v0.60.0
Browse filesSee https://github.com/qualcomm/ai-hub-models/releases/v0.60.0 for changelog.
- README.md +110 -101
- release_assets.json +7 -7
README.md
CHANGED
|
@@ -15,7 +15,7 @@ pipeline_tag: image-to-image
|
|
| 15 |
DnCNN is a 17-layer denoising convolutional neural network that uses residual learning to remove Gaussian noise (sigma=25) from grayscale images. The network predicts the noise residual and subtracts it from the input to produce a clean image.
|
| 16 |
|
| 17 |
This is based on the implementation of DnCNN found [here](https://github.com/cszn/KAIR).
|
| 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 |
|
|
@@ -28,134 +28,143 @@ Below are pre-exported model assets ready for deployment.
|
|
| 28 |
|
| 29 |
| Runtime | Precision | Chipset | SDK Versions | Download |
|
| 30 |
|---|---|---|---|---|
|
| 31 |
-
| 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/dncnn/releases/v0.
|
| 32 |
-
| 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/dncnn/releases/v0.
|
| 33 |
-
| QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/dncnn/releases/v0.
|
| 34 |
-
| QNN_DLC | w8a8 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/dncnn/releases/v0.
|
| 35 |
-
| TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/dncnn/releases/v0.
|
| 36 |
-
| TFLITE | w8a8 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/dncnn/releases/v0.
|
| 37 |
|
| 38 |
For more device-specific assets and performance metrics, visit **[DnCNN on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/dncnn)**.
|
| 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/v0.
|
| 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 [DnCNN on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.
|
| 51 |
|
| 52 |
## Model Details
|
| 53 |
|
| 54 |
**Model Type:** Model_use_case.image_editing
|
| 55 |
|
| 56 |
**Model Stats:**
|
| 57 |
-
- Model checkpoint: dncnn_25
|
| 58 |
- Input resolution: 256x256
|
| 59 |
-
-
|
| 60 |
- Model size (float): 2.12 MB
|
| 61 |
- Model size (w8a8): 581 KB
|
|
|
|
| 62 |
|
| 63 |
## Performance Summary
|
| 64 |
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
|
| 65 |
|---|---|---|---|---|---|---
|
| 66 |
-
| DnCNN | ONNX | float | Snapdragon® X2 Elite | 4.
|
| 67 |
-
| DnCNN | ONNX | float | Snapdragon® X Elite | 7.
|
| 68 |
-
| DnCNN | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 5.
|
| 69 |
-
| DnCNN | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 13.
|
| 70 |
-
| DnCNN | ONNX | float | Qualcomm® Dragonwing™
|
| 71 |
-
| DnCNN | ONNX | float | Qualcomm®
|
| 72 |
-
| DnCNN | ONNX | float | Qualcomm®
|
| 73 |
-
| DnCNN | ONNX | float | Qualcomm® Dragonwing™ IQ-
|
| 74 |
-
| DnCNN | ONNX | float | Qualcomm® Dragonwing™
|
| 75 |
-
| DnCNN | ONNX | float |
|
| 76 |
-
| DnCNN | ONNX | float | Snapdragon® 8 Elite
|
| 77 |
-
| DnCNN | ONNX |
|
| 78 |
-
| DnCNN | ONNX | w8a8 | Snapdragon®
|
| 79 |
-
| DnCNN | ONNX | w8a8 | Snapdragon®
|
| 80 |
-
| DnCNN | ONNX | w8a8 | Snapdragon® 8 Gen
|
| 81 |
-
| DnCNN | ONNX | w8a8 |
|
| 82 |
-
| DnCNN | ONNX | w8a8 | Qualcomm® Dragonwing™
|
| 83 |
-
| DnCNN | ONNX | w8a8 | Qualcomm®
|
| 84 |
-
| DnCNN | ONNX | w8a8 | Qualcomm® Dragonwing™
|
| 85 |
-
| DnCNN | ONNX | w8a8 | Qualcomm®
|
| 86 |
-
| DnCNN | ONNX | w8a8 | Qualcomm® Dragonwing™
|
| 87 |
-
| DnCNN | ONNX | w8a8 |
|
| 88 |
-
| DnCNN | ONNX | w8a8 |
|
| 89 |
-
| DnCNN |
|
| 90 |
-
| DnCNN |
|
| 91 |
-
| DnCNN |
|
| 92 |
-
| DnCNN |
|
| 93 |
-
| DnCNN |
|
| 94 |
-
| DnCNN | QNN_DLC | float |
|
| 95 |
-
| DnCNN | QNN_DLC | float |
|
| 96 |
-
| DnCNN | QNN_DLC | float |
|
| 97 |
-
| DnCNN | QNN_DLC | float |
|
| 98 |
-
| DnCNN | QNN_DLC | float | Qualcomm®
|
| 99 |
-
| DnCNN | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-
|
| 100 |
-
| DnCNN | QNN_DLC | float | Qualcomm® Dragonwing™
|
| 101 |
-
| DnCNN | QNN_DLC | float | Qualcomm®
|
| 102 |
-
| DnCNN | QNN_DLC | float | Qualcomm®
|
| 103 |
-
| DnCNN | QNN_DLC | float | Qualcomm®
|
| 104 |
-
| DnCNN | QNN_DLC | float |
|
| 105 |
-
| DnCNN | QNN_DLC | float |
|
| 106 |
-
| DnCNN | QNN_DLC |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 107 |
| DnCNN | QNN_DLC | w8a8 | Snapdragon® X Elite | 2.007 ms | 0 - 0 MB | NPU
|
| 108 |
-
| DnCNN | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 1.
