v0.60.0
Browse filesSee https://github.com/qualcomm/ai-hub-models/releases/v0.60.0 for changelog.
- README.md +145 -131
- release_assets.json +9 -9
README.md
CHANGED
|
@@ -16,7 +16,7 @@ pipeline_tag: image-classification
|
|
| 16 |
GPUNet 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 GPUNet found [here](https://github.com/NVIDIA/DeepLearningExamples/tree/master/PyTorch/Classification/GPUNet).
|
| 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 |
|
|
@@ -29,169 +29,183 @@ Below are pre-exported model assets ready for deployment.
|
|
| 29 |
|
| 30 |
| Runtime | Precision | Chipset | SDK Versions | Download |
|
| 31 |
|---|---|---|---|---|
|
| 32 |
-
| 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/gpunet/releases/v0.
|
| 33 |
-
| ONNX | w8a16 | Universal | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/gpunet/releases/v0.
|
| 34 |
-
| ONNX | w8a8 | Universal | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/gpunet/releases/v0.
|
| 35 |
-
| QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/gpunet/releases/v0.
|
| 36 |
-
| QNN_DLC | w8a16 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/gpunet/releases/v0.
|
| 37 |
-
| QNN_DLC | w8a8 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/gpunet/releases/v0.
|
| 38 |
-
| TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/gpunet/releases/v0.
|
| 39 |
-
| TFLITE | w8a8 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/gpunet/releases/v0.
|
| 40 |
|
| 41 |
For more device-specific assets and performance metrics, visit **[GPUNet on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/gpunet)**.
|
| 42 |
|
| 43 |
|
| 44 |
### Option 2: Export with Custom Configurations
|
| 45 |
|
| 46 |
-
Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.
|
| 47 |
- Custom weights (e.g., fine-tuned checkpoints)
|
| 48 |
- Custom input shapes
|
| 49 |
- Target device and runtime configurations
|
| 50 |
|
| 51 |
This option is ideal if you need to customize the model beyond the default configuration provided here.
|
| 52 |
|
| 53 |
-
See our repository for [GPUNet on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.
|
| 54 |
|
| 55 |
## Model Details
|
| 56 |
|
| 57 |
**Model Type:** Model_use_case.image_classification
|
| 58 |
|
| 59 |
**Model Stats:**
|
| 60 |
-
- Model checkpoint: Imagenet
|
| 61 |
- Input resolution: 224x224
|
| 62 |
-
-
|
| 63 |
- Model size (float): 45.28MB
|
| 64 |
- Model size (w8a8): 21.3MB
|
|
|
|
| 65 |
|
| 66 |
## Performance Summary
|
| 67 |
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
|
| 68 |
|---|---|---|---|---|---|---
|
| 69 |
-
| GPUNet | ONNX | float | Snapdragon® X2 Elite | 0.
|
| 70 |
-
| GPUNet | ONNX | float | Snapdragon® X Elite | 0.
|
| 71 |
-
| GPUNet | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 0.
|
| 72 |
-
| GPUNet | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 1.
|
| 73 |
-
| GPUNet | ONNX | float | Qualcomm® Dragonwing™
|
| 74 |
-
| GPUNet | ONNX | float | Qualcomm®
|
| 75 |
-
| GPUNet | ONNX | float | Qualcomm®
|
| 76 |
-
| GPUNet | ONNX | float | Qualcomm® Dragonwing™ IQ-
|
|
|
|
| 77 |
| GPUNet | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 0.599 ms | 0 - 32 MB | NPU
|
| 78 |
| GPUNet | ONNX | float | Snapdragon® 8 Elite Mobile | 0.599 ms | 0 - 32 MB | NPU
|
| 79 |
-
| GPUNet | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.
|
| 80 |
-
| GPUNet | ONNX | w8a16 | Snapdragon® X2 Elite | 0.
|
| 81 |
-
| GPUNet | ONNX | w8a16 | Snapdragon® X Elite | 0.
|
| 82 |
-
| GPUNet | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 0.
|
| 83 |
-
| GPUNet | ONNX | w8a16 | Snapdragon® 8 Gen 1 Mobile | 1.
|
| 84 |
-
| GPUNet | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 3.
|
| 85 |
-
| GPUNet | ONNX | w8a16 | Qualcomm® Dragonwing™
|
| 86 |
-
| GPUNet | ONNX | w8a16 | Qualcomm®
|
| 87 |
-
| GPUNet | ONNX | w8a16 | Qualcomm®
|
| 88 |
-
| GPUNet | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-
|
|
|
|
|
|
|
|
|
|
| 89 |
| GPUNet | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 0.435 ms | 0 - 51 MB | NPU
|
| 90 |
| GPUNet | ONNX | w8a16 | Snapdragon® 8 Elite Mobile | 0.435 ms | 0 - 51 MB | NPU
|
| 91 |
-
| GPUNet | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 0.
