v0.61.0
Browse filesSee https://github.com/qualcomm/ai-hub-models/releases/v0.61.0 for changelog.
- README.md +110 -109
- release_assets.json +7 -7
README.md
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
---
|
| 2 |
library_name: pytorch
|
| 3 |
-
license:
|
| 4 |
tags:
|
| 5 |
- backbone
|
| 6 |
- bu_auto
|
|
@@ -16,7 +16,7 @@ pipeline_tag: image-classification
|
|
| 16 |
EfficientNet-Lite4 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.
|
| 17 |
|
| 18 |
This is based on the implementation of EfficientNet-Lite4 found [here](https://github.com/RangiLyu/EfficientNet-Lite).
|
| 19 |
-
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.
|
| 20 |
|
| 21 |
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.
|
| 22 |
|
|
@@ -29,26 +29,26 @@ Below are pre-exported model assets ready for deployment.
|
|
| 29 |
|
| 30 |
| Runtime | Precision | Chipset | SDK Versions | Download |
|
| 31 |
|---|---|---|---|---|
|
| 32 |
-
| 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/efficientnet_lite4/releases/v0.
|
| 33 |
-
| 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/efficientnet_lite4/releases/v0.
|
| 34 |
-
| QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/efficientnet_lite4/releases/v0.
|
| 35 |
-
| QNN_DLC | w8a8 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/efficientnet_lite4/releases/v0.
|
| 36 |
-
| TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/efficientnet_lite4/releases/v0.
|
| 37 |
-
| TFLITE | w8a8 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/efficientnet_lite4/releases/v0.
|
| 38 |
|
| 39 |
For more device-specific assets and performance metrics, visit **[EfficientNet-Lite4 on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/efficientnet_lite4)**.
|
| 40 |
|
| 41 |
|
| 42 |
### Option 2: Export with Custom Configurations
|
| 43 |
|
| 44 |
-
Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.
|
| 45 |
- Custom weights (e.g., fine-tuned checkpoints)
|
| 46 |
- Custom input shapes
|
| 47 |
- Target device and runtime configurations
|
| 48 |
|
| 49 |
This option is ideal if you need to customize the model beyond the default configuration provided here.
|
| 50 |
|
| 51 |
-
See our repository for [EfficientNet-Lite4 on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.
|
| 52 |
|
| 53 |
## Model Details
|
| 54 |
|
|
@@ -63,107 +63,108 @@ See our repository for [EfficientNet-Lite4 on GitHub](https://github.com/qualcom
|
|
| 63 |
## Performance Summary
|
| 64 |
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
|
| 65 |
|---|---|---|---|---|---|---
|
| 66 |
-
| EfficientNet-Lite4 | ONNX | float | Snapdragon® X2 Elite | 1.
|
| 67 |
-
| EfficientNet-Lite4 | ONNX | float | Snapdragon® X Elite | 2.
|
| 68 |
-
| EfficientNet-Lite4 | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 1.
|
| 69 |
-
| EfficientNet-Lite4 | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 5.
|
| 70 |
-
| EfficientNet-Lite4 | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 4.
|
| 71 |
-
| EfficientNet-Lite4 | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 2.
|
| 72 |
-
| EfficientNet-Lite4 | ONNX | float | Qualcomm® QCS8450 | 5.
|
| 73 |
-
| EfficientNet-Lite4 | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 4.
|
| 74 |
-
| EfficientNet-Lite4 | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 2.
|
| 75 |
-
| EfficientNet-Lite4 | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 1.
|
| 76 |
-
| EfficientNet-Lite4 | ONNX | float | Snapdragon® 8 Elite Mobile | 1.
|
| 77 |
-
| EfficientNet-Lite4 | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.
|
| 78 |
-
| EfficientNet-Lite4 | ONNX | w8a8 | Snapdragon® X2 Elite | 0.
