v0.55.0
Browse filesSee https://github.com/qualcomm/ai-hub-models/releases/v0.55.0 for changelog.
- README.md +41 -56
- release_assets.json +7 -7
README.md
CHANGED
|
@@ -27,10 +27,10 @@ Below are pre-exported model assets ready for deployment.
|
|
| 27 |
|
| 28 |
| Runtime | Precision | Chipset | SDK Versions | Download |
|
| 29 |
|---|---|---|---|---|
|
| 30 |
-
| ONNX | float | Universal | QAIRT 2.42, ONNX Runtime 1.
|
| 31 |
-
| ONNX | w8a16_mixed_fp16 | Universal | QAIRT 2.42, ONNX Runtime 1.
|
| 32 |
-
| QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/cvt/releases/v0.
|
| 33 |
-
| TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/cvt/releases/v0.
|
| 34 |
|
| 35 |
For more device-specific assets and performance metrics, visit **[CVT on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/cvt)**.
|
| 36 |
|
|
@@ -60,58 +60,43 @@ See our repository for [CVT on GitHub](https://github.com/qualcomm/ai-hub-models
|
|
| 60 |
## Performance Summary
|
| 61 |
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
|
| 62 |
|---|---|---|---|---|---|---
|
| 63 |
-
| CVT | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile |
|
| 64 |
-
| CVT | ONNX | float | Snapdragon®
|
| 65 |
-
| CVT | ONNX | float | Snapdragon®
|
| 66 |
-
| CVT | ONNX | float | Snapdragon®
|
| 67 |
-
| CVT | ONNX | float |
|
| 68 |
-
| CVT | ONNX | float | Snapdragon® 8
|
| 69 |
-
| CVT | ONNX | float | Qualcomm®
|
| 70 |
-
| CVT | ONNX | float |
|
| 71 |
-
| CVT | ONNX | float | Qualcomm®
|
| 72 |
-
| CVT | ONNX | w8a16_mixed_fp16 | Snapdragon® 8 Elite Gen 5 Mobile |
|
| 73 |
-
| CVT | ONNX | w8a16_mixed_fp16 | Snapdragon® 8
|
| 74 |
-
| CVT | ONNX | w8a16_mixed_fp16 | Snapdragon®
|
| 75 |
-
| CVT | ONNX | w8a16_mixed_fp16 |
|
| 76 |
-
| CVT |
|
| 77 |
-
| CVT |
|
| 78 |
-
| CVT |
|
| 79 |
-
| CVT | QNN_DLC | float | Snapdragon® 8
|
| 80 |
-
| CVT | QNN_DLC | float |
|
| 81 |
-
| CVT | QNN_DLC | float |
|
| 82 |
-
| CVT | QNN_DLC | float |
|
| 83 |
-
| CVT | QNN_DLC | float |
|
| 84 |
-
| CVT | QNN_DLC | float |
|
| 85 |
-
| CVT | QNN_DLC | float | Qualcomm®
|
| 86 |
-
| CVT | QNN_DLC | float | Qualcomm®
|
| 87 |
-
| CVT | QNN_DLC | float | Qualcomm®
|
| 88 |
-
| CVT | QNN_DLC | float |
|
| 89 |
-
| CVT | QNN_DLC | float | Qualcomm®
|
| 90 |
-
| CVT | QNN_DLC | float | Qualcomm®
|
| 91 |
-
| CVT | QNN_DLC | float |
|
| 92 |
-
| CVT |
|
| 93 |
-
| CVT |
|
| 94 |
-
| CVT |
|
| 95 |
-
| CVT |
|
| 96 |
-
| CVT |
|
| 97 |
-
| CVT |
|
| 98 |
-
| CVT |
|
| 99 |
-
| CVT |
|
| 100 |
-
| CVT | QNN_DLC | w8a16_mixed_fp16 | Qualcomm® QCS8550 (Proxy) | 353.757 ms | 4 - 8 MB | NPU
|
| 101 |
-
| CVT | QNN_DLC | w8a16_mixed_fp16 | Qualcomm® SA8775P | 323.162 ms | 2 - 2318 MB | NPU
|
| 102 |
-
| CVT | QNN_DLC | w8a16_mixed_fp16 | Qualcomm® SA8775P | 323.162 ms | 2 - 2318 MB | NPU
|
| 103 |
-
| CVT | QNN_DLC | w8a16_mixed_fp16 | Qualcomm® SA8775P | 323.162 ms | 2 - 2318 MB | NPU
|
| 104 |
-
| CVT | QNN_DLC | w8a16_mixed_fp16 | Qualcomm® QCS9075 | 396.175 ms | 4 - 9 MB | NPU
|
| 105 |
-
| CVT | QNN_DLC | w8a16_mixed_fp16 | Snapdragon® 8 Elite For Galaxy Mobile | 211.344 ms | 4 - 2334 MB | NPU
|
| 106 |
-
| CVT | QNN_DLC | w8a16_mixed_fp16 | Qualcomm® SA7255P | 473.078 ms | 3 - 2319 MB | NPU
|
| 107 |
-
| CVT | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 166.523 ms | 0 - 2304 MB | NPU
|
| 108 |
-
| CVT | TFLITE | float | Snapdragon® 8 Elite Mobile | 182.509 ms | 0 - 2353 MB | NPU
|
| 109 |
-
| CVT | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 216.769 ms | 0 - 2674 MB | NPU
|
| 110 |
-