|
| 92 |
-
| GPUNet | ONNX |
|
| 93 |
-
| GPUNet | ONNX | w8a8 | Snapdragon®
|
| 94 |
-
| GPUNet | ONNX | w8a8 | Snapdragon®
|
| 95 |
-
| GPUNet | ONNX | w8a8 | Snapdragon® 8 Gen
|
| 96 |
-
| GPUNet | ONNX | w8a8 |
|
| 97 |
-
| GPUNet | ONNX | w8a8 | Qualcomm® Dragonwing™
|
| 98 |
-
| GPUNet | ONNX | w8a8 | Qualcomm®
|
| 99 |
-
| GPUNet | ONNX | w8a8 | Qualcomm® Dragonwing™
|
| 100 |
-
| GPUNet | ONNX | w8a8 | Qualcomm®
|
| 101 |
-
| GPUNet | ONNX | w8a8 | Qualcomm® Dragonwing™
|
| 102 |
-
| GPUNet | ONNX | w8a8 |
|
| 103 |
-
| GPUNet | ONNX | w8a8 |
|
| 104 |
-
| GPUNet |
|
| 105 |
-
| GPUNet |
|
| 106 |
-
| GPUNet |
|
| 107 |
-
| GPUNet |
|
| 108 |
-
| GPUNet |
|
| 109 |
-
| GPUNet | QNN_DLC | float |
|
| 110 |
-
| GPUNet | QNN_DLC | float |
|
| 111 |
-
| GPUNet | QNN_DLC | float |
|
| 112 |
-
| GPUNet | QNN_DLC | float |
|
| 113 |
-
| GPUNet | QNN_DLC | float | Qualcomm®
|
| 114 |
-
| GPUNet | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-
|
| 115 |
-
| GPUNet | QNN_DLC | float | Qualcomm® Dragonwing™
|
| 116 |
-
| GPUNet | QNN_DLC | float | Qualcomm®
|
| 117 |
-
| GPUNet | QNN_DLC | float | Qualcomm®
|
| 118 |
-
| GPUNet | QNN_DLC | float | Qualcomm®
|
| 119 |
-
| GPUNet | QNN_DLC | float |
|
| 120 |
-
| GPUNet | QNN_DLC | float |
|
| 121 |
-
| GPUNet | QNN_DLC |
|
| 122 |
-
| GPUNet | QNN_DLC |
|
| 123 |
-
| GPUNet | QNN_DLC |
|
| 124 |
-
| GPUNet | QNN_DLC |
|
| 125 |
-
| GPUNet | QNN_DLC |
|
| 126 |
-
| GPUNet | QNN_DLC |
|
| 127 |
-
| GPUNet | QNN_DLC | w8a16 |
|
| 128 |
-
| GPUNet | QNN_DLC | w8a16 |
|
| 129 |
-
| GPUNet | QNN_DLC | w8a16 |
|
| 130 |
-
| GPUNet | QNN_DLC | w8a16 |
|
| 131 |
-
| GPUNet | QNN_DLC | w8a16 | Qualcomm®
|
| 132 |
-
| GPUNet | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-
|
| 133 |
-
| GPUNet | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-
|
| 134 |
-
| GPUNet | QNN_DLC | w8a16 | Qualcomm® Dragonwing™
|
| 135 |
-
| GPUNet | QNN_DLC | w8a16 | Qualcomm®
|
| 136 |
-
| GPUNet | QNN_DLC | w8a16 | Qualcomm®
|
| 137 |
-
| GPUNet | QNN_DLC | w8a16 | Qualcomm®
|
| 138 |
-
| GPUNet | QNN_DLC | w8a16 | Qualcomm®
|
| 139 |
-
| GPUNet | QNN_DLC | w8a16 |
|
| 140 |
-
| GPUNet | QNN_DLC | w8a16 |
|
| 141 |
-
| GPUNet | QNN_DLC | w8a16 |
|
| 142 |
-
| GPUNet | QNN_DLC |
|
| 143 |
-
| GPUNet | QNN_DLC |
|
| 144 |
-
| GPUNet | QNN_DLC |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 145 |
| GPUNet | QNN_DLC | w8a8 | Snapdragon® 8 Gen 1 Mobile | 0.852 ms | 0 - 62 MB | NPU
|
| 146 |
-
| GPUNet | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 2.