|
| 109 |
-
| DnCNN | QNN_DLC | w8a8 | Snapdragon® 8 Gen 1 Mobile | 2.
|
| 110 |
-
| DnCNN | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 9.
|
| 111 |
-
| DnCNN | QNN_DLC | w8a8 | Qualcomm® Dragonwing™
|
| 112 |
-
| DnCNN | QNN_DLC | w8a8 | Qualcomm® Dragonwing™
|
| 113 |
-
| DnCNN | QNN_DLC | w8a8 | Qualcomm®
|
| 114 |
-
| DnCNN | QNN_DLC | w8a8 | Qualcomm®
|
| 115 |
-
| DnCNN | QNN_DLC | w8a8 | Qualcomm®
|
| 116 |
-
| DnCNN | QNN_DLC | w8a8 | Qualcomm®
|
| 117 |
-
| DnCNN | QNN_DLC | w8a8 | Qualcomm®
|
|
|
|
| 118 |
| DnCNN | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 2.007 ms | 0 - 0 MB | NPU
|
| 119 |
-
| DnCNN | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 38.
|
| 120 |
-
| DnCNN | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 3.
|
| 121 |
-
| DnCNN | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 1.
|
| 122 |
-
| DnCNN | QNN_DLC | w8a8 | Qualcomm® SA7255P | 7.
|
| 123 |
-
| DnCNN | QNN_DLC | w8a8 | Qualcomm® SA8295P | 4.
|
| 124 |
-
| DnCNN | QNN_DLC | w8a8 | Snapdragon® 8 Elite Mobile | 1.
|
| 125 |
| DnCNN | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.805 ms | 0 - 28 MB | NPU
|
| 126 |
-
| DnCNN | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 3.
|
| 127 |
-
| DnCNN | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 5.
|
| 128 |
-
| DnCNN | TFLITE | float | Snapdragon® 8 Gen 1 Mobile |
|
| 129 |
-
| DnCNN | TFLITE | float | Qualcomm® Dragonwing™
|
| 130 |
-
| DnCNN | TFLITE | float | Qualcomm® Dragonwing™
|
| 131 |
-
| DnCNN | TFLITE | float | Qualcomm®
|
| 132 |
-
| DnCNN | TFLITE | float | Qualcomm®
|
| 133 |
-
| DnCNN | TFLITE | float | Qualcomm®
|
| 134 |
-
| DnCNN | TFLITE | float | Qualcomm®
|
| 135 |
-
| DnCNN | TFLITE | float | Qualcomm®
|
| 136 |
-
| DnCNN | TFLITE | float | Qualcomm® Dragonwing™
|
| 137 |
-
| DnCNN | TFLITE | float | Qualcomm®
|
| 138 |
-
| DnCNN | TFLITE | float | Qualcomm®
|
| 139 |
-
| DnCNN | TFLITE | float |
|
| 140 |
-
| DnCNN | TFLITE | float | Snapdragon® 8 Elite
|
| 141 |
-
| DnCNN | TFLITE |
|
| 142 |
-
| DnCNN | TFLITE | w8a8 | Snapdragon® 8 Gen
|
| 143 |
-
| DnCNN | TFLITE | w8a8 |
|
| 144 |
-
| DnCNN | TFLITE | w8a8 | Qualcomm® Dragonwing™
|
| 145 |
-
| DnCNN | TFLITE | w8a8 | Qualcomm® Dragonwing™
|
| 146 |
-
| DnCNN | TFLITE | w8a8 | Qualcomm®
|
| 147 |
-
| DnCNN | TFLITE | w8a8 | Qualcomm®
|
| 148 |
-
| DnCNN | TFLITE | w8a8 | Qualcomm®
|
| 149 |
-
| DnCNN | TFLITE | w8a8 | Qualcomm®
|
| 150 |
-
| DnCNN | TFLITE | w8a8 | Qualcomm®
|
| 151 |
-
| DnCNN | TFLITE | w8a8 | Qualcomm®
|
| 152 |
-
| DnCNN | TFLITE | w8a8 | Qualcomm® Dragonwing™
|
| 153 |
-
| DnCNN | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-
|
| 154 |
-
| DnCNN | TFLITE | w8a8 | Qualcomm®
|
| 155 |
-
| DnCNN | TFLITE | w8a8 | Qualcomm®
|
| 156 |
-
| DnCNN | TFLITE | w8a8 |
|
| 157 |
-
| DnCNN | TFLITE | w8a8 |
|
| 158 |
-
| DnCNN | TFLITE | w8a8 | Snapdragon®
|
|
|
|
|
|
|
| 159 |
|
| 160 |
## License
|
| 161 |
* The license for the original implementation of DnCNN can be found
|
|
|
|
| 15 |
DnCNN is a 17-layer denoising convolutional neural network that uses residual learning to remove Gaussian noise (sigma=25) from grayscale images. The network predicts the noise residual and subtracts it from the input to produce a clean image.
|
