v0.63.0
Browse filesSee https://github.com/qualcomm/ai-hub-models/releases/v0.63.0 for changelog.
- README.md +82 -84
- release_assets.json +11 -11
README.md
CHANGED
|
@@ -15,7 +15,7 @@ pipeline_tag: image-classification
|
|
| 15 |
MobileVit 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.
|
| 16 |
|
| 17 |
This is based on the implementation of Mobile-VIT found [here](https://github.com/apple/ml-cvnets).
|
| 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 |
|
|
@@ -28,25 +28,25 @@ Below are pre-exported model assets ready for deployment.
|
|
| 28 |
|
| 29 |
| Runtime | Precision | Chipset | SDK Versions | Download |
|
| 30 |
|---|---|---|---|---|
|
| 31 |
-
| ONNX | float | Universal | QAIRT 2.
|
| 32 |
-
| ONNX | w8a16 | Universal | QAIRT 2.
|
| 33 |
-
| QNN_DLC | float | Universal | QAIRT 2.
|
| 34 |
-
| QNN_DLC | w8a16 | Universal | QAIRT 2.
|
| 35 |
-
| TFLITE | float | Universal | QAIRT 2.
|
| 36 |
|
| 37 |
For more device-specific assets and performance metrics, visit **[Mobile-VIT on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/mobile_vit)**.
|
| 38 |
|
| 39 |
|
| 40 |
### Option 2: Export with Custom Configurations
|
| 41 |
|
| 42 |
-
Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.
|
| 43 |
- Custom weights (e.g., fine-tuned checkpoints)
|
| 44 |
- Custom input shapes
|
| 45 |
- Target device and runtime configurations
|
| 46 |
|
| 47 |
This option is ideal if you need to customize the model beyond the default configuration provided here.
|
| 48 |
|
| 49 |
-
See our repository for [Mobile-VIT on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.
|
| 50 |
|
| 51 |
## Model Details
|
| 52 |
|
|
@@ -62,82 +62,80 @@ See our repository for [Mobile-VIT on GitHub](https://github.com/qualcomm/ai-hub
|
|
| 62 |
## Performance Summary
|
| 63 |
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
|
| 64 |
|---|---|---|---|---|---|---
|
| 65 |
-
| Mobile-VIT | ONNX | float | Snapdragon®
|
| 66 |
-
| Mobile-VIT | ONNX | float | Snapdragon®
|
| 67 |
-
| Mobile-VIT | ONNX | float | Snapdragon®
|
| 68 |
-
| Mobile-VIT | ONNX | float | Snapdragon®
|
| 69 |
-
| Mobile-VIT | ONNX | float |
|
| 70 |
-
| Mobile-VIT | ONNX | float |
|
| 71 |
-
| Mobile-VIT | ONNX | float | Qualcomm®
|
| 72 |
-
| Mobile-VIT | ONNX | float | Qualcomm® Dragonwing™
|
| 73 |
-
| Mobile-VIT | ONNX | float | Qualcomm®
|
| 74 |
-
| Mobile-VIT | ONNX | float | Qualcomm® Dragonwing™
|
| 75 |
-
| Mobile-VIT | ONNX | float |
|
| 76 |
-
| Mobile-VIT | ONNX | float |
|
| 77 |
-
| Mobile-VIT | ONNX | w8a16 | Snapdragon®
|
| 78 |
-
| Mobile-VIT | ONNX | w8a16 | Snapdragon®
|
| 79 |
-
| Mobile-VIT | ONNX | w8a16 | Snapdragon®
|
| 80 |
-
| Mobile-VIT | ONNX | w8a16 | Snapdragon®
|
| 81 |
-
| Mobile-VIT | ONNX | w8a16 |
|
| 82 |
-
| Mobile-VIT | ONNX | w8a16 |
|
| 83 |
-
| Mobile-VIT | ONNX | w8a16 | Qualcomm® Dragonwing™
|
| 84 |
-
| Mobile-VIT | ONNX | w8a16 | Qualcomm®
|
| 85 |
-
| Mobile-VIT | ONNX | w8a16 | Qualcomm® Dragonwing™
|
| 86 |
-
| Mobile-VIT | ONNX | w8a16 | Qualcomm®
|
| 87 |
-
| Mobile-VIT | ONNX | w8a16 | Qualcomm® Dragonwing™
|
| 88 |
-
| Mobile-VIT | ONNX | w8a16 | Qualcomm® Dragonwing™
|
| 89 |
-
| Mobile-VIT | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-
|
| 90 |
-
| Mobile-VIT | ONNX | w8a16 |
|
| 91 |
-
| Mobile-VIT | ONNX | w8a16 |
|
| 92 |
-
| Mobile-VIT | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 4.