|
| 147 |
-
| GPUNet | QNN_DLC | w8a8 | Qualcomm® Dragonwing™
|
| 148 |
-
| GPUNet | QNN_DLC | w8a8 | Qualcomm® Dragonwing™
|
| 149 |
-
| GPUNet | QNN_DLC | w8a8 | Qualcomm®
|
| 150 |
-
| GPUNet | QNN_DLC | w8a8 | Qualcomm®
|
| 151 |
-
| GPUNet | QNN_DLC | w8a8 | Qualcomm®
|
|
|
|
| 152 |
| GPUNet | QNN_DLC | w8a8 | Qualcomm® QCS8450 | 0.852 ms | 0 - 62 MB | NPU
|
| 153 |
-
| GPUNet | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 0.
|
| 154 |
-
| GPUNet | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 0.
|
| 155 |
-
| GPUNet | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 3.
|
| 156 |
| GPUNet | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 0.788 ms | 0 - 40 MB | NPU
|
| 157 |
-
| GPUNet | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 0.
|
| 158 |
-
| GPUNet | QNN_DLC | w8a8 | Qualcomm® SA7255P | 1.
|
| 159 |
-
| GPUNet | QNN_DLC | w8a8 | Qualcomm® SA8295P | 1.
|
| 160 |
-
| GPUNet | QNN_DLC | w8a8 | Snapdragon® 8 Elite Mobile | 0.
|
| 161 |
-
| GPUNet | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.
|
| 162 |
| GPUNet | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 0.788 ms | 0 - 40 MB | NPU
|
| 163 |
-
| GPUNet | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 0.
|
| 164 |
-
| GPUNet | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 2.
|
| 165 |
-
| GPUNet | TFLITE | float | Qualcomm® Dragonwing™
|
| 166 |
-
| GPUNet | TFLITE | float | Qualcomm® Dragonwing™
|
| 167 |
-
| GPUNet | TFLITE | float | Qualcomm®
|
| 168 |
-
| GPUNet | TFLITE | float | Qualcomm®
|
| 169 |
-
| GPUNet | TFLITE | float | Qualcomm®
|
| 170 |
-
| GPUNet | TFLITE | float | Qualcomm®
|
| 171 |
-
| GPUNet | TFLITE | float | Qualcomm®
|
| 172 |
-
| GPUNet | TFLITE | float | Qualcomm® Dragonwing™
|
| 173 |
-
| GPUNet | TFLITE | float | Qualcomm®
|
| 174 |
-
| GPUNet | TFLITE | float | Qualcomm®
|
| 175 |
-
| GPUNet | TFLITE | float |
|
| 176 |
-
| GPUNet | TFLITE | float | Snapdragon® 8 Elite
|
| 177 |
-
| GPUNet | TFLITE |
|
| 178 |
-
| GPUNet | TFLITE | w8a8 | Snapdragon® 8 Gen
|
| 179 |
-
| GPUNet | TFLITE | w8a8 |
|
| 180 |
-
| GPUNet | TFLITE | w8a8 | Qualcomm® Dragonwing™
|
| 181 |
-
| GPUNet | TFLITE | w8a8 | Qualcomm® Dragonwing™
|
| 182 |
-
| GPUNet | TFLITE | w8a8 | Qualcomm®
|
| 183 |
-
| GPUNet | TFLITE | w8a8 | Qualcomm®
|
| 184 |
-
| GPUNet | TFLITE | w8a8 | Qualcomm®
|
| 185 |
-
| GPUNet | TFLITE | w8a8 | Qualcomm®
|
| 186 |
-
| GPUNet | TFLITE | w8a8 | Qualcomm®
|
| 187 |
-
| GPUNet | TFLITE | w8a8 | Qualcomm®
|
| 188 |
-
| GPUNet | TFLITE | w8a8 | Qualcomm® Dragonwing™
|
| 189 |
-
| GPUNet | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-
|
| 190 |
-
| GPUNet | TFLITE | w8a8 | Qualcomm®
|
| 191 |
-
| GPUNet | TFLITE | w8a8 | Qualcomm®
|
| 192 |
-
| GPUNet | TFLITE | w8a8 |
|
| 193 |
-
| GPUNet | TFLITE | w8a8 |
|
| 194 |
-
| GPUNet | TFLITE | w8a8 | Snapdragon®
|
|
|
|
|
|
|
| 195 |
|
| 196 |
## License
|
| 197 |
* The license for the original implementation of GPUNet can be found
|
|
|
|
| 16 |
GPUNet 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 GPUNet found [here](https://github.com/NVIDIA/DeepLearningExamples/tree/master/PyTorch/Classification/GPUNet).
