v0.48.0
Browse filesSee https://github.com/qualcomm/ai-hub-models/releases/v0.48.0 for changelog.
README.md
CHANGED
|
@@ -15,7 +15,7 @@ pipeline_tag: image-classification
|
|
| 15 |
WideResNet50 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 WideResNet50 found [here](https://github.com/pytorch/vision/blob/main/torchvision/models/resnet.py).
|
| 18 |
-
This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the [Qualcomm® AI Hub Models](https://github.com/
|
| 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 |
|
|
@@ -28,26 +28,26 @@ Below are pre-exported model assets ready for deployment.
|
|
| 28 |
|
| 29 |
| Runtime | Precision | Chipset | SDK Versions | Download |
|
| 30 |
|---|---|---|---|---|
|
| 31 |
-
| ONNX | float | Universal | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/wideresnet50/releases/v0.
|
| 32 |
-
| ONNX | w8a8 | Universal | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/wideresnet50/releases/v0.
|
| 33 |
-
| QNN_DLC | float | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/wideresnet50/releases/v0.
|
| 34 |
-
| QNN_DLC | w8a8 | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/wideresnet50/releases/v0.
|
| 35 |
-
| TFLITE | float | Universal | QAIRT 2.43, TFLite 2.17.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/wideresnet50/releases/v0.
|
| 36 |
-
| TFLITE | w8a8 | Universal | QAIRT 2.43, TFLite 2.17.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/wideresnet50/releases/v0.
|
| 37 |
|
| 38 |
For more device-specific assets and performance metrics, visit **[WideResNet50 on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/wideresnet50)**.
|
| 39 |
|
| 40 |
|
| 41 |
### Option 2: Export with Custom Configurations
|
| 42 |
|
| 43 |
-
Use the [Qualcomm® AI Hub Models](https://github.com/
|
| 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 [WideResNet50 on GitHub](https://github.com/
|
| 51 |
|
| 52 |
## Model Details
|
| 53 |
|
|
@@ -63,73 +63,73 @@ See our repository for [WideResNet50 on GitHub](https://github.com/quic/ai-hub-m
|
|
| 63 |
## Performance Summary
|
| 64 |
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
|
| 65 |
|---|---|---|---|---|---|---
|
| 66 |
-
| WideResNet50 | ONNX | float | Snapdragon®
|
| 67 |
-
| WideResNet50 | ONNX | float | Snapdragon®
|
| 68 |
-
| WideResNet50 | ONNX | float |
|
| 69 |
-
| WideResNet50 | ONNX | float | Qualcomm®
|
| 70 |
-
| WideResNet50 | ONNX | float |
|
| 71 |
-
| WideResNet50 | ONNX | float | Snapdragon® 8 Elite
|
| 72 |
-
| WideResNet50 | ONNX | float | Snapdragon®
|
| 73 |
-
| WideResNet50 | ONNX | w8a8 | Snapdragon®
|
| 74 |
-
| WideResNet50 | ONNX | w8a8 | Snapdragon®
|
| 75 |
-
| WideResNet50 | ONNX | w8a8 |
|
| 76 |
-
| WideResNet50 | ONNX | w8a8 | Qualcomm®
|
| 77 |
-
| WideResNet50 | ONNX | w8a8 | Qualcomm®
|
| 78 |
-
| WideResNet50 | ONNX | w8a8 | Qualcomm®
|
| 79 |
-
| WideResNet50 | ONNX | w8a8 |
|
| 80 |
-
| WideResNet50 | ONNX | w8a8 | Snapdragon®
|
| 81 |
-
| WideResNet50 | ONNX | w8a8 | Snapdragon®
|
| 82 |
-
| WideResNet50 | ONNX | w8a8 | Snapdragon®
|
| 83 |
-
| WideResNet50 | QNN_DLC | float | Snapdragon® X Elite | 4.76 ms | 1 - 1 MB | NPU
|
| 84 |
-
| WideResNet50 | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 3.67 ms | 0 - 228 MB | NPU
|
| 85 |
-
| WideResNet50 | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 24.578 ms | 1 - 175 MB | NPU
|
| 86 |
-
| WideResNet50 | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 4.873 ms | 1 - 234 MB | NPU
|
| 87 |
-
| WideResNet50 | QNN_DLC | float | Qualcomm® SA8775P | 7.182 ms | 1 - 170 MB | NPU
|
| 88 |
-
| WideResNet50 | QNN_DLC | float | Qualcomm® QCS9075 | 7.109 ms | 1 - 3 MB | NPU
