v0.63.0
Browse filesSee https://github.com/qualcomm/ai-hub-models/releases/v0.63.0 for changelog.
- README.md +76 -82
- release_assets.json +11 -11
README.md
CHANGED
|
@@ -15,7 +15,7 @@ pipeline_tag: image-classification
|
|
| 15 |
ConvNextBase 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 ConvNext-Base found [here](https://github.com/pytorch/vision/blob/main/torchvision/models/convnext.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/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 **[ConvNext-Base on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/convnext_base)**.
|
| 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 [ConvNext-Base on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.
|
| 50 |
|
| 51 |
## Model Details
|
| 52 |
|
|
@@ -62,86 +62,80 @@ See our repository for [ConvNext-Base on GitHub](https://github.com/qualcomm/ai-
|
|
| 62 |
## Performance Summary
|
| 63 |
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
|
| 64 |
|---|---|---|---|---|---|---
|
| 65 |
-
| ConvNext-Base | ONNX | float | Snapdragon®
|
| 66 |
-
| ConvNext-Base | ONNX | float | Snapdragon®
|
| 67 |
-
| ConvNext-Base | ONNX | float | Snapdragon®
|
| 68 |
-
| ConvNext-Base | ONNX | float | Snapdragon®
|
| 69 |
-
| ConvNext-Base | ONNX | float |
|
| 70 |
-
| ConvNext-Base | ONNX | float |
|
| 71 |
-
| ConvNext-Base | ONNX | float | Qualcomm®
|
| 72 |
-
| ConvNext-Base | ONNX | float | Qualcomm® Dragonwing™
|
| 73 |
-
| ConvNext-Base | ONNX | float | Qualcomm®
|
| 74 |
-
| ConvNext-Base | ONNX | float | Qualcomm® Dragonwing™
|
| 75 |
-
| ConvNext-Base | ONNX | float |
|
| 76 |
-
| ConvNext-Base | ONNX | float |
|
| 77 |
-
| ConvNext-Base | ONNX | w8a16 | Snapdragon®
|
| 78 |
-
| ConvNext-Base | ONNX | w8a16 | Snapdragon®
|
| 79 |
-
| ConvNext-Base | ONNX | w8a16 | Snapdragon®
|
| 80 |
-
| ConvNext-Base | ONNX | w8a16 | Snapdragon®
|
| 81 |
-
| ConvNext-Base | ONNX | w8a16 |
|
| 82 |
-
| ConvNext-Base | ONNX | w8a16 |
|
| 83 |
-
| ConvNext-Base | ONNX | w8a16 | Qualcomm® Dragonwing™
|
| 84 |
-
| ConvNext-Base | ONNX | w8a16 | Qualcomm®
|
| 85 |
-
| ConvNext-Base | ONNX | w8a16 | Qualcomm® Dragonwing™
|
| 86 |
-
| ConvNext-Base | ONNX | w8a16 | Qualcomm®
|
| 87 |
-
| ConvNext-Base | ONNX | w8a16 | Qualcomm® Dragonwing™
|
| 88 |
-
| ConvNext-Base | ONNX | w8a16 | Qualcomm® Dragonwing™
|
| 89 |
-
| ConvNext-Base | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-
|
| 90 |
-
| ConvNext-Base | ONNX | w8a16 |
|
| 91 |
-
| ConvNext-Base | ONNX | w8a16 |
|
| 92 |
-
| ConvNext-Base | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 6.
