1 Mobile | 16.454 ms | 0 - 441 MB | NPU
|
| 84 |
+
| Swin-Small | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 26.821 ms | 0 - 4 MB | NPU
|
| 85 |
+
| Swin-Small | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 11.558 ms | 0 - 5 MB | NPU
|
| 86 |
+
| Swin-Small | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 13.067 ms | 0 - 59 MB | NPU
|
| 87 |
+
| Swin-Small | ONNX | w8a16 | Qualcomm® QCS8450 | 16.454 ms | 0 - 441 MB | NPU
|
| 88 |
+
| Swin-Small | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 13.688 ms | 0 - 4 MB | NPU
|
| 89 |
+
| Swin-Small | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 13.505 ms | 54 - 54 MB | NPU
|
| 90 |
+
| Swin-Small | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 66.905 ms | 0 - 535 MB | NPU
|
| 91 |
+
| Swin-Small | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 14.201 ms | 0 - 374 MB | NPU
|
| 92 |
+
| Swin-Small | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 6.605 ms | 0 - 330 MB | NPU
|
| 93 |
+
| Swin-Small | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 14.201 ms | 0 - 374 MB | NPU
|
| 94 |
+
| Swin-Small | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 6.098 ms | 0 - 286 MB | NPU
|
| 95 |
+
| Swin-Small | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 7.447 ms | 1 - 270 MB | NPU
|
| 96 |
+
| Swin-Small | QNN_DLC | float | Snapdragon® X2 Elite | 6.785 ms | 1 - 1 MB | NPU
|
| 97 |
+
| Swin-Small | QNN_DLC | float | Snapdragon® X Elite | 15.78 ms | 1 - 1 MB | NPU
|
| 98 |
+
| Swin-Small | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 9.87 ms | 0 - 402 MB | NPU
|
| 99 |
+
| Swin-Small | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 23.608 ms | 0 - 393 MB | NPU
|
| 100 |
+
| Swin-Small | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 15.206 ms | 1 - 4 MB | NPU
|
| 101 |
+
| Swin-Small | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 14.931 ms | 1 - 3 MB | NPU
|
| 102 |
| Swin-Small | QNN_DLC | float | Qualcomm® SA8650P | 17.421 ms | 1 - 593 MB | NPU
|
| 103 |
| Swin-Small | QNN_DLC | float | Qualcomm® SA8255P | 17.421 ms | 1 - 593 MB | NPU
|
| 104 |
+
| Swin-Small | QNN_DLC | float | Qualcomm® QCS8450 | 23.608 ms | 0 - 393 MB | NPU
|
| 105 |
+
| Swin-Small | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 17.142 ms | 3 - 5 MB | NPU
|
| 106 |
+
| Swin-Small | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 15.78 ms | 1 - 1 MB | NPU
|
| 107 |
+
| Swin-Small | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 7.447 ms | 1 - 270 MB | NPU
|
| 108 |
+
| Swin-Small | QNN_DLC | float | Qualcomm® SA8295P | 22.117 ms | 1 - 263 MB | NPU
|
| 109 |
+
| Swin-Small | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 6.033 ms | 0 - 316 MB | NPU
|
| 110 |
+
| Swin-Small | QNN_DLC | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 7.854 ms | 0 - 305 MB | NPU
|
| 111 |
+
| Swin-Small | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 6.569 ms | 0 - 0 MB | NPU
|
| 112 |
+
| Swin-Small | QNN_DLC | w8a16 | Snapdragon® X Elite | 17.107 ms | 0 - 0 MB | NPU
|
| 113 |
+
| Swin-Small | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 10.943 ms | 0 - 408 MB | NPU
|
| 114 |
+
| Swin-Small | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 14.468 ms | 0 - 4 MB | NPU
|
| 115 |
+
| Swin-Small | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 16.13 ms | 0 - 3 MB | NPU
|
|
|
|
|
|
|
| 116 |
| Swin-Small | QNN_DLC | w8a16 | Qualcomm® SA8650P | 16.763 ms | 0 - 638 MB | NPU
|
| 117 |
| Swin-Small | QNN_DLC | w8a16 | Qualcomm® SA8255P | 16.763 ms | 0 - 638 MB | NPU
|
| 118 |
+
| Swin-Small | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 17.062 ms | 0 - 3 MB | NPU
|
| 119 |
+
| Swin-Small | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 17.107 ms | 0 - 0 MB | NPU
|
| 120 |
+
| Swin-Small | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 75.035 ms | 0 - 512 MB | NPU
|
| 121 |
+
| Swin-Small | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 17.104 ms | 0 - 352 MB | NPU
|
| 122 |
+
| Swin-Small | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 7.854 ms | 0 - 305 MB | NPU
|
| 123 |
+
| Swin-Small | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 17.104 ms | 0 - 352 MB | NPU
|
| 124 |
+
| Swin-Small | TFLITE | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 6.522 ms | 0 - 313 MB | NPU
|
| 125 |
+
| Swin-Small | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 7.764 ms | 0 - 290 MB | NPU
|
| 126 |
+
| Swin-Small | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 9.993 ms | 0 - 419 MB | NPU
|
| 127 |
+
| Swin-Small | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 23.439 ms | 0 - 408 MB | NPU
|
| 128 |
+
| Swin-Small | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 15.275 ms | 0 - 105 MB | NPU
|
| 129 |
+
| Swin-Small | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 15.191 ms | 0 - 5 MB | NPU
|
|
|
|
|
|
|
| 130 |
| Swin-Small | TFLITE | float | Qualcomm® SA8650P | 17.46 ms | 0 - 306 MB | NPU
|
| 131 |
| Swin-Small | TFLITE | float | Qualcomm® SA8255P | 17.46 ms | 0 - 306 MB | NPU
|
| 132 |
+
| Swin-Small | TFLITE | float | Qualcomm® QCS8450 | 23.439 ms | 0 - 408 MB | NPU
|
| 133 |
+
| Swin-Small | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 17.434 ms | 0 - 104 MB | NPU
|
| 134 |
+
| Swin-Small | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 7.764 ms | 0 - 290 MB | NPU
|
| 135 |
+
| Swin-Small | TFLITE | float | Qualcomm® SA8295P | 22.528 ms | 0 - 284 MB | NPU
|
|
|
|
|
|
|
|
|
|
| 136 |
|
| 137 |
## License
|
| 138 |
* The license for the original implementation of Swin-Small can be found
|
release_assets.json
CHANGED
|
@@ -1,26 +1,26 @@
|
|
| 1 |
{
|
| 2 |
-
"version": "0.