|
| 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/v0.60.0/src/qai_hub_models/models/gpunet) 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 2.45, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/gpunet/releases/v0.60.0/gpunet-onnx-float.zip)
|
| 33 |
+
| ONNX | w8a16 | Universal | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/gpunet/releases/v0.60.0/gpunet-onnx-w8a16.zip)
|
| 34 |
+
| ONNX | w8a8 | Universal | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/gpunet/releases/v0.60.0/gpunet-onnx-w8a8.zip)
|
| 35 |
+
| QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/gpunet/releases/v0.60.0/gpunet-qnn_dlc-float.zip)
|
| 36 |
+
| QNN_DLC | w8a16 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/gpunet/releases/v0.60.0/gpunet-qnn_dlc-w8a16.zip)
|
| 37 |
+
| QNN_DLC | w8a8 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/gpunet/releases/v0.60.0/gpunet-qnn_dlc-w8a8.zip)
|
| 38 |
+
| TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/gpunet/releases/v0.60.0/gpunet-tflite-float.zip)
|
| 39 |
+
| TFLITE | w8a8 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/gpunet/releases/v0.60.0/gpunet-tflite-w8a8.zip)
|
| 40 |
|
| 41 |
For more device-specific assets and performance metrics, visit **[GPUNet on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/gpunet)**.
|
| 42 |
|
| 43 |
|
| 44 |
### Option 2: Export with Custom Configurations
|
| 45 |
|
| 46 |
+
Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.60.0/src/qai_hub_models/models/gpunet) Python library to compile and export the model with your own:
|
| 47 |
- Custom weights (e.g., fine-tuned checkpoints)
|
| 48 |
- Custom input shapes
|
| 49 |
- Target device and runtime configurations
|
| 50 |
|
| 51 |
This option is ideal if you need to customize the model beyond the default configuration provided here.
|
| 52 |
|
| 53 |
+
See our repository for [GPUNet on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.60.0/src/qai_hub_models/models/gpunet) for usage instructions.
|
| 54 |
|
| 55 |
## Model Details
|
| 56 |
|
| 57 |
**Model Type:** Model_use_case.image_classification
|
| 58 |
|
| 59 |
**Model Stats:**
|
|
|
|
| 60 |
- Input resolution: 224x224
|
| 61 |
+
- Model checkpoint: Imagenet
|
| 62 |
- Model size (float): 45.28MB
|
| 63 |
- Model size (w8a8): 21.3MB
|
| 64 |
+
- Number of parameters: 10.49M
|
| 65 |
|
| 66 |
## Performance Summary
|
| 67 |
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
|
| 68 |
|---|---|---|---|---|---|---
|
| 69 |
+
| GPUNet | ONNX | float | Snapdragon® X2 Elite | 0.473 ms | 2 - 2 MB | NPU
|
| 70 |
+
| GPUNet | ONNX | float | Snapdragon® X Elite | 0.987 ms | 24 - 24 MB | NPU
|
| 71 |
+
| GPUNet | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 0.762 ms | 0 - 63 MB | NPU
|
| 72 |
+
| GPUNet | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 1.711 ms | 1 - 64 MB | NPU
|
| 73 |
+
| GPUNet | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 1.498 ms | 1 - 4 MB | NPU
|
| 74 |
+
| GPUNet | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.013 ms | 0 - 29 MB | NPU
|
| 75 |
+
| GPUNet | ONNX | float | Qualcomm® QCS8450 | 1.711 ms | 1 - 64 MB | NPU
|
| 76 |
+
| GPUNet | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 1.387 ms | 1 - 3 MB | NPU
|
| 77 |
+
| GPUNet | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 0.987 ms | 24 - 24 MB | NPU
|
| 78 |
| GPUNet | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 0.599 ms | 0 - 32 MB | NPU
|
| 79 |
| GPUNet | ONNX | float | Snapdragon® 8 Elite Mobile | 0.599 ms | 0 - 32 MB | NPU
|
| 80 |
+
| GPUNet | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.518 ms | 0 - 36 MB | NPU
|
| 81 |
+
| GPUNet | ONNX | w8a16 | Snapdragon® X2 Elite | 0.386 ms | 1 - 1 MB | NPU
|
| 82 |
+
| GPUNet | ONNX | w8a16 | Snapdragon® X Elite | 0.842 ms | 12 - 12 MB | NPU
|
| 83 |
+
| GPUNet | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 0.588 ms | 0 - 68 MB | NPU
|
| 84 |
+
| GPUNet | ONNX | w8a16 | Snapdragon® 8 Gen 1 Mobile | 1.142 ms | 0 - 69 MB | NPU
|
| 85 |
+