| CVT | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 299.412 ms | 0 - 4 MB | NPU
|
| 111 |
-
| CVT | TFLITE | float | Qualcomm® SA8295P | 329.079 ms | 0 - 2307 MB | NPU
|
| 112 |
-
| CVT | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 182.509 ms | 0 - 2353 MB | NPU
|
| 113 |
-
| CVT | TFLITE | float | Qualcomm® QCS9075 | 317.618 ms | 0 - 36 MB | NPU
|
| 114 |
-
| CVT | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 423.956 ms | 0 - 2726 MB | NPU
|
| 115 |
|
| 116 |
## License
|
| 117 |
* The license for the original implementation of CVT can be found
|
|
|
|
| 27 |
|
| 28 |
| Runtime | Precision | Chipset | SDK Versions | Download |
|
| 29 |
|---|---|---|---|---|
|
| 30 |
+
| ONNX | float | Universal | QAIRT 2.42, ONNX Runtime 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/cvt/releases/v0.55.0/cvt-onnx-float.zip)
|
| 31 |
+
| ONNX | w8a16_mixed_fp16 | Universal | QAIRT 2.42, ONNX Runtime 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/cvt/releases/v0.55.0/cvt-onnx-w8a16_mixed_fp16.zip)
|
| 32 |
+
| QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/cvt/releases/v0.55.0/cvt-qnn_dlc-float.zip)
|
| 33 |
+
| TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/cvt/releases/v0.55.0/cvt-tflite-float.zip)
|
| 34 |
|
| 35 |
For more device-specific assets and performance metrics, visit **[CVT on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/cvt)**.
|
| 36 |
|
|
|
|
| 60 |
## Performance Summary
|
| 61 |
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
|
| 62 |
|---|---|---|---|---|---|---
|
| 63 |
+
| CVT | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 180.758 ms | 8 - 2258 MB | NPU
|
| 64 |
+
| CVT | ONNX | float | Snapdragon® X2 Elite | 182.295 ms | 205 - 205 MB | NPU
|
| 65 |
+
| CVT | ONNX | float | Snapdragon® X Elite | 284.357 ms | 147 - 147 MB | NPU
|
| 66 |
+
| CVT | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 243.389 ms | 8 - 2601 MB | NPU
|
| 67 |
+
| CVT | ONNX | float | Qualcomm® QCS8550 (Proxy) | 306.931 ms | 0 - 25 MB | NPU
|
| 68 |
+
| CVT | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 186.596 ms | 5 - 2270 MB | NPU
|
| 69 |
+
| CVT | ONNX | float | Qualcomm® QCS9075 | 321.296 ms | 7 - 52 MB | NPU
|
| 70 |
+
| CVT | ONNX | float | Qualcomm® QCS8750 | 186.596 ms | 5 - 2270 MB | NPU
|
| 71 |
+
| CVT | ONNX | float | Qualcomm® QCS7181 | 284.357 ms | 147 - 147 MB | NPU
|
| 72 |
+
| CVT | ONNX | w8a16_mixed_fp16 | Snapdragon® 8 Elite Gen 5 Mobile | 218.945 ms | 15 - 1246 MB | NPU
|
| 73 |
+
| CVT | ONNX | w8a16_mixed_fp16 | Snapdragon® 8 Gen 3 Mobile | 298.525 ms | 15 - 1617 MB | NPU
|
| 74 |
+
| CVT | ONNX | w8a16_mixed_fp16 | Snapdragon® 8 Elite For Galaxy Mobile | 261.974 ms | 13 - 1107 MB | NPU
|
| 75 |
+
| CVT | ONNX | w8a16_mixed_fp16 | Qualcomm® QCS8750 | 261.974 ms | 13 - 1107 MB | NPU
|
| 76 |
+
| CVT | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 168.835 ms | 7 - 2297 MB | NPU
|
| 77 |
+
| CVT | QNN_DLC | float | Snapdragon® X2 Elite | 182.659 ms | 7 - 7 MB | NPU
|
| 78 |
+
| CVT | QNN_DLC | float | Snapdragon® X Elite | 286.587 ms | 7 - 7 MB | NPU
|
| 79 |
+
| CVT | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 222.542 ms | 0 - 2569 MB | NPU
|
| 80 |
+
| CVT | QNN_DLC | float | Qualcomm® QCS8275 | 425.777 ms | 2 - 2214 MB | NPU
|
| 81 |
+
| CVT | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 333.185 ms | 8 - 12 MB | NPU
|
| 82 |
+
| CVT | QNN_DLC | float | Qualcomm® SA8775P | 293.056 ms | 2 - 2213 MB | NPU
|
| 83 |
+
| CVT | QNN_DLC | float | Qualcomm® SA8650P | 293.056 ms | 2 - 2213 MB | NPU
|
| 84 |
+