|
| 79 |
-
| EfficientNet-Lite4 | ONNX | w8a8 | Snapdragon® X Elite | 1.
|
| 80 |
-
| EfficientNet-Lite4 | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.
|
| 81 |
-
| EfficientNet-Lite4 | ONNX | w8a8 | Snapdragon® 8 Gen 1 Mobile | 2.
|
| 82 |
-
| EfficientNet-Lite4 | ONNX | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 6.
|
| 83 |
-
| EfficientNet-Lite4 | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 1.
|
| 84 |
-
| EfficientNet-Lite4 | ONNX | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.
|
| 85 |
-
| EfficientNet-Lite4 | ONNX | w8a8 | Qualcomm® QCS8450 | 2.
|
| 86 |
-
| EfficientNet-Lite4 | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 1.
|
| 87 |
-
| EfficientNet-Lite4 | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 1.
|
| 88 |
-
| EfficientNet-Lite4 | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 10.
|
| 89 |
-
| EfficientNet-Lite4 | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 1.
|
| 90 |
-
| EfficientNet-Lite4 | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 0.
|
| 91 |
-
| EfficientNet-Lite4 | ONNX | w8a8 | Snapdragon® 8 Elite Mobile | 0.
|
| 92 |
-
| EfficientNet-Lite4 | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.
|
| 93 |
-
| EfficientNet-Lite4 | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 1.
|
| 94 |
-
| EfficientNet-Lite4 | QNN_DLC | float | Snapdragon® X2 Elite | 1.
|
| 95 |
-
| EfficientNet-Lite4 | QNN_DLC | float | Snapdragon® X Elite | 3.
|
| 96 |
-
| EfficientNet-Lite4 | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 2.
|
| 97 |
-
| EfficientNet-Lite4 | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 6.
|
| 98 |
-
| EfficientNet-Lite4 | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 4.
|
| 99 |
-
| EfficientNet-Lite4 | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 15.
|
| 100 |
-
| EfficientNet-Lite4 | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 3.
|
| 101 |
-
| EfficientNet-Lite4 | QNN_DLC | float | Qualcomm® SA8775P | 4.
|
| 102 |
-
| EfficientNet-Lite4 | QNN_DLC | float | Qualcomm® SA8650P | 4.
|
| 103 |
-
| EfficientNet-Lite4 | QNN_DLC | float | Qualcomm® SA8255P | 4.
|
| 104 |
-
| EfficientNet-Lite4 | QNN_DLC | float | Qualcomm® QCS8450 | 6.
|
| 105 |
-
| EfficientNet-Lite4 | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 4.
|
| 106 |
-
| EfficientNet-Lite4 | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 3.
|
| 107 |
-
| EfficientNet-Lite4 | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 1.
|
| 108 |
-
| EfficientNet-Lite4 | QNN_DLC | float | Qualcomm® SA7255P | 15.
|
| 109 |
-
| EfficientNet-Lite4 | QNN_DLC | float | Qualcomm® SA8295P | 6.
|
| 110 |
-
| EfficientNet-Lite4 | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 1.
|
| 111 |
-
| EfficientNet-Lite4 | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.
|
| 112 |
-
| EfficientNet-Lite4 | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 0.
|
| 113 |
-
| EfficientNet-Lite4 | QNN_DLC | w8a8 | Snapdragon® X Elite | 1.
|
| 114 |
-
| EfficientNet-Lite4 | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.
|
| 115 |
-
| EfficientNet-Lite4 | QNN_DLC | w8a8 | Snapdragon® 8 Gen 1 Mobile | 2.
|
| 116 |
-
| EfficientNet-Lite4 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 7.
|
| 117 |
-
| EfficientNet-Lite4 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 1.
|
| 118 |
-
| EfficientNet-Lite4 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 3.
|
| 119 |
-
| EfficientNet-Lite4 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.
|
| 120 |
-
| EfficientNet-Lite4 | QNN_DLC | w8a8 | Qualcomm® SA8775P | 1.