| GPUNet | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 3.441 ms | 0 - 3 MB | NPU
|
| 86 |
+
| GPUNet | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 0.878 ms | 0 - 4 MB | NPU
|
| 87 |
+
| GPUNet | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 0.817 ms | 0 - 16 MB | NPU
|
| 88 |
+
| GPUNet | ONNX | w8a16 | Qualcomm® QCS8450 | 1.142 ms | 0 - 69 MB | NPU
|
| 89 |
+
| GPUNet | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 0.931 ms | 0 - 3 MB | NPU
|
| 90 |
+
| GPUNet | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 0.842 ms | 12 - 12 MB | NPU
|
| 91 |
+
| GPUNet | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 5.761 ms | 0 - 172 MB | NPU
|
| 92 |
+
| GPUNet | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 1.064 ms | 0 - 47 MB | NPU
|
| 93 |
| GPUNet | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 0.435 ms | 0 - 51 MB | NPU
|
| 94 |
| GPUNet | ONNX | w8a16 | Snapdragon® 8 Elite Mobile | 0.435 ms | 0 - 51 MB | NPU
|
| 95 |
+
| GPUNet | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 0.372 ms | 0 - 50 MB | NPU
|
| 96 |
+
| GPUNet | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 1.064 ms | 0 - 47 MB | NPU
|
| 97 |
+
| GPUNet | ONNX | w8a8 | Snapdragon® X2 Elite | 0.308 ms | 1 - 1 MB | NPU
|
| 98 |
+
| GPUNet | ONNX | w8a8 | Snapdragon® X Elite | 0.602 ms | 12 - 12 MB | NPU
|
| 99 |
+
| GPUNet | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.466 ms | 0 - 66 MB | NPU
|
| 100 |
+
| GPUNet | ONNX | w8a8 | Snapdragon® 8 Gen 1 Mobile | 0.878 ms | 0 - 66 MB | NPU
|
| 101 |
+
| GPUNet | ONNX | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 2.011 ms | 0 - 3 MB | NPU
|
| 102 |
+
| GPUNet | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 0.695 ms | 0 - 4 MB | NPU
|
| 103 |
+
| GPUNet | ONNX | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 0.613 ms | 0 - 91 MB | NPU
|
| 104 |
+
| GPUNet | ONNX | w8a8 | Qualcomm® QCS8450 | 0.878 ms | 0 - 66 MB | NPU
|
| 105 |
+
| GPUNet | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 0.767 ms | 0 - 3 MB | NPU
|
| 106 |
+
| GPUNet | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 0.602 ms | 12 - 12 MB | NPU
|
| 107 |
+
| GPUNet | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 3.221 ms | 0 - 48 MB | NPU
|
| 108 |
+
| GPUNet | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 0.751 ms | 0 - 44 MB | NPU
|
| 109 |
+
| GPUNet | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 0.392 ms | 0 - 42 MB | NPU
|
| 110 |
+
| GPUNet | ONNX | w8a8 | Snapdragon® 8 Elite Mobile | 0.392 ms | 0 - 42 MB | NPU
|
| 111 |
+
| GPUNet | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.35 ms | 0 - 49 MB | NPU
|
| 112 |
+
| GPUNet | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 0.751 ms | 0 - 44 MB | NPU
|
| 113 |
+
| GPUNet | QNN_DLC | float | Snapdragon® X2 Elite | 0.632 ms | 1 - 1 MB | NPU
|
| 114 |
+
| GPUNet | QNN_DLC | float | Snapdragon® X Elite | 1.397 ms | 1 - 1 MB | NPU
|
| 115 |
+
| GPUNet | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 0.913 ms | 0 - 61 MB | NPU
|
| 116 |
+
| GPUNet | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 2.408 ms | 0 - 63 MB | NPU
|
| 117 |
+
| GPUNet | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 1.624 ms | 1 - 4 MB | NPU
|
| 118 |
+
| GPUNet | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 4.671 ms | 1 - 33 MB | NPU
|
| 119 |
+
| GPUNet | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.269 ms | 1 - 2 MB | NPU
|
| 120 |
+
| GPUNet | QNN_DLC | float | Qualcomm® SA8775P | 1.72 ms | 1 - 34 MB | NPU
|
| 121 |
+
| GPUNet | QNN_DLC | float | Qualcomm® SA8650P | 1.72 ms | 1 - 34 MB | NPU
|
| 122 |
+
| GPUNet | QNN_DLC | float | Qualcomm® SA8255P | 1.72 ms | 1 - 34 MB | NPU
|
| 123 |
+
| GPUNet | QNN_DLC | float | Qualcomm® QCS8450 | 2.408 ms | 0 - 63 MB | NPU
|
| 124 |
+
| GPUNet | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 1.571 ms | 1 - 3 MB | NPU
|
| 125 |
+
| GPUNet | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 1.397 ms | 1 - 1 MB | NPU
|
| 126 |
+
| GPUNet | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 0.703 ms | 1 - 31 MB | NPU
