v0.64.0
Browse filesSee https://github.com/qualcomm/ai-hub-models/releases/v0.64.0 for changelog.
- README.md +79 -75
- release_assets.json +8 -8
README.md
CHANGED
|
@@ -16,7 +16,7 @@ pipeline_tag: image-classification
|
|
| 16 |
SwinBase 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-Base 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 2.50, ONNX Runtime 1.
|
| 33 |
-
| ONNX | w8a16 | Universal | QAIRT 2.50, ONNX Runtime 1.
|
| 34 |
-
| QNN_DLC | float | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/swin_base/releases/v0.
|
| 35 |
-
| QNN_DLC | w8a16 | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/swin_base/releases/v0.
|
| 36 |
-
| TFLITE | float | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/swin_base/releases/v0.
|
| 37 |
|
| 38 |
For more device-specific assets and performance metrics, visit **[Swin-Base on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/swin_base)**.
|
| 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-Base on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.
|
| 51 |
|
| 52 |
## Model Details
|
| 53 |
|
|
@@ -63,75 +63,79 @@ See our repository for [Swin-Base 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-Base | ONNX | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 7.
|
| 67 |
-
| Swin-Base | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 9.
|
| 68 |
-
| Swin-Base | ONNX | float | Snapdragon® X2 Elite | 7.
|
| 69 |
-
| Swin-Base | ONNX | float | Snapdragon® X Elite | 19.
|
| 70 |
-
| Swin-Base | ONNX | float | Snapdragon® 8 Gen 3 Mobile |
|
| 71 |
-
| Swin-Base | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 28.
|
| 72 |
-
| Swin-Base | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 20.
|
| 73 |
-
| Swin-Base | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 18.
|
| 74 |
-
| Swin-Base | ONNX | float | Qualcomm® QCS8450 | 28.
|
| 75 |
-
| Swin-Base | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 21.
|
| 76 |
-
| Swin-Base | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 19.
|
| 77 |
-
| Swin-Base | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 9.
|
| 78 |
-
| Swin-Base | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 6.
|
| 79 |
-
| Swin-Base | ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile |
|
| 80 |
-
| Swin-Base | ONNX | w8a16 | Snapdragon® X2 Elite | 6.
|
| 81 |
-
| Swin-Base | ONNX | w8a16 | Snapdragon® X Elite | 16.
|
| 82 |
-
| Swin-Base | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 10.
|
| 83 |
-
| Swin-Base | ONNX | w8a16 | Snapdragon® 8 Gen 1 Mobile | 20.
|
| 84 |
-
| Swin-Base | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS6490 |
|
| 85 |
-
| Swin-Base | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 14.
|
| 86 |
-
| Swin-Base | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 15.
|
| 87 |
-
| Swin-Base | ONNX | w8a16 | Qualcomm® QCS8450 | 20.
|
| 88 |
-
| Swin-Base | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 16.
|
| 89 |
-
| Swin-Base | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 16.
|
| 90 |
-
| Swin-Base | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-6690 |
|
| 91 |
-
| Swin-Base | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 17.
|
| 92 |
-
| Swin-Base | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-8750 |
|
| 93 |
-
| Swin-Base | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 17.
|
| 94 |
-
| Swin-Base | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 7.
|
| 95 |
-
| Swin-Base | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 8.
|
| 96 |
-
| Swin-Base | QNN_DLC | float | Snapdragon® X2 Elite | 7.
|
| 97 |
-
| Swin-Base | QNN_DLC | float | Snapdragon® X Elite | 18.
|
| 98 |
-
| Swin-Base | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 12.
|
| 99 |
-
| Swin-Base | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 27.
|
| 100 |
-
| Swin-Base | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 |
|
| 101 |
-
| Swin-Base | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 17.
|
| 102 |
-
| Swin-Base | QNN_DLC | float | Qualcomm®
|
| 103 |
-
| Swin-Base | QNN_DLC | float | Qualcomm®
|
| 104 |
-
| Swin-Base | QNN_DLC | float | Qualcomm®
|
| 105 |
-
| Swin-Base | QNN_DLC | float | Qualcomm®
|
| 106 |
-
| Swin-Base | QNN_DLC | float | Qualcomm®
|
| 107 |
-
| Swin-Base | QNN_DLC |
|
| 108 |
-
| Swin-Base | QNN_DLC |
|
| 109 |
-
| Swin-Base | QNN_DLC |
|
| 110 |
-
| Swin-Base | QNN_DLC | w8a16 | Snapdragon®
|
| 111 |
-
| Swin-Base | QNN_DLC | w8a16 | Snapdragon® 8
|
| 112 |
-
| Swin-Base | QNN_DLC | w8a16 |
|
| 113 |
-
| Swin-Base | QNN_DLC | w8a16 |
|
|
|
|
|
|
|
|
|
|
| 114 |
| Swin-Base | QNN_DLC | w8a16 | Qualcomm® SA8650P | 19.574 ms | 0 - 411 MB | NPU
|
| 115 |
| Swin-Base | QNN_DLC | w8a16 | Qualcomm® SA8255P | 19.574 ms | 0 - 411 MB | NPU
|
| 116 |
-
| Swin-Base | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 19.