| 16 |
|
| 17 |
This is based on the implementation of DnCNN found [here](https://github.com/cszn/KAIR).
|
| 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/v0.60.0/src/qai_hub_models/models/dncnn) 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 2.45, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/dncnn/releases/v0.60.0/dncnn-onnx-float.zip)
|
| 32 |
+
| 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/dncnn/releases/v0.60.0/dncnn-onnx-w8a8.zip)
|
| 33 |
+
| QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/dncnn/releases/v0.60.0/dncnn-qnn_dlc-float.zip)
|
| 34 |
+
| QNN_DLC | w8a8 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/dncnn/releases/v0.60.0/dncnn-qnn_dlc-w8a8.zip)
|
| 35 |
+
| TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/dncnn/releases/v0.60.0/dncnn-tflite-float.zip)
|
| 36 |
+
| TFLITE | w8a8 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/dncnn/releases/v0.60.0/dncnn-tflite-w8a8.zip)
|
| 37 |
|
| 38 |
For more device-specific assets and performance metrics, visit **[DnCNN on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/dncnn)**.
|
| 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/v0.60.0/src/qai_hub_models/models/dncnn) 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 [DnCNN on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.60.0/src/qai_hub_models/models/dncnn) for usage instructions.
|
| 51 |
|
| 52 |
## Model Details
|
| 53 |
|
| 54 |
**Model Type:** Model_use_case.image_editing
|
| 55 |
|
| 56 |
**Model Stats:**
|
|
|
|
| 57 |
- Input resolution: 256x256
|
| 58 |
+
- Model checkpoint: dncnn_25
|
| 59 |
- Model size (float): 2.12 MB
|
| 60 |
- Model size (w8a8): 581 KB
|
| 61 |
+
- Number of parameters: 555K
|
| 62 |
|
| 63 |
## Performance Summary
|
| 64 |
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
|
| 65 |
|---|---|---|---|---|---|---
|
| 66 |
+
| DnCNN | ONNX | float | Snapdragon® X2 Elite | 4.043 ms | 1 - 1 MB | NPU
|
| 67 |
+
| DnCNN | ONNX | float | Snapdragon® X Elite | 7.136 ms | 0 - 0 MB | NPU
|
| 68 |
+
| DnCNN | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 5.185 ms | 19 - 195 MB | NPU
|
| 69 |
+
| DnCNN | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 13.757 ms | 1 - 179 MB | NPU
|
| 70 |
+
| DnCNN | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 16.317 ms | 1 - 4 MB | NPU
|
| 71 |
+
| DnCNN | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 6.874 ms | 1 - 3 MB | NPU
|
| 72 |
+
| DnCNN | ONNX | float | Qualcomm® QCS8450 | 13.757 ms | 1 - 179 MB | NPU
|
| 73 |
+
| DnCNN | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 14.202 ms | 1 - 4 MB | NPU
|
| 74 |
+
| DnCNN | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 7.136 ms | 0 - 0 MB | NPU
|
| 75 |
+
| DnCNN | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 4.126 ms | 0 - 142 MB | NPU
|
| 76 |
+
| DnCNN | ONNX | float | Snapdragon® 8 Elite Mobile | 4.126 ms | 0 - 142 MB | NPU
|
| 77 |
+
| DnCNN | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.197 ms | 0 - 146 MB | NPU
|
| 78 |
+
| DnCNN | ONNX | w8a8 | Snapdragon® X2 Elite | 1.043 ms | 1 - 1 MB | NPU
|
| 79 |
+
| DnCNN | ONNX | w8a8 | Snapdragon® X Elite | 1.873 ms | 0 - 0 MB | NPU
|
| 80 |
+
| DnCNN | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 1.336 ms | 0 - 47 MB | NPU