|
| 127 |
+
| GPUNet | QNN_DLC | float | Qualcomm® SA7255P | 4.671 ms | 1 - 33 MB | NPU
|
| 128 |
+
| GPUNet | QNN_DLC | float | Qualcomm® SA8295P | 2.284 ms | 0 - 32 MB | NPU
|
| 129 |
+
| GPUNet | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 0.703 ms | 1 - 31 MB | NPU
|
| 130 |
+
| GPUNet | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.573 ms | 1 - 34 MB | NPU
|
| 131 |
+
| GPUNet | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 0.575 ms | 0 - 0 MB | NPU
|
| 132 |
+
| GPUNet | QNN_DLC | w8a16 | Snapdragon® X Elite | 1.225 ms | 0 - 0 MB | NPU
|
| 133 |
+
| GPUNet | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 0.771 ms | 0 - 60 MB | NPU
|
| 134 |
+
| GPUNet | QNN_DLC | w8a16 | Snapdragon® 8 Gen 1 Mobile | 1.44 ms | 0 - 65 MB | NPU
|
| 135 |
+
| GPUNet | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 4.087 ms | 2 - 4 MB | NPU
|
| 136 |
+
| GPUNet | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 1.09 ms | 0 - 3 MB | NPU
|
| 137 |
+
| GPUNet | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 2.504 ms | 0 - 45 MB | NPU
|
| 138 |
+
| GPUNet | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.071 ms | 1 - 2 MB | NPU
|
| 139 |
+
| GPUNet | QNN_DLC | w8a16 | Qualcomm® SA8775P | 1.274 ms | 0 - 45 MB | NPU
|
| 140 |
+
| GPUNet | QNN_DLC | w8a16 | Qualcomm® SA8650P | 1.274 ms | 0 - 45 MB | NPU
|
| 141 |
+
| GPUNet | QNN_DLC | w8a16 | Qualcomm® SA8255P | 1.274 ms | 0 - 45 MB | NPU
|
| 142 |
+
| GPUNet | QNN_DLC | w8a16 | Qualcomm® QCS8450 | 1.44 ms | 0 - 65 MB | NPU
|
| 143 |
+
| GPUNet | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 1.151 ms | 2 - 4 MB | NPU
|
| 144 |
+
| GPUNet | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 1.225 ms | 0 - 0 MB | NPU
|
| 145 |
+
| GPUNet | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 6.592 ms | 0 - 168 MB | NPU
|
| 146 |
+
| GPUNet | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 1.292 ms | 0 - 43 MB | NPU
|
| 147 |
+
| GPUNet | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 0.527 ms | 0 - 42 MB | NPU
|
| 148 |
+
| GPUNet | QNN_DLC | w8a16 | Qualcomm® SA7255P | 2.504 ms | 0 - 45 MB | NPU
|
| 149 |
+
| GPUNet | QNN_DLC | w8a16 | Qualcomm® SA8295P | 1.654 ms | 0 - 41 MB | NPU
|
| 150 |
+
| GPUNet | QNN_DLC | w8a16 | Snapdragon® 8 Elite Mobile | 0.527 ms | 0 - 42 MB | NPU
|
| 151 |
+
| GPUNet | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 0.44 ms | 0 - 43 MB | NPU
|
| 152 |
+
| GPUNet | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 1.292 ms | 0 - 43 MB | NPU
|
| 153 |
+
| GPUNet | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 0.345 ms | 0 - 0 MB | NPU
|
| 154 |
+
| GPUNet | QNN_DLC | w8a8 | Snapdragon® X Elite | 0.715 ms | 1 - 1 MB | NPU
|
| 155 |
+
| GPUNet | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.465 ms | 0 - 57 MB | NPU
|
| 156 |
| GPUNet | QNN_DLC | w8a8 | Snapdragon® 8 Gen 1 Mobile | 0.852 ms | 0 - 62 MB | NPU
|
| 157 |
+
| GPUNet | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 2.211 ms | 0 - 2 MB | NPU
|
| 158 |
+
| GPUNet | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 0.662 ms | 0 - 3 MB | NPU
|
| 159 |
+
| GPUNet | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 1.414 ms | 0 - 40 MB | NPU
|
| 160 |
+
| GPUNet | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 0.614 ms | 0 - 14 MB | NPU
|
| 161 |
+
| GPUNet | QNN_DLC | w8a8 | Qualcomm® SA8775P | 0.81 ms | 0 - 42 MB | NPU
|
| 162 |
+
| GPUNet | QNN_DLC | w8a8 | Qualcomm® SA8650P | 0.81 ms | 0 - 42 MB | NPU
|
| 163 |
+
| GPUNet | QNN_DLC | w8a8 | Qualcomm® SA8255P | 0.81 ms | 0 - 42 MB | NPU
|
| 164 |
| GPUNet | QNN_DLC | w8a8 | Qualcomm® QCS8450 | 0.852 ms | 0 - 62 MB | NPU
|
| 165 |
+
| GPUNet | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 0.692 ms | 2 - 4 MB | NPU
|
| 166 |
+
| GPUNet | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 0.715 ms | 1 - 1 MB | NPU
|
| 167 |
+
| GPUNet | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 3.469 ms | 0 - 44 MB | NPU
|
| 168 |
| GPUNet | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 0.788 ms | 0 - 40 MB | NPU
