v0.47.0
Browse filesSee https://github.com/quic/ai-hub-models/releases/v0.47.0 for changelog.
README.md
CHANGED
|
@@ -28,11 +28,11 @@ 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 |
|
|
@@ -62,45 +62,51 @@ See our repository for [ConvNext-Base on GitHub](https://github.com/quic/ai-hub-
|
|
| 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® X Elite | 7.
|
| 66 |
-
| ConvNext-Base | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 5.
|
| 67 |
-
| ConvNext-Base | ONNX | float | Qualcomm® QCS8550 (Proxy) | 7.
|
| 68 |
-
| ConvNext-Base | ONNX | float | Qualcomm® QCS9075 | 11.
|
| 69 |
-
| ConvNext-Base | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 4.
|
| 70 |
-
| ConvNext-Base | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.
|
| 71 |
-
| ConvNext-Base | ONNX |
|
| 72 |
-
| ConvNext-Base | ONNX | w8a16 |
|
| 73 |
-
| ConvNext-Base | ONNX | w8a16 |
|
| 74 |
-
| ConvNext-Base | ONNX | w8a16 | Qualcomm®
|
| 75 |
-
| ConvNext-Base | ONNX | w8a16 |
|
| 76 |
-
| ConvNext-Base | ONNX | w8a16 |
|
| 77 |
-
| ConvNext-Base | ONNX | w8a16 |
|
| 78 |
-
| ConvNext-Base |
|
| 79 |
-
| ConvNext-Base |
|
| 80 |
-
| ConvNext-Base |
|
| 81 |
-
| ConvNext-Base |
|
| 82 |
-
| ConvNext-Base | QNN_DLC | float |
|
| 83 |
-
| ConvNext-Base | QNN_DLC | float |
|
| 84 |
-
| ConvNext-Base | QNN_DLC | float |
|
| 85 |
-
| ConvNext-Base | QNN_DLC | float |
|
| 86 |
-
| ConvNext-Base | QNN_DLC |
|
| 87 |
-
| ConvNext-Base | QNN_DLC |
|
| 88 |
-
| ConvNext-Base | QNN_DLC |
|
| 89 |
-
| ConvNext-Base | QNN_DLC |
|
| 90 |
-
| ConvNext-Base | QNN_DLC |
|
| 91 |
-
| ConvNext-Base | QNN_DLC | w8a16 |
|
| 92 |
-
| ConvNext-Base | QNN_DLC | w8a16 |
|
| 93 |
-
| ConvNext-Base | QNN_DLC | w8a16 | Qualcomm®
|
| 94 |
-
| ConvNext-Base | QNN_DLC | w8a16 |
|
| 95 |
-
| ConvNext-Base | QNN_DLC | w8a16 |
|
| 96 |
-
| ConvNext-Base | QNN_DLC | w8a16 |
|
| 97 |
-
| ConvNext-Base |
|
| 98 |
-
| ConvNext-Base |
|
| 99 |
-
| ConvNext-Base |
|
| 100 |
-
| ConvNext-Base |
|
| 101 |
-
| ConvNext-Base |
|
| 102 |
-
| ConvNext-Base |
|
| 103 |
-
| ConvNext-Base | TFLITE | float | Snapdragon® 8
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 104 |
|
| 105 |
## License
|
| 106 |
* The license for the original implementation of ConvNext-Base can be found
|
|
|
|
| 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/convnext_base/releases/v0.47.0/convnext_base-onnx-float.zip)
|
| 32 |
+
| ONNX | w8a16 | Universal | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/convnext_base/releases/v0.47.0/convnext_base-onnx-w8a16.zip)
|
| 33 |
+
| QNN_DLC | float | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/convnext_base/releases/v0.47.0/convnext_base-qnn_dlc-float.zip)
|
| 34 |
+
| QNN_DLC | w8a16 | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/convnext_base/releases/v0.47.0/convnext_base-qnn_dlc-w8a16.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/convnext_base/releases/v0.47.0/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 |
|
|
|
|
| 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® X Elite | 7.505 ms | 175 - 175 MB | NPU
|
| 66 |
+
| ConvNext-Base | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 5.3 ms | 1 - 352 MB | NPU
|
| 67 |
+
| ConvNext-Base | ONNX | float | Qualcomm® QCS8550 (Proxy) | 7.15 ms | 0 - 195 MB | NPU
|
| 68 |
+
| ConvNext-Base | ONNX | float | Qualcomm® QCS9075 | 11.469 ms | 0 - 4 MB | NPU
|
| 69 |
+
| ConvNext-Base | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 4.118 ms | 0 - 284 MB | NPU
|
| 70 |
+
| ConvNext-Base | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.159 ms | 1 - 285 MB | NPU
|
| 71 |
+
| ConvNext-Base | ONNX | float | Snapdragon® X2 Elite | 3.54 ms | 176 - 176 MB | NPU
|
| 72 |
+
| ConvNext-Base | ONNX | w8a16 | Snapdragon® X Elite | 6.457 ms | 90 - 90 MB | NPU
|
| 73 |
+
| ConvNext-Base | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 4.39 ms | 0 - 270 MB | NPU