| CVT | QNN_DLC | float | Qualcomm® SA8255P | 293.056 ms | 2 - 2213 MB | NPU
|
| 85 |
+
| CVT | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 441.965 ms | 7 - 2719 MB | NPU
|
| 86 |
+
| CVT | QNN_DLC | float | Qualcomm® SA7255P | 425.777 ms | 2 - 2214 MB | NPU
|
| 87 |
+
| CVT | QNN_DLC | float | Qualcomm® SA8295P | 334.17 ms | 0 - 2323 MB | NPU
|
| 88 |
+
| CVT | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 181.922 ms | 0 - 2290 MB | NPU
|
| 89 |
+
| CVT | QNN_DLC | float | Qualcomm® QCS9075 | 322.616 ms | 7 - 17 MB | NPU
|
| 90 |
+
| CVT | QNN_DLC | float | Qualcomm® QCS8750 | 181.922 ms | 0 - 2290 MB | NPU
|
| 91 |
+
| CVT | QNN_DLC | float | Qualcomm® QCS7181 | 286.587 ms | 7 - 7 MB | NPU
|
| 92 |
+
| CVT | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 166.616 ms | 0 - 2305 MB | NPU
|
| 93 |
+
| CVT | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 224.577 ms | 0 - 2670 MB | NPU
|
| 94 |
+
| CVT | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 321.143 ms | 0 - 4 MB | NPU
|
| 95 |
+
| CVT | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 440.053 ms | 1 - 2726 MB | NPU
|
| 96 |
+
| CVT | TFLITE | float | Qualcomm® SA8295P | 330.943 ms | 0 - 2306 MB | NPU
|
| 97 |
+
| CVT | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 180.728 ms | 1 - 2364 MB | NPU
|
| 98 |
+
| CVT | TFLITE | float | Qualcomm® QCS9075 | 318.129 ms | 0 - 36 MB | NPU
|
| 99 |
+
| CVT | TFLITE | float | Qualcomm® QCS8750 | 180.728 ms | 1 - 2364 MB | NPU
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 100 |
|
| 101 |
## License
|
| 102 |
* The license for the original implementation of CVT can be found
|
release_assets.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"version": "0.
|
| 3 |
"precisions": {
|
| 4 |
"float": {
|
| 5 |
"universal_assets": {
|
|
@@ -8,20 +8,20 @@
|
|
| 8 |
"qairt": "2.45.0.260326154327",
|
| 9 |
"litert": "1.4.3"
|
| 10 |
},
|
| 11 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/cvt/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/cvt/releases/v0.
|
| 18 |
},
|
| 19 |
"onnx": {
|
| 20 |
"tool_versions": {
|
| 21 |
"qairt": "2.42.0.251225135753_193295",
|
| 22 |
-
"onnx_runtime": "1.
|
| 23 |
},
|
| 24 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/cvt/releases/v0.
|
| 25 |
}
|
| 26 |
}
|
| 27 |
},
|
|
@@ -30,9 +30,9 @@
|
|
| 30 |
"onnx": {
|
| 31 |
"tool_versions": {
|
| 32 |
"qairt": "2.42.0.251225135753_193295",
|
| 33 |
-
"onnx_runtime": "1.
|
| 34 |
},
|
| 35 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/cvt/releases/v0.
|
| 36 |
}
|
| 37 |
}
|
| 38 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"version": "0.55.0",
|
| 3 |
"precisions": {
|
| 4 |
"float": {
|
| 5 |
"universal_assets": {
|
|
|
|
| 8 |
"qairt": "2.45.0.260326154327",
|
| 9 |
"litert": "1.4.3"
|
| 10 |
},
|
| 11 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/cvt/releases/v0.55.0/cvt-tflite-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/cvt/releases/v0.55.0/cvt-qnn_dlc-float.zip"
|
| 18 |
},
|
| 19 |
"onnx": {
|
| 20 |
"tool_versions": {
|
| 21 |
"qairt": "2.42.0.251225135753_193295",
|
| 22 |
+
"onnx_runtime": "1.25.0"
|
| 23 |
},
|
| 24 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/cvt/releases/v0.55.0/cvt-onnx-float.zip"
|
| 25 |
}
|
| 26 |
}
|
| 27 |
},
|
|
|
|
| 30 |
"onnx": {
|
| 31 |
"tool_versions": {
|
| 32 |
"qairt": "2.42.0.251225135753_193295",
|
| 33 |
+
"onnx_runtime": "1.25.0"
|
| 34 |
},
|
| 35 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/cvt/releases/v0.55.0/cvt-onnx-w8a16_mixed_fp16.zip"
|
| 36 |
}
|
| 37 |
}
|
| 38 |
}
|