|
| 81 |
+
| DnCNN | ONNX | w8a8 | Snapdragon® 8 Gen 1 Mobile | 2.371 ms | 0 - 52 MB | NPU
|
| 82 |
+
| DnCNN | ONNX | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 9.5 ms | 0 - 3 MB | NPU
|
| 83 |
+
| DnCNN | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 2.205 ms | 0 - 4 MB | NPU
|
| 84 |
+
| DnCNN | ONNX | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.788 ms | 0 - 2 MB | NPU
|
| 85 |
+
| DnCNN | ONNX | w8a8 | Qualcomm® QCS8450 | 2.371 ms | 0 - 52 MB | NPU
|
| 86 |
+
| DnCNN | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 1.898 ms | 0 - 3 MB | NPU
|
| 87 |
+
| DnCNN | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 1.873 ms | 0 - 0 MB | NPU
|
| 88 |
+
| DnCNN | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 39.004 ms | 2 - 145 MB | NPU
|
| 89 |
+
| DnCNN | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 3.262 ms | 0 - 144 MB | NPU
|
| 90 |
+
| DnCNN | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 1.209 ms | 0 - 31 MB | NPU
|
| 91 |
+
| DnCNN | ONNX | w8a8 | Snapdragon® 8 Elite Mobile | 1.209 ms | 0 - 31 MB | NPU
|
| 92 |
+
| DnCNN | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.812 ms | 0 - 32 MB | NPU
|
| 93 |
+
| DnCNN | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 3.262 ms | 0 - 144 MB | NPU
|
| 94 |
+
| DnCNN | QNN_DLC | float | Snapdragon® X2 Elite | 4.166 ms | 0 - 0 MB | NPU
|
| 95 |
+
| DnCNN | QNN_DLC | float | Snapdragon® X Elite | 7.217 ms | 0 - 0 MB | NPU
|
| 96 |
+
| DnCNN | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 5.085 ms | 0 - 173 MB | NPU
|
| 97 |
+
| DnCNN | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 13.451 ms | 0 - 177 MB | NPU
|
| 98 |
+
| DnCNN | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 15.809 ms | 0 - 3 MB | NPU
|
| 99 |
+
| DnCNN | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 55.992 ms | 0 - 141 MB | NPU
|
| 100 |
+
| DnCNN | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 6.729 ms | 0 - 2 MB | NPU
|
| 101 |
+
| DnCNN | QNN_DLC | float | Qualcomm® SA8775P | 13.869 ms | 0 - 144 MB | NPU
|
| 102 |
+
| DnCNN | QNN_DLC | float | Qualcomm® SA8650P | 13.869 ms | 0 - 144 MB | NPU
|
| 103 |
+
| DnCNN | QNN_DLC | float | Qualcomm® SA8255P | 13.869 ms | 0 - 144 MB | NPU
|
| 104 |
+
| DnCNN | QNN_DLC | float | Qualcomm® QCS8450 | 13.451 ms | 0 - 177 MB | NPU
|
| 105 |
+
| DnCNN | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 13.982 ms | 0 - 2 MB | NPU
|
| 106 |
+
| DnCNN | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 7.217 ms | 0 - 0 MB | NPU
|
| 107 |
+
| DnCNN | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 4.037 ms | 0 - 141 MB | NPU
|
| 108 |
+
| DnCNN | QNN_DLC | float | Qualcomm® SA7255P | 55.992 ms | 0 - 141 MB | NPU
|
| 109 |
+
| DnCNN | QNN_DLC | float | Qualcomm® SA8295P | 15.313 ms | 0 - 139 MB | NPU
|
| 110 |
+
| DnCNN | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 4.037 ms | 0 - 141 MB | NPU
|
| 111 |
+
| DnCNN | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.05 ms | 0 - 149 MB | NPU
|
| 112 |
+
| DnCNN | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 1.176 ms | 0 - 0 MB | NPU
|
| 113 |
| DnCNN | QNN_DLC | w8a8 | Snapdragon® X Elite | 2.007 ms | 0 - 0 MB | NPU
|
| 114 |
+
