RF-DETR: Optimized for Qualcomm Devices
DETR is a machine learning model that can detect objects (trained on COCO dataset).
This is based on the implementation of RF-DETR 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 |
|---|---|---|---|---|
| QNN_DLC | float | Universal | QAIRT 2.45 | Download |
For more device-specific assets and performance metrics, visit RF-DETR 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 RF-DETR on GitHub for usage instructions.
Model Details
Model Type: Model_use_case.object_detection
Model Stats:
- Model checkpoint: RF-DETR-base
- Input resolution: 560x560
- Number of parameters: 29.0M
- Model size: 116MB
Performance Summary
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit |
|---|---|---|---|---|---|---|
| RF-DETR | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 34.493 ms | 4 - 802 MB | NPU |
| RF-DETR | QNN_DLC | float | Snapdragon® X2 Elite | 33.471 ms | 4 - 4 MB | NPU |
| RF-DETR | QNN_DLC | float | Snapdragon® X Elite | 73.007 ms | 4 - 4 MB | NPU |
| RF-DETR | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 54.705 ms | 4 - 982 MB | NPU |
| RF-DETR | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 163.411 ms | 1 - 889 MB | NPU |
| RF-DETR | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 72.23 ms | 4 - 6 MB | NPU |
| RF-DETR | QNN_DLC | float | Qualcomm® SA8775P | 76.746 ms | 1 - 880 MB | NPU |
| RF-DETR | QNN_DLC | float | Qualcomm® QCS9075 | 102.974 ms | 4 - 9 MB | NPU |
| RF-DETR | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 109.202 ms | 3 - 1056 MB | NPU |
| RF-DETR | QNN_DLC | float | Qualcomm® SA7255P | 163.411 ms | 1 - 889 MB | NPU |
| RF-DETR | QNN_DLC | float | Qualcomm® SA8295P | 102.693 ms | 0 - 896 MB | NPU |
| RF-DETR | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 37.911 ms | 0 - 846 MB | NPU |
License
- The license for the original implementation of RF-DETR 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.