|
| 121 |
-
| EfficientNet-Lite4 | QNN_DLC | w8a8 | Qualcomm® SA8650P | 1.
|
| 122 |
-
| EfficientNet-Lite4 | QNN_DLC | w8a8 | Qualcomm® SA8255P | 1.
|
| 123 |
-
| EfficientNet-Lite4 | QNN_DLC | w8a8 | Qualcomm® QCS8450 | 2.
|
| 124 |
-
| EfficientNet-Lite4 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 1.
|
| 125 |
-
| EfficientNet-Lite4 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 1.
|
| 126 |
-
| EfficientNet-Lite4 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 11.
|
| 127 |
-
| EfficientNet-Lite4 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 1.
|
| 128 |
-
| EfficientNet-Lite4 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 0.
|
| 129 |
-
| EfficientNet-Lite4 | QNN_DLC | w8a8 | Qualcomm® SA7255P | 3.
|
| 130 |
-
| EfficientNet-Lite4 | QNN_DLC | w8a8 | Qualcomm® SA8295P | 2.
|
| 131 |
-
| EfficientNet-Lite4 | QNN_DLC | w8a8 | Snapdragon® 8 Elite Mobile | 0.
|
| 132 |
-
| EfficientNet-Lite4 | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.
|
| 133 |
-
| EfficientNet-Lite4 | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 1.
|
| 134 |
-
| EfficientNet-Lite4 | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 2.
|
| 135 |
-
| EfficientNet-Lite4 | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 6.
|
| 136 |
-
| EfficientNet-Lite4 | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 4.
|
| 137 |
-
| EfficientNet-Lite4 | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 15.
|
| 138 |
-
| EfficientNet-Lite4 | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 3.
|
| 139 |
-
| EfficientNet-Lite4 | TFLITE | float | Qualcomm® SA8775P | 4.
|
| 140 |
-
| EfficientNet-Lite4 | TFLITE | float | Qualcomm® SA8650P | 4.
|
| 141 |
-
| EfficientNet-Lite4 | TFLITE | float | Qualcomm® SA8255P | 4.
|
| 142 |
-
| EfficientNet-Lite4 | TFLITE | float | Qualcomm® QCS8450 | 6.
|
| 143 |
-
| EfficientNet-Lite4 | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 4.
|
| 144 |
-
| EfficientNet-Lite4 | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 1.
|
| 145 |
-
| EfficientNet-Lite4 | TFLITE | float | Qualcomm® SA7255P | 15.
|
| 146 |
-
| EfficientNet-Lite4 | TFLITE | float | Qualcomm® SA8295P | 6.
|
| 147 |
-
| EfficientNet-Lite4 | TFLITE | float | Snapdragon® 8 Elite Mobile | 1.
|
| 148 |
-
| EfficientNet-Lite4 | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.
|
| 149 |
-
| EfficientNet-Lite4 | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.
|
| 150 |
-
| EfficientNet-Lite4 | TFLITE | w8a8 | Snapdragon® 8 Gen 1 Mobile | 1.
|
| 151 |
-
| EfficientNet-Lite4 | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 5.
|
|
|
|
| 152 |
| EfficientNet-Lite4 | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 2.801 ms | 0 - 59 MB | NPU
|
| 153 |
-
| EfficientNet-Lite4 | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 0.
|
| 154 |
-
| EfficientNet-Lite4 | TFLITE | w8a8 | Qualcomm® SA8775P | 1.
|
| 155 |
-
| EfficientNet-Lite4 | TFLITE | w8a8 | Qualcomm® SA8650P | 1.
|
| 156 |
-
| EfficientNet-Lite4 | TFLITE | w8a8 | Qualcomm® SA8255P | 1.
|
| 157 |
-
| EfficientNet-Lite4 | TFLITE | w8a8 | Qualcomm® QCS8450 | 1.
