Deep Layer Aggregation
Paper • 1707.06484 • Published
DLA-102-X: Optimized for Qualcomm Devices
dla is a machine learning model that can classify images from the Imagenet dataset. It is a architecture which can be used as backbone.
This is based on the implementation of DLA-102-X found here. This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the Qualcomm® AI Hub Models library to export with custom configurations. More details on model performance across various devices, can be found here.
Qualcomm AI Hub Models uses Qualcomm AI Hub Workbench to compile, profile, and evaluate this model. Sign up to run these models on a hosted Qualcomm® device.
Getting Started
There are two ways to deploy this model on your device:
Option 1: Download Pre-Exported Models
Below are pre-exported model assets ready for deployment.
| Runtime | Precision | Chipset | SDK Versions | Download |
|---|---|---|---|---|
| ONNX | float | Universal | QAIRT 2.42, ONNX Runtime 1.24.3 | Download |
| ONNX | w8a8 | Universal | QAIRT 2.42, ONNX Runtime 1.24.3 | Download |
| QNN_DLC | float | Universal | QAIRT 2.43 | Download |
| QNN_DLC | w8a8 | Universal | QAIRT 2.43 | Download |
| TFLITE | float | Universal | QAIRT 2.43, TFLite 2.19.1 | Download |
| TFLITE | w8a8 | Universal | QAIRT 2.43, TFLite 2.19.1 | Download |
For more device-specific assets and performance metrics, visit DLA-102-X on Qualcomm® AI Hub.
Option 2: Export with Custom Configurations
Use the Qualcomm® AI Hub Models Python library to compile and export the model with your own:
- Custom weights (e.g., fine-tuned checkpoints)
- Custom input shapes
- Target device and runtime configurations
This option is ideal if you need to customize the model beyond the default configuration provided here.
See our repository for DLA-102-X on GitHub for usage instructions.
Model Details
Model Type: Model_use_case.image_classification
Model Stats:
- Model checkpoint: Imagenet
- Input resolution: 224x224
- Number of parameters: 26.3M
- Model size (float): 100 MB
Performance Summary
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit |
|---|---|---|---|---|---|---|
| DLA-102-X | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.192 ms | 1 - 108 MB | NPU |
| DLA-102-X | ONNX | float | Snapdragon® X2 Elite | 1.326 ms | 54 - 54 MB | NPU |
| DLA-102-X | ONNX | float | Snapdragon® X Elite | 2.941 ms | 54 - 54 MB | NPU |
| DLA-102-X | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 1.89 ms | 0 - 168 MB | NPU |
| DLA-102-X | ONNX | float | Qualcomm® QCS8550 (Proxy) | 2.649 ms | 0 - 59 MB | NPU |
| DLA-102-X | ONNX | float | Qualcomm® QCS9075 | 3.971 ms | 1 - 4 MB | NPU |
| DLA-102-X | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.558 ms | 0 - 103 MB | NPU |
| DLA-102-X | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.737 ms | 0 - 120 MB | NPU |
| DLA-102-X | ONNX | w8a8 | Snapdragon® X2 Elite | 0.721 ms | 28 - 28 MB | NPU |
| DLA-102-X | ONNX | w8a8 | Snapdragon® X Elite | 1.632 ms | 27 - 27 MB | NPU |
| DLA-102-X | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 1.016 ms | 0 - 151 MB | NPU |
| DLA-102-X | ONNX | w8a8 | Qualcomm® QCS6490 | 73.721 ms | 19 - 36 MB | CPU |
| DLA-102-X | ONNX | w8a8 | Qualcomm® QCS8550 (Proxy) | 1.397 ms | 0 - 31 MB | NPU |
| DLA-102-X | ONNX | w8a8 | Qualcomm® QCS9075 | 1.625 ms | 0 - 3 MB | NPU |
| DLA-102-X | ONNX | w8a8 | Qualcomm® QCM6690 | 40.69 ms | 6 - 17 MB | CPU |
| DLA-102-X | ONNX | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.888 ms | 0 - 120 MB | NPU |
| DLA-102-X | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 38.736 ms | 16 - 27 MB | CPU |