|
| 93 |
-
| Mobile-VIT | QNN_DLC | float | Snapdragon®
|
| 94 |
-
| Mobile-VIT | QNN_DLC | float | Snapdragon®
|
| 95 |
-
| Mobile-VIT | QNN_DLC | float | Snapdragon®
|
| 96 |
-
| Mobile-VIT | QNN_DLC | float | Snapdragon®
|
| 97 |
-
| Mobile-VIT | QNN_DLC | float |
|
| 98 |
-
| Mobile-VIT | QNN_DLC | float |
|
| 99 |
-
| Mobile-VIT | QNN_DLC | float | Qualcomm®
|
| 100 |
-
| Mobile-VIT | QNN_DLC | float | Qualcomm®
|
| 101 |
-
| Mobile-VIT | QNN_DLC | float | Qualcomm®
|
| 102 |
-
| Mobile-VIT | QNN_DLC | float | Qualcomm®
|
| 103 |
-
| Mobile-VIT | QNN_DLC | float | Qualcomm®
|
| 104 |
-
| Mobile-VIT | QNN_DLC | float | Qualcomm®
|
| 105 |
-
| Mobile-VIT | QNN_DLC | float | Qualcomm® Dragonwing™
|
| 106 |
-
| Mobile-VIT | QNN_DLC | float | Qualcomm®
|
| 107 |
-
| Mobile-VIT | QNN_DLC | float | Qualcomm®
|
| 108 |
-
| Mobile-VIT | QNN_DLC | float |
|
| 109 |
-
| Mobile-VIT | QNN_DLC |
|
| 110 |
-
| Mobile-VIT | QNN_DLC | w8a16 | Snapdragon®
|
| 111 |
-
| Mobile-VIT | QNN_DLC | w8a16 | Snapdragon®
|
| 112 |
-
| Mobile-VIT | QNN_DLC | w8a16 | Snapdragon®
|
| 113 |
-
| Mobile-VIT | QNN_DLC | w8a16 |
|
| 114 |
-
| Mobile-VIT | QNN_DLC | w8a16 | Qualcomm® Dragonwing™
|
| 115 |
-
| Mobile-VIT | QNN_DLC | w8a16 | Qualcomm®
|
| 116 |
-
| Mobile-VIT | QNN_DLC | w8a16 | Qualcomm®
|
| 117 |
-
| Mobile-VIT | QNN_DLC | w8a16 | Qualcomm®
|
| 118 |
-
| Mobile-VIT | QNN_DLC | w8a16 | Qualcomm®
|
| 119 |
-
| Mobile-VIT | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-
|
| 120 |
-
| Mobile-VIT | QNN_DLC | w8a16 | Qualcomm® Dragonwing™
|
| 121 |
-
| Mobile-VIT | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-
|
| 122 |
-
| Mobile-VIT | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-
|
| 123 |
-
| Mobile-VIT | QNN_DLC | w8a16 | Qualcomm®
|
| 124 |
-
| Mobile-VIT | QNN_DLC | w8a16 | Snapdragon®
|
| 125 |
-
| Mobile-VIT |
|
| 126 |
-
| Mobile-VIT |
|
| 127 |
-
| Mobile-VIT | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 2.
|
| 128 |
-
| Mobile-VIT | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 6.
|
| 129 |
-
| Mobile-VIT | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 4.
|
| 130 |
-
| Mobile-VIT | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) |
|
| 131 |
-
| Mobile-VIT | TFLITE | float | Qualcomm® SA8775P |
|
| 132 |
-
| Mobile-VIT | TFLITE | float | Qualcomm® SA8650P |
|
| 133 |
-
| Mobile-VIT | TFLITE | float | Qualcomm® SA8255P |
|
| 134 |
-
| Mobile-VIT | TFLITE | float | Qualcomm® QCS8450 | 6.
|
| 135 |
-
| Mobile-VIT | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 4.