|
| 158 |
-
| EfficientNet-Lite4 | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 1.
|
| 159 |
-
| EfficientNet-Lite4 | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 10.
|
| 160 |
-
| EfficientNet-Lite4 | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 1.
|
| 161 |
-
| EfficientNet-Lite4 | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 0.
|
| 162 |
| EfficientNet-Lite4 | TFLITE | w8a8 | Qualcomm® SA7255P | 2.801 ms | 0 - 59 MB | NPU
|
| 163 |
-
| EfficientNet-Lite4 | TFLITE | w8a8 | Qualcomm® SA8295P | 2.
|
| 164 |
-
| EfficientNet-Lite4 | TFLITE | w8a8 | Snapdragon® 8 Elite Mobile | 0.
|
| 165 |
-
| EfficientNet-Lite4 | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.
|
| 166 |
-
| EfficientNet-Lite4 | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 1.
|
| 167 |
|
| 168 |
## License
|
| 169 |
* The license for the original implementation of EfficientNet-Lite4 can be found
|
|
|
|
| 1 |
---
|
| 2 |
library_name: pytorch
|
| 3 |
+
license: apache-2.0
|
| 4 |
tags:
|
| 5 |
- backbone
|
| 6 |
- bu_auto
|
|
|
|
| 16 |
EfficientNet-Lite4 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.
|
| 17 |
|
| 18 |
This is based on the implementation of EfficientNet-Lite4 found [here](https://github.com/RangiLyu/EfficientNet-Lite).
|
| 19 |
+
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/v0.61.0/src/qai_hub_models/models/efficientnet_lite4) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
|
| 20 |
|
| 21 |
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.
|
| 22 |
|
|
|
|
| 29 |
|
| 30 |
| Runtime | Precision | Chipset | SDK Versions | Download |
|
| 31 |
|---|---|---|---|---|
|
| 32 |
+
| 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/efficientnet_lite4/releases/v0.61.0/efficientnet_lite4-onnx-float.zip)
|
| 33 |
+
| 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/efficientnet_lite4/releases/v0.61.0/efficientnet_lite4-onnx-w8a8.zip)
|
| 34 |
+
| QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/efficientnet_lite4/releases/v0.61.0/efficientnet_lite4-qnn_dlc-float.zip)
|
| 35 |
+
| QNN_DLC | w8a8 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/efficientnet_lite4/releases/v0.61.0/efficientnet_lite4-qnn_dlc-w8a8.zip)
|
| 36 |
+
| TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/efficientnet_lite4/releases/v0.61.0/efficientnet_lite4-tflite-float.zip)
|
| 37 |
+
| TFLITE | w8a8 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/efficientnet_lite4/releases/v0.61.0/efficientnet_lite4-tflite-w8a8.zip)
|
| 38 |
|
| 39 |
For more device-specific assets and performance metrics, visit **[EfficientNet-Lite4 on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/efficientnet_lite4)**.
|
| 40 |
|
| 41 |
|
| 42 |
### Option 2: Export with Custom Configurations
|
| 43 |
|
| 44 |
+
Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.61.0/src/qai_hub_models/models/efficientnet_lite4) Python library to compile and export the model with your own:
|
| 45 |
- Custom weights (e.g., fine-tuned checkpoints)
|
| 46 |
- Custom input shapes
|
| 47 |
- Target device and runtime configurations
|
| 48 |
|
| 49 |
This option is ideal if you need to customize the model beyond the default configuration provided here.
|
| 50 |
|
| 51 |
+
See our repository for [EfficientNet-Lite4 on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.61.0/src/qai_hub_models/models/efficientnet_lite4) for usage instructions.