|
| 89 |
-
| WideResNet50 | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 9.206 ms | 0 - 197 MB | NPU
|
| 90 |
-
| WideResNet50 | QNN_DLC | float | Qualcomm® SA7255P | 24.578 ms | 1 - 175 MB | NPU
|
| 91 |
-
| WideResNet50 | QNN_DLC | float | Qualcomm® SA8295P | 7.883 ms | 1 - 153 MB | NPU
|
| 92 |
-
| WideResNet50 | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 2.932 ms | 0 - 177 MB | NPU
|
| 93 |
-
| WideResNet50 | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.531 ms | 0 - 171 MB | NPU
|
| 94 |
| WideResNet50 | QNN_DLC | float | Snapdragon® X2 Elite | 2.523 ms | 1 - 1 MB | NPU
|
| 95 |
-
| WideResNet50 | QNN_DLC |
|
| 96 |
-
| WideResNet50 | QNN_DLC |
|
| 97 |
-
| WideResNet50 | QNN_DLC |
|
| 98 |
-
| WideResNet50 | QNN_DLC |
|
| 99 |
-
| WideResNet50 | QNN_DLC |
|
| 100 |
-
| WideResNet50 | QNN_DLC |
|
| 101 |
-
| WideResNet50 | QNN_DLC |
|
| 102 |
-
| WideResNet50 | QNN_DLC |
|
| 103 |
-
| WideResNet50 | QNN_DLC |
|
| 104 |
-
| WideResNet50 | QNN_DLC |
|
| 105 |
-
| WideResNet50 | QNN_DLC |
|
| 106 |
-
| WideResNet50 | QNN_DLC | w8a8 | Snapdragon®
|
| 107 |
-
| WideResNet50 | QNN_DLC | w8a8 | Snapdragon®
|
| 108 |
-
| WideResNet50 | QNN_DLC | w8a8 | Snapdragon® 8
|
| 109 |
-
| WideResNet50 | QNN_DLC | w8a8 |
|
| 110 |
-
| WideResNet50 |
|
| 111 |
-
| WideResNet50 |
|
| 112 |
-
| WideResNet50 |
|
| 113 |
-
| WideResNet50 |
|
| 114 |
-
| WideResNet50 |
|
| 115 |
-
| WideResNet50 |
|
| 116 |
-
| WideResNet50 |
|
| 117 |
-
| WideResNet50 |
|
| 118 |
-
| WideResNet50 |
|
| 119 |
-
| WideResNet50 |
|
| 120 |
-
| WideResNet50 |
|
| 121 |
-
| WideResNet50 | TFLITE |
|
| 122 |
-
| WideResNet50 | TFLITE |
|
| 123 |
-
| WideResNet50 | TFLITE |
|
| 124 |
-
| WideResNet50 | TFLITE |
|
| 125 |
-
| WideResNet50 | TFLITE |
|
| 126 |
-
| WideResNet50 | TFLITE |
|
| 127 |
-
| WideResNet50 | TFLITE |
|
| 128 |
-
| WideResNet50 | TFLITE |
|
| 129 |
-
| WideResNet50 | TFLITE |
|
| 130 |
-
| WideResNet50 | TFLITE |
|
| 131 |
-
| WideResNet50 | TFLITE | w8a8 | Snapdragon®
|
| 132 |
-
| WideResNet50 | TFLITE | w8a8 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 133 |
|
| 134 |
## License
|
| 135 |
* The license for the original implementation of WideResNet50 can be found
|
|
|
|
| 15 |
WideResNet50 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 WideResNet50 found [here](https://github.com/pytorch/vision/blob/main/torchvision/models/resnet.py).
|
| 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/main/qai_hub_models/models/wideresnet50) 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 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/wideresnet50/releases/v0.48.0/wideresnet50-onnx-float.zip)
|
| 32 |
+
| ONNX | w8a8 | Universal | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/wideresnet50/releases/v0.48.0/wideresnet50-onnx-w8a8.zip)
|
| 33 |
+
| QNN_DLC | float | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/wideresnet50/releases/v0.48.0/wideresnet50-qnn_dlc-float.zip)
|
| 34 |
+
| QNN_DLC | w8a8 | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/wideresnet50/releases/v0.48.0/wideresnet50-qnn_dlc-w8a8.zip)
|
| 35 |
+
| TFLITE | float | Universal | QAIRT 2.43, TFLite 2.17.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/wideresnet50/releases/v0.48.0/wideresnet50-tflite-float.zip)
|
| 36 |
+
| TFLITE | w8a8 | Universal | QAIRT 2.43, TFLite 2.17.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/wideresnet50/releases/v0.48.0/wideresnet50-tflite-w8a8.zip)
|
| 37 |
|
| 38 |
For more device-specific assets and performance metrics, visit **[WideResNet50 on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/wideresnet50)**.