|
| 117 |
-
| Swin-Base | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 20.
|
| 118 |
-
| Swin-Base | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-6690 |
|
| 119 |
-
| Swin-Base | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 21.
|
| 120 |
-
| Swin-Base | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 9.
|
| 121 |
-
| Swin-Base | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 21.
|
| 122 |
-
| Swin-Base | TFLITE | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 7.
|
| 123 |
-
| Swin-Base | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 9.
|
| 124 |
-
| Swin-Base | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 12.
|
| 125 |
-
| Swin-Base | TFLITE | float | Snapdragon® 8 Gen 1 Mobile |
|
| 126 |
-
| Swin-Base | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 20.
|
| 127 |
-
| Swin-Base | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 18.
|
| 128 |
-
| Swin-Base | TFLITE | float | Qualcomm® SA8775P | 21.
|
| 129 |
-
| Swin-Base | TFLITE | float | Qualcomm® SA8650P | 21.
|
| 130 |
-
| Swin-Base | TFLITE | float | Qualcomm® SA8255P | 21.
|
| 131 |
-
| Swin-Base | TFLITE | float | Qualcomm® QCS8450 |
|
| 132 |
-
| Swin-Base | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 21.
|
| 133 |
-
| Swin-Base | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 9.
|
| 134 |
-
| Swin-Base | TFLITE | float | Qualcomm®
|
|
|
|
| 135 |
|
| 136 |
## License
|
| 137 |
* The license for the original implementation of Swin-Base can be found
|
|
|
|
| 16 |
SwinBase 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-Base 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/v0.64.0/src/qai_hub_models/models/swin_base) 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 1.30.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/swin_base/releases/v0.64.0/swin_base-onnx-float.zip)
|
| 33 |
+
| ONNX | w8a16 | Universal | QAIRT 2.50, ONNX Runtime 1.30.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/swin_base/releases/v0.64.0/swin_base-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_base/releases/v0.64.0/swin_base-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_base/releases/v0.64.0/swin_base-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_base/releases/v0.64.0/swin_base-tflite-float.zip)
|
| 37 |
|
| 38 |
For more device-specific assets and performance metrics, visit **[Swin-Base on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/swin_base)**.
|
| 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/v0.64.0/src/qai_hub_models/models/swin_base) 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-Base on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.64.0/src/qai_hub_models/models/swin_base) 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-Base | ONNX | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 7.624 ms | 0 - 388 MB | NPU
|
| 67 |
+
| Swin-Base | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 9.433 ms | 1 - 371 MB | NPU
|
| 68 |
+
| Swin-Base | ONNX | float | Snapdragon® X2 Elite | 7.812 ms | 2 - 2 MB | NPU
|
| 69 |
+
| Swin-Base | ONNX | float | Snapdragon® X Elite | 19.095 ms | 175 - 175 MB | NPU
|
| 70 |
+
| Swin-Base | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 12.56 ms | 0 - 528 MB | NPU
|
| 71 |
+
| Swin-Base | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 28.179 ms | 1 - 520 MB | NPU
|
| 72 |
+
| Swin-Base | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 20.457 ms | 0 - 5 MB | NPU
|
| 73 |
+
| Swin-Base | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 18.522 ms | 0 - 194 MB | NPU
|
| 74 |
+
| Swin-Base | ONNX | float | Qualcomm® QCS8450 | 28.179 ms | 1 - 520 MB | NPU
|
| 75 |
+
| Swin-Base | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 21.987 ms | 0 - 4 MB | NPU
|
| 76 |
+
| Swin-Base | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 19.095 ms | 175 - 175 MB | NPU
|
| 77 |
+
| Swin-Base | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 9.433 ms | 1 - 371 MB | NPU
|
| 78 |
+