|
| 52 |
|
| 53 |
## Model Details
|
| 54 |
|
|
|
|
| 63 |
## Performance Summary
|
| 64 |
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
|
| 65 |
|---|---|---|---|---|---|---
|
| 66 |
+
| EfficientNet-Lite4 | ONNX | float | Snapdragon® X2 Elite | 1.445 ms | 1 - 1 MB | NPU
|
| 67 |
+
| EfficientNet-Lite4 | ONNX | float | Snapdragon® X Elite | 2.721 ms | 28 - 28 MB | NPU
|
| 68 |
+
| EfficientNet-Lite4 | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 1.902 ms | 0 - 101 MB | NPU
|
| 69 |
+
| EfficientNet-Lite4 | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 5.534 ms | 0 - 101 MB | NPU
|
| 70 |
+
| EfficientNet-Lite4 | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 4.626 ms | 1 - 5 MB | NPU
|
| 71 |
+
| EfficientNet-Lite4 | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 2.626 ms | 0 - 44 MB | NPU
|
| 72 |
+
| EfficientNet-Lite4 | ONNX | float | Qualcomm® QCS8450 | 5.534 ms | 0 - 101 MB | NPU
|
| 73 |
+
| EfficientNet-Lite4 | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 4.143 ms | 1 - 4 MB | NPU
|
| 74 |
+
| EfficientNet-Lite4 | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 2.721 ms | 28 - 28 MB | NPU
|
| 75 |
+
| EfficientNet-Lite4 | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 1.5 ms | 0 - 56 MB | NPU
|
| 76 |
+
| EfficientNet-Lite4 | ONNX | float | Snapdragon® 8 Elite Mobile | 1.5 ms | 0 - 56 MB | NPU
|
| 77 |
+
| EfficientNet-Lite4 | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.148 ms | 0 - 58 MB | NPU
|
| 78 |
+
| EfficientNet-Lite4 | ONNX | w8a8 | Snapdragon® X2 Elite | 0.648 ms | 1 - 1 MB | NPU
|
| 79 |
+
| EfficientNet-Lite4 | ONNX | w8a8 | Snapdragon® X Elite | 1.279 ms | 16 - 16 MB | NPU
|
| 80 |
+
| EfficientNet-Lite4 | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.859 ms | 0 - 110 MB | NPU
|
| 81 |
+
| EfficientNet-Lite4 | ONNX | w8a8 | Snapdragon® 8 Gen 1 Mobile | 2.082 ms | 0 - 118 MB | NPU
|
| 82 |
+
| EfficientNet-Lite4 | ONNX | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 6.1 ms | 0 - 3 MB | NPU
|
| 83 |
+
| EfficientNet-Lite4 | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 1.337 ms | 0 - 4 MB | NPU
|
| 84 |
+
| EfficientNet-Lite4 | ONNX | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.231 ms | 0 - 18 MB | NPU
|
| 85 |
+
| EfficientNet-Lite4 | ONNX | w8a8 | Qualcomm® QCS8450 | 2.082 ms | 0 - 118 MB | NPU
|
| 86 |
+
| EfficientNet-Lite4 | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 1.42 ms | 0 - 3 MB | NPU
|
| 87 |
+
| EfficientNet-Lite4 | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 1.279 ms | 16 - 16 MB | NPU
|
| 88 |
+
| EfficientNet-Lite4 | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 10.96 ms | 0 - 194 MB | NPU
|
| 89 |
+
| EfficientNet-Lite4 | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 1.611 ms | 0 - 72 MB | NPU
|
| 90 |
+
| EfficientNet-Lite4 | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 0.716 ms | 0 - 72 MB | NPU
|
| 91 |
+
| EfficientNet-Lite4 | ONNX | w8a8 | Snapdragon® 8 Elite Mobile | 0.716 ms | 0 - 72 MB | NPU
|
| 92 |
+
| EfficientNet-Lite4 | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.602 ms | 0 - 74 MB | NPU
|
| 93 |
+