|
| 136 |
-
| Mobile-VIT | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 2.
|
| 137 |
-
| Mobile-VIT | TFLITE | float | Qualcomm® SA7255P |
|
| 138 |
-
| Mobile-VIT | TFLITE | float | Qualcomm® SA8295P | 7.
|
| 139 |
-
| Mobile-VIT | TFLITE | float | Snapdragon® 8 Elite Mobile | 2.386 ms | 0 - 77 MB | NPU
|
| 140 |
-
| Mobile-VIT | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.011 ms | 0 - 77 MB | NPU
|
| 141 |
|
| 142 |
## License
|
| 143 |
* The license for the original implementation of Mobile-VIT can be found
|
|
|
|
| 15 |
MobileVit 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.
|
| 16 |
|
| 17 |
This is based on the implementation of Mobile-VIT found [here](https://github.com/apple/ml-cvnets).
|
| 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/v0.63.0/src/qai_hub_models/models/mobile_vit) 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 2.50, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mobile_vit/releases/v0.63.0/mobile_vit-onnx-float.zip)
|
| 32 |
+
| 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/mobile_vit/releases/v0.63.0/mobile_vit-onnx-w8a16.zip)
|
| 33 |
+
| QNN_DLC | float | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mobile_vit/releases/v0.63.0/mobile_vit-qnn_dlc-float.zip)
|
| 34 |
+
| QNN_DLC | w8a16 | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mobile_vit/releases/v0.63.0/mobile_vit-qnn_dlc-w8a16.zip)
|
| 35 |
+
| TFLITE | float | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mobile_vit/releases/v0.63.0/mobile_vit-tflite-float.zip)
|
| 36 |
|
| 37 |
For more device-specific assets and performance metrics, visit **[Mobile-VIT on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/mobile_vit)**.
|
| 38 |
|
| 39 |
|
| 40 |
### Option 2: Export with Custom Configurations
|
| 41 |
|
| 42 |
+
Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.63.0/src/qai_hub_models/models/mobile_vit) Python library to compile and export the model with your own:
|
| 43 |
- Custom weights (e.g., fine-tuned checkpoints)
|
| 44 |
- Custom input shapes
|
| 45 |
- Target device and runtime configurations
|
| 46 |
|
| 47 |
This option is ideal if you need to customize the model beyond the default configuration provided here.
|
| 48 |
|
| 49 |
+
See our repository for [Mobile-VIT on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.63.0/src/qai_hub_models/models/mobile_vit) for usage instructions.
|
| 50 |
|
| 51 |
## Model Details
|
| 52 |
|
|
|
|
| 62 |
## Performance Summary
|
| 63 |
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
|
| 64 |
|---|---|---|---|---|---|---
|
| 65 |
+
| Mobile-VIT | ONNX | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 1.925 ms | 0 - 65 MB | NPU
|
| 66 |
+
| Mobile-VIT | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 2.294 ms | 0 - 65 MB | NPU
|
| 67 |
+
| Mobile-VIT | ONNX | float | Snapdragon® X2 Elite | 2.128 ms | 2 - 2 MB | NPU
|
| 68 |
+
| Mobile-VIT | ONNX | float | Snapdragon® X Elite | 4.276 ms | 12 - 12 MB | NPU
|
| 69 |
+
| Mobile-VIT | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 2.897 ms | 0 - 94 MB | NPU
|
| 70 |
+
| Mobile-VIT | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 6.424 ms | 1 - 103 MB | NPU
|
| 71 |
+
| Mobile-VIT | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 4.506 ms | 1 - 5 MB | NPU
|
| 72 |
+
| Mobile-VIT | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 4.095 ms | 0 - 15 MB | NPU
|
| 73 |
+
| Mobile-VIT | ONNX | float | Qualcomm® QCS8450 | 6.424 ms | 1 - 103 MB | NPU
|
| 74 |
+
| Mobile-VIT | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 4.71 ms | 1 - 4 MB | NPU
|
| 75 |
+
| Mobile-VIT | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 4.276 ms | 12 - 12 MB | NPU
