RTMDet: Optimized for Qualcomm Devices
RTMDet is a highly efficient model for real-time object detection,capable of predicting both the bounding boxes and classes of objects within an image.It is highly optimized for real-time applications, making it reliable for industrial and commercial use
This is based on the implementation of RTMDet 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
Due to licensing restrictions, we cannot distribute pre-exported model assets for this model. 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
See our repository for RTMDet on GitHub for usage instructions.
Model Details
Model Type: Model_use_case.object_detection
Model Stats:
- Model checkpoint: RTMDet Medium
- Input resolution: 640x640
- Number of parameters: 27.5M
- Model size (float): 105 MB
Performance Summary
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit |
|---|---|---|---|---|---|---|
| RTMDet | ONNX | float | Snapdragon® X Elite | 14.171 ms | 51 - 51 MB | NPU |
| RTMDet | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 10.639 ms | 1 - 231 MB | NPU |
| RTMDet | ONNX | float | Qualcomm® QCS8550 (Proxy) | 13.599 ms | 0 - 55 MB | NPU |
| RTMDet | ONNX | float | Qualcomm® QCS9075 | 23.813 ms | 5 - 12 MB | NPU |
| RTMDet | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 8.292 ms | 3 - 184 MB | NPU |
| RTMDet | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 5.965 ms | 5 - 189 MB | NPU |
| RTMDet | ONNX | float | Snapdragon® X2 Elite | 8.135 ms | 53 - 53 MB | NPU |
| RTMDet | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 11.725 ms | 0 - 284 MB | NPU |
| RTMDet | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 84.077 ms | 0 - 207 MB | NPU |
| RTMDet | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 15.722 ms | 0 - 273 MB | NPU |
| RTMDet | TFLITE | float | Qualcomm® SA8775P | 22.993 ms | 0 - 207 MB | NPU |
| RTMDet | TFLITE | float | Qualcomm® QCS9075 | 24.341 ms | 0 - 62 MB | NPU |
| RTMDet | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 37.678 ms | 0 - 348 MB | NPU |
| RTMDet | TFLITE | float | Qualcomm® SA7255P | 84.077 ms | 0 - 207 MB | NPU |
| RTMDet | TFLITE | float | Qualcomm® SA8295P | 29.929 ms | 0 - 268 MB | NPU |
| RTMDet | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 9.157 ms | 0 - 210 MB | NPU |
| RTMDet | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 6.82 ms | 0 - 210 MB | NPU |
License
- The license for the original implementation of RTMDet 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.