|
| 93 |
-
| ConvNext-Base | QNN_DLC | float | Snapdragon®
|
| 94 |
-
| ConvNext-Base | QNN_DLC | float | Snapdragon®
|
| 95 |
-
| ConvNext-Base | QNN_DLC | float | Snapdragon®
|
| 96 |
-
| ConvNext-Base | QNN_DLC | float | Snapdragon®
|
| 97 |
-
| ConvNext-Base | QNN_DLC | float |
|
| 98 |
-
| ConvNext-Base | QNN_DLC | float |
|
| 99 |
-
| ConvNext-Base | QNN_DLC | float | Qualcomm®
|
|
|
|
| 100 |
| ConvNext-Base | QNN_DLC | float | Qualcomm® SA8650P | 11.824 ms | 1 - 181 MB | NPU
|
| 101 |
| ConvNext-Base | QNN_DLC | float | Qualcomm® SA8255P | 11.824 ms | 1 - 181 MB | NPU
|
| 102 |
-
| ConvNext-Base | QNN_DLC | float | Qualcomm® QCS8450 |
|
| 103 |
-
| ConvNext-Base | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 11.
|
| 104 |
-
| ConvNext-Base | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 8.
|
| 105 |
-
| ConvNext-Base | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 4.
|
| 106 |
-
| ConvNext-Base | QNN_DLC | float | Qualcomm®
|
| 107 |
-
| ConvNext-Base | QNN_DLC |
|
| 108 |
-
| ConvNext-Base | QNN_DLC |
|
| 109 |
-
| ConvNext-Base | QNN_DLC |
|
| 110 |
-
| ConvNext-Base | QNN_DLC | w8a16 | Snapdragon®
|
| 111 |
-
| ConvNext-Base | QNN_DLC | w8a16 | Snapdragon®
|
| 112 |
-
| ConvNext-Base | QNN_DLC | w8a16 | Snapdragon® 8 Gen
|
| 113 |
-
| ConvNext-Base | QNN_DLC | w8a16 |
|
| 114 |
-
| ConvNext-Base | QNN_DLC | w8a16 | Qualcomm® Dragonwing™
|
| 115 |
-
| ConvNext-Base | QNN_DLC | w8a16 | Qualcomm® Dragonwing™
|
| 116 |
-
| ConvNext-Base | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 5.882 ms | 0 - 2 MB | NPU
|
| 117 |
-
| ConvNext-Base | QNN_DLC | w8a16 | Qualcomm® SA8775P | 6.189 ms | 0 - 204 MB | NPU
|
| 118 |
| ConvNext-Base | QNN_DLC | w8a16 | Qualcomm® SA8650P | 6.189 ms | 0 - 204 MB | NPU
|
| 119 |
| ConvNext-Base | QNN_DLC | w8a16 | Qualcomm® SA8255P | 6.189 ms | 0 - 204 MB | NPU
|
| 120 |
-
| ConvNext-Base | QNN_DLC | w8a16 | Qualcomm® QCS8450 |
|
| 121 |
-
| ConvNext-Base | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 5.
|
| 122 |
-
| ConvNext-Base | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 6.
|
| 123 |
-
| ConvNext-Base | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-6690 |
|
| 124 |
-
| ConvNext-Base | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 7.
|
| 125 |
-
| ConvNext-Base | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 3.
|
| 126 |
-
| ConvNext-Base | QNN_DLC | w8a16 | Qualcomm®
|
| 127 |
-
| ConvNext-Base | QNN_DLC | w8a16 |
|
| 128 |
-
| ConvNext-Base |
|
| 129 |
-
| ConvNext-Base |
|
| 130 |
-
| ConvNext-Base |
|
| 131 |
-
| ConvNext-Base | TFLITE | float | Snapdragon® 8 Gen
|
| 132 |
-
| ConvNext-Base | TFLITE | float |
|
| 133 |
-
| ConvNext-Base | TFLITE | float | Qualcomm® Dragonwing™
|
| 134 |
-
| ConvNext-Base | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 7.256 ms | 0 - 196 MB | NPU
|
| 135 |
-
| ConvNext-Base | TFLITE | float | Qualcomm® SA8775P | 11.089 ms | 0 - 176 MB | NPU
|
| 136 |
| ConvNext-Base | TFLITE | float | Qualcomm® SA8650P | 11.089 ms | 0 - 176 MB | NPU
|
| 137 |
| ConvNext-Base | TFLITE | float | Qualcomm® SA8255P | 11.089 ms | 0 - 176 MB | NPU
|
| 138 |
-
| ConvNext-Base | TFLITE | float | Qualcomm® QCS8450 | 19.