| EfficientNet-Lite4 | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 1.611 ms | 0 - 72 MB | NPU
|
| 94 |
+
| EfficientNet-Lite4 | QNN_DLC | float | Snapdragon® X2 Elite | 1.838 ms | 1 - 1 MB | NPU
|
| 95 |
+
| EfficientNet-Lite4 | QNN_DLC | float | Snapdragon® X Elite | 3.534 ms | 1 - 1 MB | NPU
|
| 96 |
+
| EfficientNet-Lite4 | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 2.199 ms | 0 - 98 MB | NPU
|
| 97 |
+
| EfficientNet-Lite4 | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 6.884 ms | 0 - 99 MB | NPU
|
| 98 |
+
| EfficientNet-Lite4 | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 4.837 ms | 1 - 4 MB | NPU
|
| 99 |
+
| EfficientNet-Lite4 | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 15.306 ms | 1 - 54 MB | NPU
|
| 100 |
+
| EfficientNet-Lite4 | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 3.139 ms | 1 - 3 MB | NPU
|
| 101 |
+
| EfficientNet-Lite4 | QNN_DLC | float | Qualcomm® SA8775P | 4.796 ms | 1 - 54 MB | NPU
|
| 102 |
+
| EfficientNet-Lite4 | QNN_DLC | float | Qualcomm® SA8650P | 4.796 ms | 1 - 54 MB | NPU
|
| 103 |
+
| EfficientNet-Lite4 | QNN_DLC | float | Qualcomm® SA8255P | 4.796 ms | 1 - 54 MB | NPU
|
| 104 |
+
| EfficientNet-Lite4 | QNN_DLC | float | Qualcomm® QCS8450 | 6.884 ms | 0 - 99 MB | NPU
|
| 105 |
+
| EfficientNet-Lite4 | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 4.511 ms | 1 - 4 MB | NPU
|
| 106 |
+
| EfficientNet-Lite4 | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 3.534 ms | 1 - 1 MB | NPU
|
| 107 |
+
| EfficientNet-Lite4 | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 1.688 ms | 0 - 55 MB | NPU
|
| 108 |
+
| EfficientNet-Lite4 | QNN_DLC | float | Qualcomm® SA7255P | 15.306 ms | 1 - 54 MB | NPU
|
| 109 |
+
| EfficientNet-Lite4 | QNN_DLC | float | Qualcomm® SA8295P | 6.445 ms | 1 - 50 MB | NPU
|
| 110 |
+
| EfficientNet-Lite4 | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 1.688 ms | 0 - 55 MB | NPU
|
| 111 |
+
| EfficientNet-Lite4 | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.267 ms | 1 - 56 MB | NPU
|
| 112 |
+
| EfficientNet-Lite4 | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 0.755 ms | 0 - 0 MB | NPU
|
| 113 |
+
| EfficientNet-Lite4 | QNN_DLC | w8a8 | Snapdragon® X Elite | 1.436 ms | 0 - 0 MB | NPU
|
| 114 |
+
| EfficientNet-Lite4 | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.908 ms | 0 - 97 MB | NPU
|
| 115 |
+
| EfficientNet-Lite4 | QNN_DLC | w8a8 | Snapdragon® 8 Gen 1 Mobile | 2.334 ms | 0 - 106 MB | NPU
|
| 116 |
+
| EfficientNet-Lite4 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 7.091 ms | 0 - 2 MB | NPU
|
| 117 |
+
| EfficientNet-Lite4 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 1.334 ms | 0 - 3 MB | NPU
|
| 118 |
+
| EfficientNet-Lite4 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 3.376 ms | 0 - 63 MB | NPU
|
| 119 |
+
| EfficientNet-Lite4 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.271 ms | 0 - 2 MB | NPU
|
| 120 |
+
| EfficientNet-Lite4 | QNN_DLC | w8a8 | Qualcomm® SA8775P | 1.603 ms | 0 - 65 MB | NPU
|
| 121 |
+
| EfficientNet-Lite4 | QNN_DLC | w8a8 | Qualcomm® SA8650P | 1.603 ms | 0 - 65 MB | NPU
|
| 122 |
+