|
| 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/main/qai_hub_models/models/wideresnet50) 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 [WideResNet50 on GitHub](https://github.com/qualcomm/ai-hub-models/blob/main/qai_hub_models/models/wideresnet50) 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 |
+
| WideResNet50 | ONNX | float | Snapdragon® X2 Elite | 2.928 ms | 132 - 132 MB | NPU
|
| 67 |
+
| WideResNet50 | ONNX | float | Snapdragon® X Elite | 4.443 ms | 132 - 132 MB | NPU
|
| 68 |
+
| WideResNet50 | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 3.487 ms | 0 - 227 MB | NPU
|
| 69 |
+
| WideResNet50 | ONNX | float | Qualcomm® QCS8550 (Proxy) | 4.573 ms | 1 - 3 MB | NPU
|
| 70 |
+
| WideResNet50 | ONNX | float | Qualcomm® QCS9075 | 6.779 ms | 0 - 4 MB | NPU
|
| 71 |
+
| WideResNet50 | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 2.818 ms | 0 - 168 MB | NPU
|
| 72 |
+
| WideResNet50 | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.634 ms | 1 - 189 MB | NPU
|
| 73 |
+
| WideResNet50 | ONNX | w8a8 | Snapdragon® X2 Elite | 0.811 ms | 66 - 66 MB | NPU
|
| 74 |
+
| WideResNet50 | ONNX | w8a8 | Snapdragon® X Elite | 1.798 ms | 66 - 66 MB | NPU
|
| 75 |
+
| WideResNet50 | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 1.415 ms | 0 - 131 MB | NPU
|
| 76 |
+
| WideResNet50 | ONNX | w8a8 | Qualcomm® QCS6490 | 76.112 ms | 10 - 106 MB | CPU
|
| 77 |
+
| WideResNet50 | ONNX | w8a8 | Qualcomm® QCS8550 (Proxy) | 1.853 ms | 0 - 42 MB | NPU
|
| 78 |
+
| WideResNet50 | ONNX | w8a8 | Qualcomm® QCS9075 | 1.919 ms | 0 - 3 MB | NPU
|
| 79 |
+
| WideResNet50 | ONNX | w8a8 | Qualcomm® QCM6690 | 61.279 ms | 10 - 19 MB | CPU
|
| 80 |
+
| WideResNet50 | ONNX | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 1.223 ms | 0 - 52 MB | NPU
|
| 81 |
+
| WideResNet50 | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 58.096 ms | 8 - 17 MB | CPU
|
| 82 |
+
| WideResNet50 | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 1.156 ms | 0 - 56 MB | NPU
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 83 |
| WideResNet50 | QNN_DLC | float | Snapdragon® X2 Elite | 2.523 ms | 1 - 1 MB | NPU
|
| 84 |
+
| WideResNet50 | QNN_DLC | float | Snapdragon® X Elite | 4.756 ms | 1 - 1 MB | NPU
|
| 85 |
+
| WideResNet50 | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 3.647 ms | 0 - 227 MB | NPU
|
| 86 |
+
| WideResNet50 | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 24.586 ms | 1 - 175 MB | NPU
|
| 87 |
+
| WideResNet50 | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 4.864 ms | 1 - 2 MB | NPU
|
| 88 |
+
| WideResNet50 | QNN_DLC | float | Qualcomm® SA8775P | 7.16 ms | 1 - 170 MB | NPU
|
| 89 |
+
| WideResNet50 | QNN_DLC | float | Qualcomm® QCS9075 | 7.076 ms | 1 - 3 MB | NPU
|
| 90 |
+
| WideResNet50 | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 9.2 ms | 0 - 197 MB | NPU
|
| 91 |
+
| WideResNet50 | QNN_DLC | float | Qualcomm® SA7255P | 24.586 ms | 1 - 175 MB | NPU
|
| 92 |
+
| WideResNet50 | QNN_DLC | float | Qualcomm® SA8295P | 7.903 ms | 1 - 153 MB | NPU
|
| 93 |
+
| WideResNet50 | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 2.926 ms | 1 - 177 MB | NPU
|
| 94 |
+
| WideResNet50 | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.544 ms | 1 - 172 MB | NPU
|
| 95 |
+
| WideResNet50 | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 0.871 ms | 0 - 0 MB | NPU
|
| 96 |
+
| WideResNet50 | QNN_DLC | w8a8 | Snapdragon® X Elite | 1.801 ms | 0 - 0 MB | NPU
|
| 97 |
+
| WideResNet50 | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 1.42 ms | 0 - 127 MB | NPU
|
| 98 |
+