| Swin-Base | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 6.143 ms | 0 - 414 MB | NPU
|
| 79 |
+
| Swin-Base | ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 7.966 ms | 0 - 399 MB | NPU
|
| 80 |
+
| Swin-Base | ONNX | w8a16 | Snapdragon® X2 Elite | 6.313 ms | 1 - 1 MB | NPU
|
| 81 |
+
| Swin-Base | ONNX | w8a16 | Snapdragon® X Elite | 16.391 ms | 93 - 93 MB | NPU
|
| 82 |
+
| Swin-Base | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 10.723 ms | 0 - 538 MB | NPU
|
| 83 |
+
| Swin-Base | ONNX | w8a16 | Snapdragon® 8 Gen 1 Mobile | 20.247 ms | 0 - 537 MB | NPU
|
| 84 |
+
| Swin-Base | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 39.041 ms | 0 - 4 MB | NPU
|
| 85 |
+
| Swin-Base | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 14.394 ms | 0 - 4 MB | NPU
|
| 86 |
+
| Swin-Base | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 15.89 ms | 0 - 518 MB | NPU
|
| 87 |
+
| Swin-Base | ONNX | w8a16 | Qualcomm® QCS8450 | 20.247 ms | 0 - 537 MB | NPU
|
| 88 |
+
| Swin-Base | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 16.163 ms | 0 - 4 MB | NPU
|
| 89 |
+
| Swin-Base | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 16.391 ms | 93 - 93 MB | NPU
|
| 90 |
+
| Swin-Base | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 108.62 ms | 0 - 667 MB | NPU
|
| 91 |
+
| Swin-Base | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 17.916 ms | 0 - 613 MB | NPU
|
| 92 |
+
| Swin-Base | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 7.966 ms | 0 - 399 MB | NPU
|
| 93 |
+
| Swin-Base | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 17.916 ms | 0 - 613 MB | NPU
|
| 94 |
+
| Swin-Base | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 7.17 ms | 0 - 370 MB | NPU
|
| 95 |
+
| Swin-Base | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 8.965 ms | 1 - 353 MB | NPU
|
| 96 |
+
| Swin-Base | QNN_DLC | float | Snapdragon® X2 Elite | 7.868 ms | 1 - 1 MB | NPU
|
| 97 |
+
| Swin-Base | QNN_DLC | float | Snapdragon® X Elite | 18.641 ms | 1 - 1 MB | NPU
|
| 98 |
+
| Swin-Base | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 12.199 ms | 1 - 507 MB | NPU
|
| 99 |
+
| Swin-Base | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 27.857 ms | 0 - 492 MB | NPU
|
| 100 |
+
| Swin-Base | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 19.82 ms | 1 - 4 MB | NPU
|
| 101 |
+
| Swin-Base | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 17.928 ms | 1 - 322 MB | NPU
|
| 102 |
+
| Swin-Base | QNN_DLC | float | Qualcomm® SA8775P | 20.855 ms | 1 - 351 MB | NPU
|
| 103 |
+
| Swin-Base | QNN_DLC | float | Qualcomm® SA8650P | 20.855 ms | 1 - 351 MB | NPU
|
| 104 |
+
| Swin-Base | QNN_DLC | float | Qualcomm® SA8255P | 20.855 ms | 1 - 351 MB | NPU
|
| 105 |
+
| Swin-Base | QNN_DLC | float | Qualcomm® QCS8450 | 27.857 ms | 0 - 492 MB | NPU
|
| 106 |
+
| Swin-Base | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 21.148 ms | 3 - 5 MB | NPU
|
| 107 |
+
| Swin-Base | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 18.641 ms | 1 - 1 MB | NPU
|
| 108 |
+
| Swin-Base | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 8.965 ms | 1 - 353 MB | NPU
|
| 109 |
+
| Swin-Base | QNN_DLC | float | Qualcomm® SA8295P | 27.016 ms | 1 - 343 MB | NPU
|
| 110 |
+
| Swin-Base | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 7.138 ms | 0 - 401 MB | NPU
|
| 111 |
+
| Swin-Base | QNN_DLC | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 9.3 ms | 0 - 388 MB | NPU
|
| 112 |
+
| Swin-Base | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 7.645 ms | 0 - 0 MB | NPU
|
| 113 |
+
| Swin-Base | QNN_DLC | w8a16 | Snapdragon® X Elite | 20.238 ms | 0 - 0 MB | NPU
|
| 114 |
+
| Swin-Base | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 12.963 ms | 0 - 512 MB | NPU
|
| 115 |
+
| Swin-Base | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 17.063 ms | 0 - 4 MB | NPU
|
| 116 |
+
| Swin-Base | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 19.506 ms | 0 - 2 MB | NPU
|
| 117 |