|
| 76 |
+
| Mobile-VIT | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 2.294 ms | 0 - 65 MB | NPU
|
| 77 |
+
| Mobile-VIT | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 1.708 ms | 0 - 94 MB | NPU
|
| 78 |
+
| Mobile-VIT | ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 2.031 ms | 0 - 89 MB | NPU
|
| 79 |
+
| Mobile-VIT | ONNX | w8a16 | Snapdragon® X2 Elite | 1.76 ms | 1 - 1 MB | NPU
|
| 80 |
+
| Mobile-VIT | ONNX | w8a16 | Snapdragon® X Elite | 4.423 ms | 6 - 6 MB | NPU
|
| 81 |
+
| Mobile-VIT | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 2.787 ms | 0 - 123 MB | NPU
|
| 82 |
+
| Mobile-VIT | ONNX | w8a16 | Snapdragon® 8 Gen 1 Mobile | 4.803 ms | 0 - 121 MB | NPU
|
| 83 |
+
| Mobile-VIT | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 9.876 ms | 0 - 4 MB | NPU
|
| 84 |
+
| Mobile-VIT | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 3.827 ms | 0 - 4 MB | NPU
|
| 85 |
+
| Mobile-VIT | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 4.229 ms | 0 - 9 MB | NPU
|
| 86 |
+
| Mobile-VIT | ONNX | w8a16 | Qualcomm® QCS8450 | 4.803 ms | 0 - 121 MB | NPU
|
| 87 |
+
| Mobile-VIT | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 4.471 ms | 0 - 4 MB | NPU
|
| 88 |
+
| Mobile-VIT | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 4.423 ms | 6 - 6 MB | NPU
|
| 89 |
+
| Mobile-VIT | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 20.424 ms | 0 - 206 MB | NPU
|
| 90 |
+
| Mobile-VIT | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 4.657 ms | 0 - 201 MB | NPU
|
| 91 |
+
| Mobile-VIT | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 2.031 ms | 0 - 89 MB | NPU
|
| 92 |
+
| Mobile-VIT | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 4.657 ms | 0 - 201 MB | NPU
|
| 93 |
+
| Mobile-VIT | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 1.869 ms | 1 - 60 MB | NPU
|
| 94 |
+
| Mobile-VIT | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 2.236 ms | 0 - 58 MB | NPU
|
| 95 |
+
| Mobile-VIT | QNN_DLC | float | Snapdragon® X2 Elite | 2.316 ms | 1 - 1 MB | NPU
|
| 96 |
+
| Mobile-VIT | QNN_DLC | float | Snapdragon® X Elite | 4.393 ms | 1 - 1 MB | NPU
|
| 97 |
+
| Mobile-VIT | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 2.8 ms | 0 - 86 MB | NPU
|
| 98 |
+
| Mobile-VIT | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 6.249 ms | 0 - 94 MB | NPU
|
| 99 |
+
| Mobile-VIT | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 4.297 ms | 1 - 4 MB | NPU
|
| 100 |
+
| Mobile-VIT | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 3.984 ms | 1 - 3 MB | NPU
|
| 101 |
+
| Mobile-VIT | QNN_DLC | float | Qualcomm® SA8775P | 4.745 ms | 1 - 62 MB | NPU
|
| 102 |
+
| Mobile-VIT | QNN_DLC | float | Qualcomm® SA8650P | 4.745 ms | 1 - 62 MB | NPU
|
| 103 |
+
| Mobile-VIT | QNN_DLC | float | Qualcomm® SA8255P | 4.745 ms | 1 - 62 MB | NPU
|
| 104 |
+
| Mobile-VIT | QNN_DLC | float | Qualcomm® QCS8450 | 6.249 ms | 0 - 94 MB | NPU
|
| 105 |
+
| Mobile-VIT | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 4.564 ms | 1 - 4 MB | NPU
|
| 106 |
+
| Mobile-VIT | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 4.393 ms | 1 - 1 MB | NPU
|
| 107 |
+
| Mobile-VIT | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 2.236 ms | 0 - 58 MB | NPU
|
| 108 |
+
| Mobile-VIT | QNN_DLC | float | Qualcomm® SA8295P | 7.082 ms | 0 - 63 MB | NPU
|
| 109 |
+
| Mobile-VIT | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 1.748 ms | 0 - 81 MB | NPU
|
| 110 |
+
| Mobile-VIT | QNN_DLC | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 2.11 ms | 0 - 74 MB | NPU
|
| 111 |
+
| Mobile-VIT | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 2.112 ms | 0 - 0 MB | NPU
|