| WideResNet50 | QNN_DLC | w8a8 | Qualcomm® QCS6490 | 7.823 ms | 0 - 2 MB | NPU
|
| 99 |
+
| WideResNet50 | QNN_DLC | w8a8 | Qualcomm® QCS8275 (Proxy) | 3.953 ms | 0 - 52 MB | NPU
|
| 100 |
+
| WideResNet50 | QNN_DLC | w8a8 | Qualcomm® QCS8550 (Proxy) | 1.861 ms | 0 - 2 MB | NPU
|
| 101 |
+
| WideResNet50 | QNN_DLC | w8a8 | Qualcomm® SA8775P | 2.008 ms | 0 - 52 MB | NPU
|
| 102 |
+
| WideResNet50 | QNN_DLC | w8a8 | Qualcomm® QCS9075 | 1.907 ms | 0 - 2 MB | NPU
|
| 103 |
+
| WideResNet50 | QNN_DLC | w8a8 | Qualcomm® QCM6690 | 17.133 ms | 0 - 212 MB | NPU
|
| 104 |
+
| WideResNet50 | QNN_DLC | w8a8 | Qualcomm® QCS8450 (Proxy) | 2.542 ms | 0 - 128 MB | NPU
|
| 105 |
+
| WideResNet50 | QNN_DLC | w8a8 | Qualcomm® SA7255P | 3.953 ms | 0 - 52 MB | NPU
|
| 106 |
+
| WideResNet50 | QNN_DLC | w8a8 | Qualcomm® SA8295P | 2.743 ms | 0 - 49 MB | NPU
|
| 107 |
+
| WideResNet50 | QNN_DLC | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 1.145 ms | 0 - 53 MB | NPU
|
| 108 |
+
| WideResNet50 | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 2.864 ms | 0 - 210 MB | NPU
|
| 109 |
+
| WideResNet50 | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 1.099 ms | 0 - 53 MB | NPU
|
| 110 |
+
| WideResNet50 | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 3.566 ms | 0 - 253 MB | NPU
|
| 111 |
+
| WideResNet50 | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 23.673 ms | 0 - 115 MB | NPU
|
| 112 |
+
| WideResNet50 | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 4.771 ms | 0 - 2 MB | NPU
|
| 113 |
+
| WideResNet50 | TFLITE | float | Qualcomm® SA8775P | 7.037 ms | 0 - 115 MB | NPU
|
| 114 |
+
| WideResNet50 | TFLITE | float | Qualcomm® QCS9075 | 7.064 ms | 0 - 134 MB | NPU
|
| 115 |
+
| WideResNet50 | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 8.178 ms | 0 - 230 MB | NPU
|
| 116 |
+
| WideResNet50 | TFLITE | float | Qualcomm® SA7255P | 23.673 ms | 0 - 115 MB | NPU
|
| 117 |
+
| WideResNet50 | TFLITE | float | Qualcomm® SA8295P | 7.682 ms | 0 - 101 MB | NPU
|
| 118 |
+
| WideResNet50 | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 2.881 ms | 0 - 120 MB | NPU
|
| 119 |
+
| WideResNet50 | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.5 ms | 0 - 118 MB | NPU
|
| 120 |
+
| WideResNet50 | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 1.319 ms | 0 - 128 MB | NPU
|
| 121 |
+
| WideResNet50 | TFLITE | w8a8 | Qualcomm® QCS6490 | 6.808 ms | 0 - 68 MB | NPU
|
| 122 |
+
| WideResNet50 | TFLITE | w8a8 | Qualcomm® QCS8275 (Proxy) | 3.776 ms | 0 - 50 MB | NPU
|
| 123 |
+
| WideResNet50 | TFLITE | w8a8 | Qualcomm® QCS8550 (Proxy) | 1.748 ms | 0 - 2 MB | NPU
|
| 124 |
+
| WideResNet50 | TFLITE | w8a8 | Qualcomm® SA8775P | 1.902 ms | 0 - 51 MB | NPU
|
| 125 |
+
| WideResNet50 | TFLITE | w8a8 | Qualcomm® QCS9075 | 1.744 ms | 0 - 68 MB | NPU
|
| 126 |
+
| WideResNet50 | TFLITE | w8a8 | Qualcomm® QCM6690 | 16.895 ms | 0 - 211 MB | NPU
|
| 127 |
+
| WideResNet50 | TFLITE | w8a8 | Qualcomm® QCS8450 (Proxy) | 2.401 ms | 0 - 129 MB | NPU
|
| 128 |
+
| WideResNet50 | TFLITE | w8a8 | Qualcomm® SA7255P | 3.776 ms | 0 - 50 MB | NPU
|
| 129 |
+
| WideResNet50 | TFLITE | w8a8 | Qualcomm® SA8295P | 2.574 ms | 0 - 54 MB | NPU
|
| 130 |
+
| WideResNet50 | TFLITE | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 1.112 ms | 0 - 52 MB | NPU
|
| 131 |
+
| WideResNet50 | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 2.747 ms | 0 - 205 MB | NPU
|
| 132 |
+
| WideResNet50 | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 1.05 ms | 0 - 53 MB | NPU
|
| 133 |
|
| 134 |
## License
|
| 135 |
* The license for the original implementation of WideResNet50 can be found
|