|
| 169 |
+
| GPUNet | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 0.337 ms | 0 - 39 MB | NPU
|
| 170 |
+
| GPUNet | QNN_DLC | w8a8 | Qualcomm® SA7255P | 1.414 ms | 0 - 40 MB | NPU
|
| 171 |
+
| GPUNet | QNN_DLC | w8a8 | Qualcomm® SA8295P | 1.097 ms | 0 - 38 MB | NPU
|
| 172 |
+
| GPUNet | QNN_DLC | w8a8 | Snapdragon® 8 Elite Mobile | 0.337 ms | 0 - 39 MB | NPU
|
| 173 |
+
| GPUNet | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.291 ms | 0 - 42 MB | NPU
|
| 174 |
| GPUNet | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 0.788 ms | 0 - 40 MB | NPU
|
| 175 |
+
| GPUNet | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 0.909 ms | 0 - 78 MB | NPU
|
| 176 |
+
| GPUNet | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 2.397 ms | 0 - 83 MB | NPU
|
| 177 |
+
| GPUNet | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 1.631 ms | 0 - 28 MB | NPU
|
| 178 |
+
| GPUNet | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 4.711 ms | 0 - 44 MB | NPU
|
| 179 |
+
| GPUNet | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.263 ms | 0 - 20 MB | NPU
|
| 180 |
+
| GPUNet | TFLITE | float | Qualcomm® SA8775P | 1.757 ms | 0 - 47 MB | NPU
|
| 181 |
+
| GPUNet | TFLITE | float | Qualcomm® SA8650P | 1.757 ms | 0 - 47 MB | NPU
|
| 182 |
+
| GPUNet | TFLITE | float | Qualcomm® SA8255P | 1.757 ms | 0 - 47 MB | NPU
|
| 183 |
+
| GPUNet | TFLITE | float | Qualcomm® QCS8450 | 2.397 ms | 0 - 83 MB | NPU
|
| 184 |
+
| GPUNet | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 1.608 ms | 0 - 27 MB | NPU
|
| 185 |
+
| GPUNet | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 0.707 ms | 0 - 47 MB | NPU
|
| 186 |
+
| GPUNet | TFLITE | float | Qualcomm® SA7255P | 4.711 ms | 0 - 44 MB | NPU
|
| 187 |
+
| GPUNet | TFLITE | float | Qualcomm® SA8295P | 2.272 ms | 0 - 44 MB | NPU
|
| 188 |
+
| GPUNet | TFLITE | float | Snapdragon® 8 Elite Mobile | 0.707 ms | 0 - 47 MB | NPU
|
| 189 |
+
| GPUNet | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.558 ms | 0 - 48 MB | NPU
|
| 190 |
+
| GPUNet | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.327 ms | 0 - 55 MB | NPU
|
| 191 |
+
| GPUNet | TFLITE | w8a8 | Snapdragon® 8 Gen 1 Mobile | 0.661 ms | 0 - 62 MB | NPU
|
| 192 |
+
| GPUNet | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 1.776 ms | 0 - 15 MB | NPU
|
| 193 |
+
| GPUNet | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 0.515 ms | 0 - 15 MB | NPU
|
| 194 |
+
| GPUNet | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 1.111 ms | 0 - 39 MB | NPU
|
| 195 |
+
| GPUNet | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 0.429 ms | 0 - 4 MB | NPU
|
| 196 |
+
| GPUNet | TFLITE | w8a8 | Qualcomm® SA8775P | 0.636 ms | 0 - 43 MB | NPU
|
| 197 |
+
| GPUNet | TFLITE | w8a8 | Qualcomm® SA8650P | 0.636 ms | 0 - 43 MB | NPU
|
| 198 |
+
| GPUNet | TFLITE | w8a8 | Qualcomm® SA8255P | 0.636 ms | 0 - 43 MB | NPU
|
| 199 |
+
| GPUNet | TFLITE | w8a8 | Qualcomm® QCS8450 | 0.661 ms | 0 - 62 MB | NPU
|
| 200 |
+
| GPUNet | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 0.536 ms | 0 - 14 MB | NPU
|
| 201 |
+
| GPUNet | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 3.02 ms | 0 - 41 MB | NPU
|
| 202 |
+
| GPUNet | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 0.615 ms | 0 - 38 MB | NPU
|
| 203 |
+
| GPUNet | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 0.272 ms | 0 - 37 MB | NPU
|
| 204 |
+
| GPUNet | TFLITE | w8a8 | Qualcomm® SA7255P | 1.111 ms | 0 - 39 MB | NPU
|
| 205 |
+
| GPUNet | TFLITE | w8a8 | Qualcomm® SA8295P | 0.906 ms | 0 - 37 MB | NPU
|
| 206 |
+
| GPUNet | TFLITE | w8a8 | Snapdragon® 8 Elite Mobile | 0.272 ms | 0 - 37 MB | NPU
|
| 207 |
+
| GPUNet | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.24 ms | 0 - 40 MB | NPU
|
| 208 |
+
| GPUNet | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 0.615 ms | 0 - 38 MB | NPU
|
| 209 |
|
| 210 |
## License
|
| 211 |
* The license for the original implementation of GPUNet can be found
|
release_assets.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"version": "0.