|
| 139 |
-
| ConvNext-Base | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 |
|
| 140 |
-
| ConvNext-Base | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 4.
|
| 141 |
-
| ConvNext-Base | TFLITE | float | Qualcomm®
|
| 142 |
-
| ConvNext-Base | TFLITE | float | Qualcomm® SA8295P | 18.788 ms | 0 - 160 MB | NPU
|
| 143 |
-
| ConvNext-Base | TFLITE | float | Snapdragon® 8 Elite Mobile | 4.101 ms | 0 - 179 MB | NPU
|
| 144 |
-
| ConvNext-Base | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.222 ms | 0 - 182 MB | NPU
|
| 145 |
|
| 146 |
## License
|
| 147 |
* The license for the original implementation of ConvNext-Base can be found
|
|
|
|
| 15 |
ConvNextBase 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 ConvNext-Base found [here](https://github.com/pytorch/vision/blob/main/torchvision/models/convnext.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/v0.63.0/src/qai_hub_models/models/convnext_base) 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/convnext_base/releases/v0.63.0/convnext_base-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/convnext_base/releases/v0.63.0/convnext_base-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/convnext_base/releases/v0.63.0/convnext_base-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/convnext_base/releases/v0.63.0/convnext_base-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/convnext_base/releases/v0.63.0/convnext_base-tflite-float.zip)
|
| 36 |
|
| 37 |
For more device-specific assets and performance metrics, visit **[ConvNext-Base on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/convnext_base)**.
|
| 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/convnext_base) 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 [ConvNext-Base on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.63.0/src/qai_hub_models/models/convnext_base) 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 |
+
| ConvNext-Base | ONNX | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 3.217 ms | 0 - 188 MB | NPU
|
| 66 |
+
| ConvNext-Base | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 4.139 ms | 0 - 186 MB | NPU
|
| 67 |
+
| ConvNext-Base | ONNX | float | Snapdragon® X2 Elite | 3.573 ms | 2 - 2 MB | NPU
|
| 68 |
+
| ConvNext-Base | ONNX | float | Snapdragon® X Elite | 7.227 ms | 176 - 176 MB | NPU
|
| 69 |
+
| ConvNext-Base | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 5.356 ms | 0 - 316 MB | NPU
|
| 70 |
+
| ConvNext-Base | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 18.574 ms | 1 - 308 MB | NPU
|
| 71 |
+
| ConvNext-Base | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 12.176 ms | 0 - 5 MB | NPU
|
| 72 |
+
| ConvNext-Base | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 7.126 ms | 0 - 194 MB | NPU
|
| 73 |
+
| ConvNext-Base | ONNX | float | Qualcomm® QCS8450 | 18.574 ms | 1 - 308 MB | NPU
|
| 74 |
+
| ConvNext-Base | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 10.747 ms | 1 - 4 MB | NPU
|
| 75 |
+
| ConvNext-Base | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 7.227 ms | 176 - 176 MB | NPU
|
| 76 |
+
| ConvNext-Base | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 4.139 ms | 0 - 186 MB | NPU
|
| 77 |
+
| ConvNext-Base | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 1.93 ms | 0 - 207 MB | NPU
|
| 78 |
+
| ConvNext-Base | ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 2.566 ms | 0 - 186 MB | NPU
|
| 79 |
+
| ConvNext-Base | ONNX | w8a16 | Snapdragon® X2 Elite | 2.144 ms | 1 - 1 MB | NPU
|
| 80 |
+
| ConvNext-Base | ONNX | w8a16 | Snapdragon® X Elite | 4.96 ms | 91 - 91 MB | NPU
|
| 81 |
+