| EfficientNet-Lite4 | QNN_DLC | w8a8 | Qualcomm® SA8255P | 1.603 ms | 0 - 65 MB | NPU
|
| 123 |
+
| EfficientNet-Lite4 | QNN_DLC | w8a8 | Qualcomm® QCS8450 | 2.334 ms | 0 - 106 MB | NPU
|
| 124 |
+
| EfficientNet-Lite4 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 1.43 ms | 0 - 2 MB | NPU
|
| 125 |
+
| EfficientNet-Lite4 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 1.436 ms | 0 - 0 MB | NPU
|
| 126 |
+
| EfficientNet-Lite4 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 11.276 ms | 0 - 185 MB | NPU
|
| 127 |
+
| EfficientNet-Lite4 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 1.621 ms | 0 - 65 MB | NPU
|
| 128 |
+
| EfficientNet-Lite4 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 0.653 ms | 0 - 67 MB | NPU
|
| 129 |
+
| EfficientNet-Lite4 | QNN_DLC | w8a8 | Qualcomm® SA7255P | 3.376 ms | 0 - 63 MB | NPU
|
| 130 |
+
| EfficientNet-Lite4 | QNN_DLC | w8a8 | Qualcomm® SA8295P | 2.529 ms | 0 - 61 MB | NPU
|
| 131 |
+
| EfficientNet-Lite4 | QNN_DLC | w8a8 | Snapdragon® 8 Elite Mobile | 0.653 ms | 0 - 67 MB | NPU
|
| 132 |
+
| EfficientNet-Lite4 | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.528 ms | 0 - 64 MB | NPU
|
| 133 |
+
| EfficientNet-Lite4 | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 1.621 ms | 0 - 65 MB | NPU
|
| 134 |
+
| EfficientNet-Lite4 | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 2.185 ms | 0 - 112 MB | NPU
|
| 135 |
+
| EfficientNet-Lite4 | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 6.678 ms | 0 - 113 MB | NPU
|
| 136 |
+
| EfficientNet-Lite4 | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 4.849 ms | 0 - 33 MB | NPU
|
| 137 |
+
| EfficientNet-Lite4 | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 15.31 ms | 0 - 64 MB | NPU
|
| 138 |
+
| EfficientNet-Lite4 | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 3.104 ms | 0 - 3 MB | NPU
|
| 139 |
+
| EfficientNet-Lite4 | TFLITE | float | Qualcomm® SA8775P | 4.802 ms | 0 - 65 MB | NPU
|
| 140 |
+
| EfficientNet-Lite4 | TFLITE | float | Qualcomm® SA8650P | 4.802 ms | 0 - 65 MB | NPU
|
| 141 |
+
| EfficientNet-Lite4 | TFLITE | float | Qualcomm® SA8255P | 4.802 ms | 0 - 65 MB | NPU
|
| 142 |
+
| EfficientNet-Lite4 | TFLITE | float | Qualcomm® QCS8450 | 6.678 ms | 0 - 113 MB | NPU
|
| 143 |
+
| EfficientNet-Lite4 | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 4.551 ms | 0 - 32 MB | NPU
|
| 144 |
+
| EfficientNet-Lite4 | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 1.688 ms | 0 - 68 MB | NPU
|
| 145 |
+
| EfficientNet-Lite4 | TFLITE | float | Qualcomm® SA7255P | 15.31 ms | 0 - 64 MB | NPU
|
| 146 |
+
| EfficientNet-Lite4 | TFLITE | float | Qualcomm® SA8295P | 6.458 ms | 0 - 48 MB | NPU
|
| 147 |
+
| EfficientNet-Lite4 | TFLITE | float | Snapdragon® 8 Elite Mobile | 1.688 ms | 0 - 68 MB | NPU
|
| 148 |
+
| EfficientNet-Lite4 | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.261 ms | 0 - 67 MB | NPU
|
| 149 |
+
| EfficientNet-Lite4 | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.656 ms | 0 - 100 MB | NPU
|
| 150 |
+
| EfficientNet-Lite4 | TFLITE | w8a8 | Snapdragon® 8 Gen 1 Mobile | 1.756 ms | 0 - 103 MB | NPU
|
| 151 |
+