|
| 74 |
+
| ConvNext-Base | ONNX | w8a16 | Qualcomm® QCS6490 | 1091.858 ms | 32 - 63 MB | CPU
|
| 75 |
+
| ConvNext-Base | ONNX | w8a16 | Qualcomm® QCS8550 (Proxy) | 6.185 ms | 0 - 359 MB | NPU
|
| 76 |
+
| ConvNext-Base | ONNX | w8a16 | Qualcomm® QCS9075 | 5.895 ms | 0 - 3 MB | NPU
|
| 77 |
+
| ConvNext-Base | ONNX | w8a16 | Qualcomm® QCM6690 | 630.675 ms | 43 - 55 MB | CPU
|
| 78 |
+
| ConvNext-Base | ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 3.205 ms | 0 - 208 MB | NPU
|
| 79 |
+
| ConvNext-Base | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 605.16 ms | 74 - 89 MB | CPU
|
| 80 |
+
| ConvNext-Base | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 2.596 ms | 0 - 223 MB | NPU
|
| 81 |
+
| ConvNext-Base | ONNX | w8a16 | Snapdragon® X2 Elite | 2.779 ms | 90 - 90 MB | NPU
|
| 82 |
+
| ConvNext-Base | QNN_DLC | float | Snapdragon® X Elite | 8.57 ms | 1 - 1 MB | NPU
|
| 83 |
+
| ConvNext-Base | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 6.002 ms | 0 - 347 MB | NPU
|
| 84 |
+
| ConvNext-Base | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 42.209 ms | 1 - 278 MB | NPU
|
| 85 |
+
| ConvNext-Base | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 8.247 ms | 1 - 448 MB | NPU
|
| 86 |
+
| ConvNext-Base | QNN_DLC | float | Qualcomm® QCS9075 | 12.123 ms | 1 - 3 MB | NPU
|
| 87 |
+
| ConvNext-Base | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 20.649 ms | 0 - 336 MB | NPU
|
| 88 |
+
| ConvNext-Base | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 4.655 ms | 1 - 281 MB | NPU
|
| 89 |
+
| ConvNext-Base | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.556 ms | 0 - 282 MB | NPU
|
| 90 |
+
| ConvNext-Base | QNN_DLC | float | Snapdragon® X2 Elite | 4.311 ms | 1 - 1 MB | NPU
|
| 91 |
+
| ConvNext-Base | QNN_DLC | w8a16 | Snapdragon® X Elite | 6.27 ms | 0 - 0 MB | NPU
|
| 92 |
+
| ConvNext-Base | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 4.071 ms | 0 - 247 MB | NPU
|
| 93 |
+
| ConvNext-Base | QNN_DLC | w8a16 | Qualcomm® QCS6490 | 23.725 ms | 2 - 4 MB | NPU
|
| 94 |
+
| ConvNext-Base | QNN_DLC | w8a16 | Qualcomm® QCS8275 (Proxy) | 14.607 ms | 0 - 198 MB | NPU
|
| 95 |
+
| ConvNext-Base | QNN_DLC | w8a16 | Qualcomm® QCS8550 (Proxy) | 5.941 ms | 0 - 2 MB | NPU
|
| 96 |
+
| ConvNext-Base | QNN_DLC | w8a16 | Qualcomm® QCS9075 | 6.136 ms | 0 - 2 MB | NPU
|
| 97 |
+
| ConvNext-Base | QNN_DLC | w8a16 | Qualcomm® QCM6690 | 76.067 ms | 0 - 394 MB | NPU
|
| 98 |
+
| ConvNext-Base | QNN_DLC | w8a16 | Qualcomm® QCS8450 (Proxy) | 9.092 ms | 0 - 245 MB | NPU
|
| 99 |
+
| ConvNext-Base | QNN_DLC | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 3.28 ms | 0 - 189 MB | NPU
|
| 100 |
+
| ConvNext-Base | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 7.763 ms | 0 - 249 MB | NPU
|
| 101 |
+
| ConvNext-Base | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 2.509 ms | 0 - 201 MB | NPU
|
| 102 |
+
| ConvNext-Base | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 3.056 ms | 0 - 0 MB | NPU
|
| 103 |
+
| ConvNext-Base | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 5.443 ms | 0 - 343 MB | NPU
|
| 104 |
+
| ConvNext-Base | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 40.924 ms | 0 - 274 MB | NPU
|
| 105 |
+
| ConvNext-Base | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 7.25 ms | 0 - 2 MB | NPU
|
| 106 |
+
| ConvNext-Base | TFLITE | float | Qualcomm® QCS9075 | 11.45 ms | 0 - 177 MB | NPU
|
| 107 |
+
| ConvNext-Base | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 19.581 ms | 0 - 331 MB | NPU
|
| 108 |
+
| ConvNext-Base | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 4.101 ms | 0 - 274 MB | NPU
|
| 109 |
+
| ConvNext-Base | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.157 ms | 0 - 278 MB | NPU
|
| 110 |
|
| 111 |
## License
|
| 112 |
* The license for the original implementation of ConvNext-Base can be found
|