| ConvNext-Base | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 3.422 ms | 0 - 269 MB | NPU
|
| 82 |
+
| ConvNext-Base | ONNX | w8a16 | Snapdragon® 8 Gen 1 Mobile | 6.994 ms | 0 - 265 MB | NPU
|
| 83 |
+
| ConvNext-Base | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 20.07 ms | 0 - 4 MB | NPU
|
| 84 |
+
| ConvNext-Base | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 4.866 ms | 0 - 5 MB | NPU
|
| 85 |
+
| ConvNext-Base | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 4.813 ms | 0 - 98 MB | NPU
|
| 86 |
+
| ConvNext-Base | ONNX | w8a16 | Qualcomm® QCS8450 | 6.994 ms | 0 - 265 MB | NPU
|
| 87 |
+
| ConvNext-Base | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 4.858 ms | 0 - 4 MB | NPU
|
| 88 |
+
| ConvNext-Base | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 4.96 ms | 91 - 91 MB | NPU
|
| 89 |
+
| ConvNext-Base | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 57.117 ms | 0 - 375 MB | NPU
|
| 90 |
+
| ConvNext-Base | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 6.892 ms | 0 - 267 MB | NPU
|
| 91 |
+
| ConvNext-Base | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 2.566 ms | 0 - 186 MB | NPU
|
| 92 |
+
| ConvNext-Base | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 6.892 ms | 0 - 267 MB | NPU
|
| 93 |
+
| ConvNext-Base | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 3.537 ms | 1 - 187 MB | NPU
|
| 94 |
+
| ConvNext-Base | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 4.571 ms | 1 - 182 MB | NPU
|
| 95 |
+
| ConvNext-Base | QNN_DLC | float | Snapdragon® X2 Elite | 4.329 ms | 1 - 1 MB | NPU
|
| 96 |
+
| ConvNext-Base | QNN_DLC | float | Snapdragon® X Elite | 8.399 ms | 1 - 1 MB | NPU
|
| 97 |
+
| ConvNext-Base | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 5.894 ms | 0 - 310 MB | NPU
|
| 98 |
+
| ConvNext-Base | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 19.03 ms | 0 - 300 MB | NPU
|
| 99 |
+
| ConvNext-Base | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 13.026 ms | 1 - 4 MB | NPU
|
| 100 |
+
| ConvNext-Base | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 7.955 ms | 1 - 2 MB | NPU
|
| 101 |
| ConvNext-Base | QNN_DLC | float | Qualcomm® SA8650P | 11.824 ms | 1 - 181 MB | NPU
|
| 102 |
| ConvNext-Base | QNN_DLC | float | Qualcomm® SA8255P | 11.824 ms | 1 - 181 MB | NPU
|
| 103 |
+
| ConvNext-Base | QNN_DLC | float | Qualcomm® QCS8450 | 19.03 ms | 0 - 300 MB | NPU
|
| 104 |
+
| ConvNext-Base | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 11.513 ms | 3 - 5 MB | NPU
|
| 105 |
+
| ConvNext-Base | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 8.399 ms | 1 - 1 MB | NPU
|
| 106 |
+
| ConvNext-Base | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 4.571 ms | 1 - 182 MB | NPU
|
| 107 |
+
| ConvNext-Base | QNN_DLC | float | Qualcomm® SA8295P | 19.476 ms | 1 - 172 MB | NPU
|
| 108 |
+
| ConvNext-Base | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 2.352 ms | 0 - 198 MB | NPU
|
| 109 |
+
| ConvNext-Base | QNN_DLC | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 3.051 ms | 0 - 177 MB | NPU
|
| 110 |
+
| ConvNext-Base | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 2.883 ms | 0 - 0 MB | NPU
|
| 111 |
+
| ConvNext-Base | QNN_DLC | w8a16 | Snapdragon® X Elite | 6.223 ms | 0 - 0 MB | NPU
|
| 112 |
+
| ConvNext-Base | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 4.052 ms | 0 - 259 MB | NPU
|
| 113 |
+
| ConvNext-Base | QNN_DLC | w8a16 | Snapdragon® 8 Gen 1 Mobile | 7.981 ms | 0 - 259 MB | NPU
|
| 114 |
+
| ConvNext-Base | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 22.168 ms | 2 - 5 MB | NPU
|
| 115 |
+