| EfficientNet-Lite4 | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 5.79 ms | 0 - 31 MB | NPU
|
| 152 |
+
| EfficientNet-Lite4 | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 1.039 ms | 0 - 18 MB | NPU
|
| 153 |
| EfficientNet-Lite4 | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 2.801 ms | 0 - 59 MB | NPU
|
| 154 |
+
| EfficientNet-Lite4 | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 0.928 ms | 0 - 2 MB | NPU
|
| 155 |
+
| EfficientNet-Lite4 | TFLITE | w8a8 | Qualcomm® SA8775P | 1.273 ms | 0 - 62 MB | NPU
|
| 156 |
+
| EfficientNet-Lite4 | TFLITE | w8a8 | Qualcomm® SA8650P | 1.273 ms | 0 - 62 MB | NPU
|
| 157 |
+
| EfficientNet-Lite4 | TFLITE | w8a8 | Qualcomm® SA8255P | 1.273 ms | 0 - 62 MB | NPU
|
| 158 |
+
| EfficientNet-Lite4 | TFLITE | w8a8 | Qualcomm® QCS8450 | 1.756 ms | 0 - 103 MB | NPU
|
| 159 |
+
| EfficientNet-Lite4 | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 1.085 ms | 0 - 17 MB | NPU
|
| 160 |
+
| EfficientNet-Lite4 | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 10.046 ms | 0 - 178 MB | NPU
|
| 161 |
+
| EfficientNet-Lite4 | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 1.241 ms | 0 - 174 MB | NPU
|
| 162 |
+
| EfficientNet-Lite4 | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 0.518 ms | 0 - 58 MB | NPU
|
| 163 |
| EfficientNet-Lite4 | TFLITE | w8a8 | Qualcomm® SA7255P | 2.801 ms | 0 - 59 MB | NPU
|
| 164 |
+
| EfficientNet-Lite4 | TFLITE | w8a8 | Qualcomm® SA8295P | 2.14 ms | 0 - 56 MB | NPU
|
| 165 |
+
| EfficientNet-Lite4 | TFLITE | w8a8 | Snapdragon® 8 Elite Mobile | 0.518 ms | 0 - 58 MB | NPU
|
| 166 |
+
| EfficientNet-Lite4 | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.417 ms | 0 - 62 MB | NPU
|
| 167 |
+
| EfficientNet-Lite4 | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 1.241 ms | 0 - 174 MB | NPU
|
| 168 |
|
| 169 |
## License
|
| 170 |
* The license for the original implementation of EfficientNet-Lite4 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/efficientnet_lite4/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/efficientnet_lite4/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/efficientnet_lite4/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/efficientnet_lite4/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/efficientnet_lite4/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/efficientnet_lite4/releases/v0.
|
| 47 |
}
|
| 48 |
}
|
| 49 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"version": "0.61.0",
|
| 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/efficientnet_lite4/releases/v0.61.0/efficientnet_lite4-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/efficientnet_lite4/releases/v0.61.0/efficientnet_lite4-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/efficientnet_lite4/releases/v0.61.0/efficientnet_lite4-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/efficientnet_lite4/releases/v0.61.0/efficientnet_lite4-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/efficientnet_lite4/releases/v0.61.0/efficientnet_lite4-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/efficientnet_lite4/releases/v0.61.0/efficientnet_lite4-tflite-w8a8.zip"
|
| 47 |
}
|
| 48 |
}
|
| 49 |
}
|