| Swin-Base | QNN_DLC | w8a16 | Qualcomm® SA8650P | 19.574 ms | 0 - 411 MB | NPU
|
| 118 |
| Swin-Base | QNN_DLC | w8a16 | Qualcomm® SA8255P | 19.574 ms | 0 - 411 MB | NPU
|
| 119 |
+
| Swin-Base | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 19.858 ms | 2 - 5 MB | NPU
|
| 120 |
+
| Swin-Base | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 20.238 ms | 0 - 0 MB | NPU
|
| 121 |
+
| Swin-Base | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 94.703 ms | 0 - 645 MB | NPU
|
| 122 |
+
| Swin-Base | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 21.623 ms | 0 - 589 MB | NPU
|
| 123 |
+
| Swin-Base | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 9.3 ms | 0 - 388 MB | NPU
|
| 124 |
+
| Swin-Base | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 21.623 ms | 0 - 589 MB | NPU
|
| 125 |
+
| Swin-Base | TFLITE | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 7.727 ms | 0 - 379 MB | NPU
|
| 126 |
+
| Swin-Base | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 9.501 ms | 0 - 358 MB | NPU
|
| 127 |
+
| Swin-Base | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 12.818 ms | 0 - 504 MB | NPU
|
| 128 |
+
| Swin-Base | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 27.835 ms | 0 - 497 MB | NPU
|
| 129 |
+
| Swin-Base | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 20.137 ms | 0 - 179 MB | NPU
|
| 130 |
+
| Swin-Base | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 18.637 ms | 0 - 4 MB | NPU
|
| 131 |
+
| Swin-Base | TFLITE | float | Qualcomm® SA8775P | 21.613 ms | 0 - 359 MB | NPU
|
| 132 |
+
| Swin-Base | TFLITE | float | Qualcomm® SA8650P | 21.613 ms | 0 - 359 MB | NPU
|
| 133 |
+
| Swin-Base | TFLITE | float | Qualcomm® SA8255P | 21.613 ms | 0 - 359 MB | NPU
|
| 134 |
+
| Swin-Base | TFLITE | float | Qualcomm® QCS8450 | 27.835 ms | 0 - 497 MB | NPU
|
| 135 |
+
| Swin-Base | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 21.746 ms | 0 - 178 MB | NPU
|
| 136 |
+
| Swin-Base | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 9.501 ms | 0 - 358 MB | NPU
|
| 137 |
+
| Swin-Base | TFLITE | float | Qualcomm® SA7255P | 52.046 ms | 0 - 367 MB | NPU
|
| 138 |
+
| Swin-Base | TFLITE | float | Qualcomm® SA8295P | 27.746 ms | 0 - 351 MB | NPU
|
| 139 |
|
| 140 |
## License
|
| 141 |
* The license for the original implementation of Swin-Base 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": "2.50.0.260828221209",
|
| 9 |
-
"onnx_runtime": "1.
|
| 10 |
},
|
| 11 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/swin_base/releases/v0.
|
| 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_base/releases/v0.
|
| 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_base/releases/v0.
|
| 24 |
}
|
| 25 |
}
|
| 26 |
},
|
|
@@ -29,15 +29,15 @@
|
|
| 29 |
"onnx": {
|
| 30 |
"tool_versions": {
|
| 31 |
"qairt": "2.50.0.260828221209",
|
| 32 |
-
"onnx_runtime": "1.
|
| 33 |
},
|
| 34 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/swin_base/releases/v0.
|
| 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_base/releases/v0.
|
| 41 |
}
|
| 42 |
}
|
| 43 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"version": "0.64.0",
|
| 3 |
"precisions": {
|
| 4 |
"float": {
|
| 5 |
"universal_assets": {
|
| 6 |
"onnx": {
|
| 7 |
"tool_versions": {
|
| 8 |
"qairt": "2.50.0.260828221209",
|
| 9 |
+
"onnx_runtime": "1.30.0"
|
| 10 |
},
|
| 11 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/swin_base/releases/v0.64.0/swin_base-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_base/releases/v0.64.0/swin_base-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_base/releases/v0.64.0/swin_base-tflite-float.zip"
|
| 24 |
}
|
| 25 |
}
|
| 26 |
},
|
|
|
|
| 29 |
"onnx": {
|
| 30 |
"tool_versions": {
|
| 31 |
"qairt": "2.50.0.260828221209",
|
| 32 |
+
"onnx_runtime": "1.30.0"
|
| 33 |
},
|
| 34 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/swin_base/releases/v0.64.0/swin_base-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_base/releases/v0.64.0/swin_base-qnn_dlc-w8a16.zip"
|
| 41 |
}
|
| 42 |
}
|
| 43 |
}
|