| ConvNext-Base | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 5.731 ms | 0 - 4 MB | NPU
|
| 116 |
+
| ConvNext-Base | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 5.823 ms | 0 - 2 MB | NPU
|
|
|
|
|
|
|
| 117 |
| ConvNext-Base | QNN_DLC | w8a16 | Qualcomm® SA8650P | 6.189 ms | 0 - 204 MB | NPU
|
| 118 |
| ConvNext-Base | QNN_DLC | w8a16 | Qualcomm® SA8255P | 6.189 ms | 0 - 204 MB | NPU
|
| 119 |
+
| ConvNext-Base | QNN_DLC | w8a16 | Qualcomm® QCS8450 | 7.981 ms | 0 - 259 MB | NPU
|
| 120 |
+
| ConvNext-Base | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 5.898 ms | 0 - 3 MB | NPU
|
| 121 |
+
| ConvNext-Base | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 6.223 ms | 0 - 0 MB | NPU
|
| 122 |
+
| ConvNext-Base | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 69.886 ms | 0 - 376 MB | NPU
|
| 123 |
+
| ConvNext-Base | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 7.635 ms | 0 - 262 MB | NPU
|
| 124 |
+
| ConvNext-Base | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 3.051 ms | 0 - 177 MB | NPU
|
| 125 |
+
| ConvNext-Base | QNN_DLC | w8a16 | Qualcomm® SA8295P | 9.25 ms | 0 - 216 MB | NPU
|
| 126 |
+
| ConvNext-Base | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 7.635 ms | 0 - 262 MB | NPU
|
| 127 |
+
| ConvNext-Base | TFLITE | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 3.22 ms | 0 - 184 MB | NPU
|
| 128 |
+
| ConvNext-Base | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 4.136 ms | 0 - 177 MB | NPU
|
| 129 |
+
| ConvNext-Base | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 5.416 ms | 0 - 309 MB | NPU
|
| 130 |
+
| ConvNext-Base | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 19.029 ms | 0 - 297 MB | NPU
|
| 131 |
+
| ConvNext-Base | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 12.423 ms | 0 - 178 MB | NPU
|
| 132 |
+
| ConvNext-Base | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 7.271 ms | 0 - 215 MB | NPU
|
|
|
|
|
|
|
| 133 |
| ConvNext-Base | TFLITE | float | Qualcomm® SA8650P | 11.089 ms | 0 - 176 MB | NPU
|
| 134 |
| ConvNext-Base | TFLITE | float | Qualcomm® SA8255P | 11.089 ms | 0 - 176 MB | NPU
|
| 135 |
+
| ConvNext-Base | TFLITE | float | Qualcomm® QCS8450 | 19.029 ms | 0 - 297 MB | NPU
|
| 136 |
+
| ConvNext-Base | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 10.817 ms | 0 - 178 MB | NPU
|
| 137 |
+
| ConvNext-Base | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 4.136 ms | 0 - 177 MB | NPU
|
| 138 |
+
| ConvNext-Base | TFLITE | float | Qualcomm® SA8295P | 18.464 ms | 0 - 164 MB | NPU
|
|
|
|
|
|
|
|
|
|
| 139 |
|
| 140 |
## License
|
| 141 |
* The license for the original implementation of ConvNext-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.
|
| 9 |
"onnx_runtime": "1.27.1"
|
| 10 |
},
|
| 11 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/convnext_base/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/convnext_base/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/convnext_base/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/convnext_base/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/convnext_base/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/convnext_base/releases/v0.63.0/convnext_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/convnext_base/releases/v0.63.0/convnext_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/convnext_base/releases/v0.63.0/convnext_base-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/convnext_base/releases/v0.63.0/convnext_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/convnext_base/releases/v0.63.0/convnext_base-qnn_dlc-w8a16.zip"
|
| 41 |
}
|
| 42 |
}
|
| 43 |
}
|