|
| 3 |
"precisions": {
|
| 4 |
"float": {
|
| 5 |
"universal_assets": {
|
| 6 |
"onnx": {
|
| 7 |
"tool_versions": {
|
| 8 |
-
"qairt": "2.
|
| 9 |
"onnx_runtime": "1.27.1"
|
| 10 |
},
|
| 11 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/swin_small/releases/v0.
|
| 12 |
},
|
| 13 |
"qnn_dlc": {
|
| 14 |
"tool_versions": {
|
| 15 |
-
"qairt": "2.
|
| 16 |
},
|
| 17 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/swin_small/releases/v0.
|
| 18 |
},
|
| 19 |
"tflite": {
|
| 20 |
"tool_versions": {
|
| 21 |
-
"qairt": "2.
|
| 22 |
},
|
| 23 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/swin_small/releases/v0.
|
| 24 |
}
|
| 25 |
}
|
| 26 |
},
|
|
@@ -28,16 +28,16 @@
|
|
| 28 |
"universal_assets": {
|
| 29 |
"onnx": {
|
| 30 |
"tool_versions": {
|
| 31 |
-
"qairt": "2.
|
| 32 |
"onnx_runtime": "1.27.1"
|
| 33 |
},
|
| 34 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/swin_small/releases/v0.
|
| 35 |
},
|
| 36 |
"qnn_dlc": {
|
| 37 |
"tool_versions": {
|
| 38 |
-
"qairt": "2.
|
| 39 |
},
|
| 40 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/swin_small/releases/v0.
|
| 41 |
}
|
| 42 |
}
|
| 43 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"version": "0.63.0",
|
| 3 |
"precisions": {
|
| 4 |
"float": {
|
| 5 |
"universal_assets": {
|
| 6 |
"onnx": {
|
| 7 |
"tool_versions": {
|
| 8 |
+
"qairt": "2.50.0.260828221209",
|
| 9 |
"onnx_runtime": "1.27.1"
|
| 10 |
},
|
| 11 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/swin_small/releases/v0.63.0/swin_small-onnx-float.zip"
|
| 12 |
},
|
| 13 |
"qnn_dlc": {
|
| 14 |
"tool_versions": {
|
| 15 |
+
"qairt": "2.50.0.260828221209"
|
| 16 |
},
|
| 17 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/swin_small/releases/v0.63.0/swin_small-qnn_dlc-float.zip"
|
| 18 |
},
|
| 19 |
"tflite": {
|
| 20 |
"tool_versions": {
|
| 21 |
+
"qairt": "2.50.0.260828221209"
|
| 22 |
},
|
| 23 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/swin_small/releases/v0.63.0/swin_small-tflite-float.zip"
|
| 24 |
}
|
| 25 |
}
|
| 26 |
},
|
|
|
|
| 28 |
"universal_assets": {
|
| 29 |
"onnx": {
|
| 30 |
"tool_versions": {
|
| 31 |
+
"qairt": "2.50.0.260828221209",
|
| 32 |
"onnx_runtime": "1.27.1"
|
| 33 |
},
|
| 34 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/swin_small/releases/v0.63.0/swin_small-onnx-w8a16.zip"
|
| 35 |
},
|
| 36 |
"qnn_dlc": {
|
| 37 |
"tool_versions": {
|
| 38 |
+
"qairt": "2.50.0.260828221209"
|
| 39 |
},
|
| 40 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/swin_small/releases/v0.63.0/swin_small-qnn_dlc-w8a16.zip"
|
| 41 |
}
|
| 42 |
}
|
| 43 |
}
|