| 112 |
+
| Mobile-VIT | QNN_DLC | w8a16 | Snapdragon® X Elite | 4.859 ms | 0 - 0 MB | NPU
|
| 113 |
+
| Mobile-VIT | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 2.919 ms | 0 - 97 MB | NPU
|
| 114 |
+
| Mobile-VIT | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 3.95 ms | 0 - 4 MB | NPU
|
| 115 |
+
| Mobile-VIT | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 4.447 ms | 0 - 2 MB | NPU
|
| 116 |
+
| Mobile-VIT | QNN_DLC | w8a16 | Qualcomm® SA8775P | 4.919 ms | 0 - 77 MB | NPU
|
| 117 |
+
| Mobile-VIT | QNN_DLC | w8a16 | Qualcomm® SA8650P | 4.919 ms | 0 - 77 MB | NPU
|
| 118 |
+
| Mobile-VIT | QNN_DLC | w8a16 | Qualcomm® SA8255P | 4.919 ms | 0 - 77 MB | NPU
|
| 119 |
+
| Mobile-VIT | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 4.698 ms | 0 - 3 MB | NPU
|
| 120 |
+
| Mobile-VIT | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 4.859 ms | 0 - 0 MB | NPU
|
| 121 |
+
| Mobile-VIT | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 17.402 ms | 0 - 190 MB | NPU
|
| 122 |
+
| Mobile-VIT | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 4.872 ms | 0 - 187 MB | NPU
|
| 123 |
+
| Mobile-VIT | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 2.11 ms | 0 - 74 MB | NPU
|
| 124 |
+
| Mobile-VIT | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 4.872 ms | 0 - 187 MB | NPU
|
| 125 |
+
| Mobile-VIT | TFLITE | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 1.87 ms | 0 - 69 MB | NPU
|
| 126 |
+
| Mobile-VIT | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 2.238 ms | 0 - 78 MB | NPU
|
| 127 |
+
| Mobile-VIT | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 2.818 ms | 0 - 103 MB | NPU
|
| 128 |
+
| Mobile-VIT | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 6.282 ms | 0 - 108 MB | NPU
|
| 129 |
+
| Mobile-VIT | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 4.329 ms | 0 - 16 MB | NPU
|
| 130 |
+
| Mobile-VIT | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 3.973 ms | 0 - 2 MB | NPU
|
| 131 |
+
| Mobile-VIT | TFLITE | float | Qualcomm® SA8775P | 4.743 ms | 0 - 76 MB | NPU
|
| 132 |
+
| Mobile-VIT | TFLITE | float | Qualcomm® SA8650P | 4.743 ms | 0 - 76 MB | NPU
|
| 133 |
+
| Mobile-VIT | TFLITE | float | Qualcomm® SA8255P | 4.743 ms | 0 - 76 MB | NPU
|
| 134 |
+
| Mobile-VIT | TFLITE | float | Qualcomm® QCS8450 | 6.282 ms | 0 - 108 MB | NPU
|
| 135 |
+
| Mobile-VIT | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 4.544 ms | 0 - 16 MB | NPU
|
| 136 |
+
| Mobile-VIT | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 2.238 ms | 0 - 78 MB | NPU
|
| 137 |
+
| Mobile-VIT | TFLITE | float | Qualcomm® SA7255P | 10.794 ms | 0 - 73 MB | NPU
|
| 138 |
+
| Mobile-VIT | TFLITE | float | Qualcomm® SA8295P | 7.124 ms | 0 - 67 MB | NPU
|
|
|
|
|
|
|
| 139 |
|
| 140 |
## License
|
| 141 |
* The license for the original implementation of Mobile-VIT 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/mobile_vit/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/mobile_vit/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/mobile_vit/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/mobile_vit/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/mobile_vit/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/mobile_vit/releases/v0.63.0/mobile_vit-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/mobile_vit/releases/v0.63.0/mobile_vit-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/mobile_vit/releases/v0.63.0/mobile_vit-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/mobile_vit/releases/v0.63.0/mobile_vit-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/mobile_vit/releases/v0.63.0/mobile_vit-qnn_dlc-w8a16.zip"
|
| 41 |
}
|
| 42 |
}
|
| 43 |
}
|