|
|
--- |
|
|
library_name: pytorch |
|
|
license: other |
|
|
tags: |
|
|
- real_time |
|
|
- android |
|
|
pipeline_tag: object-detection |
|
|
|
|
|
--- |
|
|
|
|
|
 |
|
|
|
|
|
# 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](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/rtmdet). |
|
|
This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the [Qualcomm® AI Hub Models](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/rtmdet) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary). |
|
|
|
|
|
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. |
|
|
|
|
|
## Getting Started |
|
|
Due to licensing restrictions, we cannot distribute pre-exported model assets for this model. |
|
|
Use the [Qualcomm® AI Hub Models](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/rtmdet) 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](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/rtmdet) 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 | 14.503 ms | 51 - 51 MB | NPU |
|
|
| RTMDet | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 10.617 ms | 5 - 178 MB | NPU |
|
|
| RTMDet | ONNX | float | Qualcomm® QCS8550 (Proxy) | 14.209 ms | 5 - 7 MB | NPU |
|
|
| RTMDet | ONNX | float | Qualcomm® QCS9075 | 24.305 ms | 5 - 12 MB | NPU |
|
|
| RTMDet | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 8.341 ms | 1 - 127 MB | NPU |
|
|
| RTMDet | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 6.26 ms | 5 - 136 MB | NPU |
|
|
| RTMDet | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 11.853 ms | 0 - 284 MB | NPU |
|
|
| RTMDet | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 83.912 ms | 0 - 208 MB | NPU |
|
|
| RTMDet | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 15.707 ms | 0 - 4 MB | NPU |
|
|
| RTMDet | TFLITE | float | Qualcomm® SA8775P | 22.95 ms | 0 - 208 MB | NPU |
|
|
| RTMDet | TFLITE | float | Qualcomm® QCS9075 | 24.718 ms | 0 - 62 MB | NPU |
|
|
| RTMDet | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 38.102 ms | 0 - 348 MB | NPU |
|
|
| RTMDet | TFLITE | float | Qualcomm® SA7255P | 83.912 ms | 0 - 208 MB | NPU |
|
|
| RTMDet | TFLITE | float | Qualcomm® SA8295P | 30.0 ms | 0 - 269 MB | NPU |
|
|
| RTMDet | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 9.21 ms | 0 - 210 MB | NPU |
|
|
| RTMDet | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 6.713 ms | 0 - 206 MB | NPU |
|
|
|
|
|
## License |
|
|
* The license for the original implementation of RTMDet can be found |
|
|
[here](https://github.com/open-mmlab/mmdetection/blob/3.x/LICENSE). |
|
|
|
|
|
## References |
|
|
* [RTMDet: An Empirical Study of Designing Real-Time Object Detectors](https://github.com/open-mmlab/mmdetection/blob/3.x/README.md) |
|
|
* [Source Model Implementation](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/rtmdet) |
|
|
|
|
|
## Community |
|
|
* Join [our AI Hub Slack community](https://aihub.qualcomm.com/community/slack) to collaborate, post questions and learn more about on-device AI. |
|
|
* For questions or feedback please [reach out to us](mailto:ai-hub-support@qti.qualcomm.com). |
|
|
|