| DnCNN | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 1.323 ms | 0 - 46 MB | NPU
|
| 115 |
+
| DnCNN | QNN_DLC | w8a8 | Snapdragon® 8 Gen 1 Mobile | 2.514 ms | 0 - 51 MB | NPU
|
| 116 |
+
| DnCNN | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 9.419 ms | 0 - 2 MB | NPU
|
| 117 |
+
| DnCNN | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 2.183 ms | 0 - 2 MB | NPU
|
| 118 |
+
| DnCNN | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 7.581 ms | 0 - 28 MB | NPU
|
| 119 |
+
| DnCNN | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.777 ms | 0 - 3 MB | NPU
|
| 120 |
+
| DnCNN | QNN_DLC | w8a8 | Qualcomm® SA8775P | 1.999 ms | 0 - 30 MB | NPU
|
| 121 |
+
| DnCNN | QNN_DLC | w8a8 | Qualcomm® SA8650P | 1.999 ms | 0 - 30 MB | NPU
|
| 122 |
+
| DnCNN | QNN_DLC | w8a8 | Qualcomm® SA8255P | 1.999 ms | 0 - 30 MB | NPU
|
| 123 |
+
| DnCNN | QNN_DLC | w8a8 | Qualcomm® QCS8450 | 2.514 ms | 0 - 51 MB | NPU
|
| 124 |
+
| DnCNN | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 2.02 ms | 2 - 4 MB | NPU
|
| 125 |
| DnCNN | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 2.007 ms | 0 - 0 MB | NPU
|
| 126 |
+
| DnCNN | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 38.849 ms | 0 - 140 MB | NPU
|
| 127 |
+
| DnCNN | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 3.256 ms | 0 - 140 MB | NPU
|
| 128 |
+
| DnCNN | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 1.221 ms | 0 - 28 MB | NPU
|
| 129 |
+
| DnCNN | QNN_DLC | w8a8 | Qualcomm® SA7255P | 7.581 ms | 0 - 28 MB | NPU
|
| 130 |
+
| DnCNN | QNN_DLC | w8a8 | Qualcomm® SA8295P | 4.226 ms | 0 - 26 MB | NPU
|
| 131 |
+
| DnCNN | QNN_DLC | w8a8 | Snapdragon® 8 Elite Mobile | 1.221 ms | 0 - 28 MB | NPU
|
| 132 |
| DnCNN | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.805 ms | 0 - 28 MB | NPU
|
| 133 |
+
| DnCNN | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 3.256 ms | 0 - 140 MB | NPU
|
| 134 |
+
| DnCNN | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 5.2 ms | 0 - 179 MB | NPU
|
| 135 |
+
| DnCNN | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 14.005 ms | 0 - 180 MB | NPU
|
| 136 |
+
| DnCNN | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 16.242 ms | 0 - 5 MB | NPU
|
| 137 |
+
| DnCNN | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 56.39 ms | 0 - 142 MB | NPU
|
| 138 |
+
| DnCNN | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 6.928 ms | 0 - 2 MB | NPU
|
| 139 |
+
| DnCNN | TFLITE | float | Qualcomm® SA8775P | 14.161 ms | 0 - 144 MB | NPU
|
| 140 |
+
| DnCNN | TFLITE | float | Qualcomm® SA8650P | 14.161 ms | 0 - 144 MB | NPU
|
| 141 |
+
| DnCNN | TFLITE | float | Qualcomm® SA8255P | 14.161 ms | 0 - 144 MB | NPU
|
| 142 |
+
| DnCNN | TFLITE | float | Qualcomm® QCS8450 | 14.005 ms | 0 - 180 MB | NPU
|
| 143 |
+
| DnCNN | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 14.318 ms | 0 - 4 MB | NPU
|
| 144 |
+
| DnCNN | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 4.163 ms | 0 - 147 MB | NPU
|
| 145 |
+
| DnCNN | TFLITE | float | Qualcomm® SA7255P | 56.39 ms | 0 - 142 MB | NPU
|
| 146 |
+
| DnCNN | TFLITE | float | Qualcomm® SA8295P | 15.612 ms | 0 - 141 MB | NPU
|
| 147 |
+
| DnCNN | TFLITE | float | Snapdragon® 8 Elite Mobile | 4.163 ms | 0 - 147 MB | NPU
|
| 148 |
+
| DnCNN | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.173 ms | 0 - 146 MB | NPU