|
| 3 |
"precisions": {
|
| 4 |
"float": {
|
| 5 |
"universal_assets": {
|
|
@@ -8,19 +8,19 @@
|
|
| 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/gpunet/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/gpunet/releases/v0.
|
| 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/gpunet/releases/v0.
|
| 24 |
}
|
| 25 |
}
|
| 26 |
},
|
|
@@ -31,13 +31,13 @@
|
|
| 31 |
"qairt": "2.45.0.260326154327",
|
| 32 |
"onnx_runtime": "1.27.1"
|
| 33 |
},
|
| 34 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/gpunet/releases/v0.
|
| 35 |
},
|
| 36 |
"qnn_dlc": {
|
| 37 |
"tool_versions": {
|
| 38 |
"qairt": "2.45.0.260326154327"
|
| 39 |
},
|
| 40 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/gpunet/releases/v0.
|
| 41 |
}
|
| 42 |
}
|
| 43 |
},
|
|
@@ -48,19 +48,19 @@
|
|
| 48 |
"qairt": "2.45.0.260326154327",
|
| 49 |
"onnx_runtime": "1.27.1"
|
| 50 |
},
|
| 51 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/gpunet/releases/v0.
|
| 52 |
},
|
| 53 |
"qnn_dlc": {
|
| 54 |
"tool_versions": {
|
| 55 |
"qairt": "2.45.0.260326154327"
|
| 56 |
},
|
| 57 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/gpunet/releases/v0.
|
| 58 |
},
|
| 59 |
"tflite": {
|
| 60 |
"tool_versions": {
|
| 61 |
"qairt": "2.45.0.260326154327"
|
| 62 |
},
|
| 63 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/gpunet/releases/v0.
|
| 64 |
}
|
| 65 |
}
|
| 66 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"version": "0.60.0",
|
| 3 |
"precisions": {
|
| 4 |
"float": {
|
| 5 |
"universal_assets": {
|
|
|
|
| 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/gpunet/releases/v0.60.0/gpunet-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/gpunet/releases/v0.60.0/gpunet-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/gpunet/releases/v0.60.0/gpunet-tflite-float.zip"
|
| 24 |
}
|
| 25 |
}
|
| 26 |
},
|
|
|
|
| 31 |
"qairt": "2.45.0.260326154327",
|
| 32 |
"onnx_runtime": "1.27.1"
|
| 33 |
},
|
| 34 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/gpunet/releases/v0.60.0/gpunet-onnx-w8a16.zip"
|
| 35 |
},
|
| 36 |
"qnn_dlc": {
|
| 37 |
"tool_versions": {
|
| 38 |
"qairt": "2.45.0.260326154327"
|
| 39 |
},
|
| 40 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/gpunet/releases/v0.60.0/gpunet-qnn_dlc-w8a16.zip"
|
| 41 |
}
|
| 42 |
}
|
| 43 |
},
|
|
|
|
| 48 |
"qairt": "2.45.0.260326154327",
|
| 49 |
"onnx_runtime": "1.27.1"
|
| 50 |
},
|
| 51 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/gpunet/releases/v0.60.0/gpunet-onnx-w8a8.zip"
|
| 52 |
},
|
| 53 |
"qnn_dlc": {
|
| 54 |
"tool_versions": {
|
| 55 |
"qairt": "2.45.0.260326154327"
|
| 56 |
},
|
| 57 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/gpunet/releases/v0.60.0/gpunet-qnn_dlc-w8a8.zip"
|
| 58 |
},
|
| 59 |
"tflite": {
|
| 60 |
"tool_versions": {
|
| 61 |
"qairt": "2.45.0.260326154327"
|
| 62 |
},
|
| 63 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/gpunet/releases/v0.60.0/gpunet-tflite-w8a8.zip"
|
| 64 |
}
|
| 65 |
}
|
| 66 |
}
|