| DLA-102-X | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.229 ms | 1 - 106 MB | NPU |
| DLA-102-X | QNN_DLC | float | Snapdragon® X2 Elite | 1.656 ms | 1 - 1 MB | NPU |
| DLA-102-X | QNN_DLC | float | Snapdragon® X Elite | 3.141 ms | 1 - 1 MB | NPU |
| DLA-102-X | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 2.01 ms | 0 - 150 MB | NPU |
| DLA-102-X | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 14.347 ms | 1 - 103 MB | NPU |
| DLA-102-X | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 2.84 ms | 1 - 3 MB | NPU |
| DLA-102-X | QNN_DLC | float | Qualcomm® QCS9075 | 4.227 ms | 3 - 5 MB | NPU |
| DLA-102-X | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 4.583 ms | 0 - 127 MB | NPU |
| DLA-102-X | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.6 ms | 0 - 104 MB | NPU |
| DLA-102-X | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.658 ms | 0 - 107 MB | NPU |
| DLA-102-X | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 0.935 ms | 0 - 0 MB | NPU |
| DLA-102-X | QNN_DLC | w8a8 | Snapdragon® X Elite | 1.586 ms | 0 - 0 MB | NPU |
| DLA-102-X | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.948 ms | 0 - 130 MB | NPU |
| DLA-102-X | QNN_DLC | w8a8 | Qualcomm® QCS6490 | 3.909 ms | 2 - 4 MB | NPU |
| DLA-102-X | QNN_DLC | w8a8 | Qualcomm® QCS8275 (Proxy) | 3.247 ms | 0 - 103 MB | NPU |
| DLA-102-X | QNN_DLC | w8a8 | Qualcomm® QCS8550 (Proxy) | 1.375 ms | 0 - 2 MB | NPU |
| DLA-102-X | QNN_DLC | w8a8 | Qualcomm® QCS9075 | 1.604 ms | 0 - 2 MB | NPU |
| DLA-102-X | QNN_DLC | w8a8 | Qualcomm® QCM6690 | 10.593 ms | 0 - 230 MB | NPU |
| DLA-102-X | QNN_DLC | w8a8 | Qualcomm® QCS8450 (Proxy) | 1.867 ms | 0 - 133 MB | NPU |
| DLA-102-X | QNN_DLC | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.794 ms | 0 - 106 MB | NPU |
| DLA-102-X | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 1.722 ms | 0 - 101 MB | NPU |
| DLA-102-X | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.225 ms | 0 - 163 MB | NPU |
| DLA-102-X | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 1.971 ms | 0 - 209 MB | NPU |
| DLA-102-X | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 14.378 ms | 0 - 162 MB | NPU |
| DLA-102-X | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 2.772 ms | 0 - 6 MB | NPU |
| DLA-102-X | TFLITE | float | Qualcomm® QCS9075 | 4.281 ms | 0 - 57 MB | NPU |
| DLA-102-X | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 4.475 ms | 0 - 179 MB | NPU |
| DLA-102-X | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.58 ms | 0 - 166 MB | NPU |
| DLA-102-X | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.586 ms | 0 - 103 MB | NPU |
| DLA-102-X | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.8 ms | 0 - 134 MB | NPU |
| DLA-102-X | TFLITE | w8a8 | Qualcomm® QCS6490 | 3.575 ms | 0 - 29 MB | NPU |
| DLA-102-X | TFLITE | w8a8 | Qualcomm® QCS8275 (Proxy) | 2.984 ms | 0 - 99 MB | NPU |
| DLA-102-X | TFLITE | w8a8 | Qualcomm® QCS8550 (Proxy) | 1.171 ms | 0 - 2 MB | NPU |
| DLA-102-X | TFLITE | w8a8 | Qualcomm® QCS9075 | 1.363 ms | 0 - 29 MB | NPU |
| DLA-102-X | TFLITE | w8a8 | Qualcomm® QCM6690 | 10.034 ms | 0 - 208 MB | NPU |
| DLA-102-X | TFLITE | w8a8 | Qualcomm® QCS8450 (Proxy) | 1.726 ms | 0 - 137 MB | NPU |
| DLA-102-X | TFLITE | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.712 ms | 0 - 95 MB | NPU |
| DLA-102-X | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 1.485 ms | 0 - 92 MB | NPU |
License
- The license for the original implementation of DLA-102-X can be found here.
References
Community
- Join our AI Hub Slack community to collaborate, post questions and learn more about on-device AI.
- For questions or feedback please reach out to us.