RTMDet: Optimized for Mobile Deployment
Real-time object detection optimized for mobile and edge
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 model is an implementation of RTMDet found here.
More details on model performance across various devices, can be found here.
Model Details
- Model Type: Object detection
- Model Stats:
- Model checkpoint: RTMDet Medium
- Input resolution: 640x640
- Number of parameters: 27.5M
- Model size: 105 MB
| Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model |
|---|---|---|---|---|---|---|---|---|
| RTMDet | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 16.655 ms | 0 - 16 MB | FP16 | NPU | -- |
| RTMDet | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 16.756 ms | 1 - 150 MB | FP16 | NPU | -- |
| RTMDet | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 12.399 ms | 0 - 102 MB | FP16 | NPU | -- |
| RTMDet | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 12.989 ms | 5 - 44 MB | FP16 | NPU | -- |
| RTMDet | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 11.629 ms | 0 - 64 MB | FP16 | NPU | -- |
| RTMDet | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 11.77 ms | 5 - 36 MB | FP16 | NPU | -- |
| RTMDet | SA7255P ADP | SA7255P | TFLITE | 578.983 ms | 0 - 62 MB | FP16 | NPU | -- |
| RTMDet | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 16.501 ms | 0 - 14 MB | FP16 | NPU | -- |
| RTMDet | SA8295P ADP | SA8295P | TFLITE | 34.28 ms | 0 - 70 MB | FP16 | NPU | -- |
| RTMDet | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 16.418 ms | 0 - 12 MB | FP16 | NPU | -- |
| RTMDet | SA8775P ADP | SA8775P | TFLITE | 29.382 ms | 0 - 61 MB | FP16 | NPU | -- |
| RTMDet | QCS8275 (Proxy) | QCS8275 Proxy | TFLITE | 578.983 ms | 0 - 62 MB | FP16 | NPU | -- |
| RTMDet | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 15.949 ms | 0 - 15 MB | FP16 | NPU | -- |
| RTMDet | QCS9075 (Proxy) | QCS9075 Proxy | TFLITE | 29.382 ms | 0 - 61 MB | FP16 | NPU | -- |
| RTMDet | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 31.458 ms | 0 - 110 MB | FP16 | NPU | -- |
| RTMDet | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 17.03 ms | 48 - 48 MB | FP16 | NPU | -- |
License
- The license for the original implementation of RTMDet can be found here.
- The license for the compiled assets for on-device deployment 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.
Usage and Limitations
Model may not be used for or in connection with any of the following applications:
- Accessing essential private and public services and benefits;
- Administration of justice and democratic processes;
- Assessing or recognizing the emotional state of a person;
- Biometric and biometrics-based systems, including categorization of persons based on sensitive characteristics;
- Education and vocational training;
- Employment and workers management;
- Exploitation of the vulnerabilities of persons resulting in harmful behavior;
- General purpose social scoring;
- Law enforcement;
- Management and operation of critical infrastructure;
- Migration, asylum and border control management;
- Predictive policing;
- Real-time remote biometric identification in public spaces;
- Recommender systems of social media platforms;
- Scraping of facial images (from the internet or otherwise); and/or
- Subliminal manipulation
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The HF Inference API does not support object-detection models for pytorch library.