|
| 149 |
+
| DnCNN | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 1.302 ms | 0 - 47 MB | NPU
|
| 150 |
+
| DnCNN | TFLITE | w8a8 | Snapdragon® 8 Gen 1 Mobile | 2.343 ms | 0 - 52 MB | NPU
|
| 151 |
+
| DnCNN | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 9.451 ms | 0 - 3 MB | NPU
|
| 152 |
+
| DnCNN | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 2.14 ms | 0 - 3 MB | NPU
|
| 153 |
+
| DnCNN | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 7.522 ms | 0 - 29 MB | NPU
|
| 154 |
+
| DnCNN | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.711 ms | 0 - 72 MB | NPU
|
| 155 |
+
| DnCNN | TFLITE | w8a8 | Qualcomm® SA8775P | 1.98 ms | 0 - 30 MB | NPU
|
| 156 |
+
| DnCNN | TFLITE | w8a8 | Qualcomm® SA8650P | 1.98 ms | 0 - 30 MB | NPU
|
| 157 |
+
| DnCNN | TFLITE | w8a8 | Qualcomm® SA8255P | 1.98 ms | 0 - 30 MB | NPU
|
| 158 |
+
| DnCNN | TFLITE | w8a8 | Qualcomm® QCS8450 | 2.343 ms | 0 - 52 MB | NPU
|
| 159 |
+
| DnCNN | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 1.819 ms | 0 - 3 MB | NPU
|
| 160 |
+
| DnCNN | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 38.909 ms | 0 - 141 MB | NPU
|
| 161 |
+
| DnCNN | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 3.215 ms | 0 - 141 MB | NPU
|
| 162 |
+
| DnCNN | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 1.19 ms | 0 - 30 MB | NPU
|
| 163 |
+
| DnCNN | TFLITE | w8a8 | Qualcomm® SA7255P | 7.522 ms | 0 - 29 MB | NPU
|
| 164 |
+
| DnCNN | TFLITE | w8a8 | Qualcomm® SA8295P | 4.183 ms | 0 - 26 MB | NPU
|
| 165 |
+
| DnCNN | TFLITE | w8a8 | Snapdragon® 8 Elite Mobile | 1.19 ms | 0 - 30 MB | NPU
|
| 166 |
+
| DnCNN | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.771 ms | 0 - 30 MB | NPU
|
| 167 |
+
| DnCNN | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 3.215 ms | 0 - 141 MB | NPU
|
| 168 |
|
| 169 |
## License
|
| 170 |
* The license for the original implementation of DnCNN 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/dncnn/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/dncnn/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/dncnn/releases/v0.
|
| 24 |
}
|
| 25 |
}
|
| 26 |
},
|
|
@@ -31,19 +31,19 @@
|
|
| 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/dncnn/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/dncnn/releases/v0.
|
| 41 |
},
|
| 42 |
"tflite": {
|
| 43 |
"tool_versions": {
|
| 44 |
"qairt": "2.45.0.260326154327"
|
| 45 |
},
|
| 46 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/dncnn/releases/v0.
|
| 47 |
}
|
| 48 |
}
|
| 49 |
}
|
|
|
|
| 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/dncnn/releases/v0.60.0/dncnn-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/dncnn/releases/v0.60.0/dncnn-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/dncnn/releases/v0.60.0/dncnn-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/dncnn/releases/v0.60.0/dncnn-onnx-w8a8.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/dncnn/releases/v0.60.0/dncnn-qnn_dlc-w8a8.zip"
|
| 41 |
},
|
| 42 |
"tflite": {
|
| 43 |
"tool_versions": {
|
| 44 |
"qairt": "2.45.0.260326154327"
|
| 45 |
},
|
| 46 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/dncnn/releases/v0.60.0/dncnn-tflite-w8a8.zip"
|
| 47 |
}
|
| 48 |
}
|
| 49 |
}
|