Yolo-R / README.md

v0.65.0

59550c5 verified 14 days ago

6.72 kB

---
library_name: pytorch
license: gpl-3.0
tags:
- bu_auto
- real_time
- android
pipeline_tag: object-detection

---
![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/yolor/web-assets/model_demo.png)

# Yolo-R: Optimized for Qualcomm Devices

YoloR is a machine learning model that predicts bounding boxes and classes of objects in an image.

This is based on the implementation of Yolo-R found [here](https://github.com/WongKinYiu/yolor).
This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.65.0/src/qai_hub_models/models/yolor) 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/qualcomm/ai-hub-models/blob/v0.65.0/src/qai_hub_models/models/yolor) 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 [Yolo-R on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.65.0/src/qai_hub_models/models/yolor) for usage instructions.


## Model Details

**Model Type:** Model_use_case.object_detection
**Model Stats:**
- Input resolution: 640x640
- Model checkpoint: yolor_p6
- Model size (float): 17.9 MB
- Number of parameters: 4.68M

## Performance Summary
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
|---|---|---|---|---|---|---
| Yolo-R | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 14.486 ms | 1 - 328 MB | NPU
| Yolo-R | ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 13.576 ms | 1 - 320 MB | NPU
| Yolo-R | ONNX | w8a16 | Snapdragon® X2 Elite | 15.19 ms | 2 - 2 MB | NPU
| Yolo-R | ONNX | w8a16 | Snapdragon® X Elite | 23.229 ms | 37 - 37 MB | NPU
| Yolo-R | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 15.874 ms | 3 - 393 MB | NPU
| Yolo-R | ONNX | w8a16 | Snapdragon® 8 Gen 1 Mobile | 30.311 ms | 0 - 389 MB | NPU
| Yolo-R | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 21.484 ms | 1 - 7 MB | NPU
| Yolo-R | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 22.502 ms | 0 - 40 MB | NPU
| Yolo-R | ONNX | w8a16 | Qualcomm® QCS8450 | 30.311 ms | 0 - 389 MB | NPU
| Yolo-R | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 23.232 ms | 1 - 6 MB | NPU
| Yolo-R | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 23.229 ms | 37 - 37 MB | NPU
| Yolo-R | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 34.113 ms | 3 - 307 MB | NPU
| Yolo-R | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 13.576 ms | 1 - 320 MB | NPU
| Yolo-R | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 34.113 ms | 3 - 307 MB | NPU
| Yolo-R | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 5.738 ms | 1 - 313 MB | NPU
| Yolo-R | QNN_DLC | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 7.379 ms | 2 - 307 MB | NPU
| Yolo-R | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 6.978 ms | 2 - 2 MB | NPU
| Yolo-R | QNN_DLC | w8a16 | Snapdragon® X Elite | 16.004 ms | 2 - 2 MB | NPU
| Yolo-R | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 9.907 ms | 2 - 370 MB | NPU
| Yolo-R | QNN_DLC | w8a16 | Snapdragon® 8 Gen 1 Mobile | 23.056 ms | 2 - 371 MB | NPU
| Yolo-R | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 56.814 ms | 2 - 7 MB | NPU
| Yolo-R | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 13.95 ms | 2 - 8 MB | NPU
| Yolo-R | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 15.109 ms | 2 - 5 MB | NPU
| Yolo-R | QNN_DLC | w8a16 | Qualcomm® SA8650P | 15.488 ms | 1 - 310 MB | NPU
| Yolo-R | QNN_DLC | w8a16 | Qualcomm® SA8255P | 15.488 ms | 1 - 310 MB | NPU
| Yolo-R | QNN_DLC | w8a16 | Qualcomm® QCS8450 | 23.056 ms | 2 - 371 MB | NPU
| Yolo-R | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 15.461 ms | 0 - 5 MB | NPU
| Yolo-R | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 16.004 ms | 2 - 2 MB | NPU
| Yolo-R | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 170.895 ms | 2 - 343 MB | NPU
| Yolo-R | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 21.866 ms | 2 - 318 MB | NPU
| Yolo-R | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 7.379 ms | 2 - 307 MB | NPU
| Yolo-R | QNN_DLC | w8a16 | Qualcomm® SA8295P | 19.914 ms | 0 - 301 MB | NPU
| Yolo-R | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 21.866 ms | 2 - 318 MB | NPU
| Yolo-R | TFLITE | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 15.188 ms | 0 - 285 MB | NPU
| Yolo-R | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 18.086 ms | 1 - 275 MB | NPU
| Yolo-R | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 48.145 ms | 0 - 398 MB | NPU
| Yolo-R | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 56.554 ms | 0 - 438 MB | NPU
| Yolo-R | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 64.291 ms | 1 - 86 MB | NPU
| Yolo-R | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 67.898 ms | 0 - 2 MB | NPU
| Yolo-R | TFLITE | float | Qualcomm® SA8775P | 133.821 ms | 17 - 41 MB | GPU
| Yolo-R | TFLITE | float | Qualcomm® SA8650P | 133.821 ms | 17 - 41 MB | GPU
| Yolo-R | TFLITE | float | Qualcomm® SA8255P | 133.821 ms | 17 - 41 MB | GPU
| Yolo-R | TFLITE | float | Qualcomm® QCS8450 | 56.554 ms | 0 - 438 MB | NPU
| Yolo-R | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 71.3 ms | 0 - 85 MB | NPU
| Yolo-R | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 18.086 ms | 1 - 275 MB | NPU
| Yolo-R | TFLITE | float | Qualcomm® SA7255P | 129.396 ms | 1 - 285 MB | NPU
| Yolo-R | TFLITE | float | Qualcomm® SA8295P | 53.337 ms | 1 - 329 MB | NPU
## License
* The license for the original implementation of Yolo-R can be found
  [here](https://github.com/WongKinYiu/yolor/blob/main/LICENSE).
## References
* [You Only Learn One Representation: Unified Network for Multiple Tasks](https://arxiv.org/abs/2105.04206)
* [Source Model Implementation](https://github.com/WongKinYiu/yolor)
## 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).

	---
	library_name: pytorch
	license: gpl-3.0
	tags:
	- bu_auto
	- real_time
	- android
	pipeline_tag: object-detection

	---

	![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/yolor/web-assets/model_demo.png)

	# Yolo-R: Optimized for Qualcomm Devices

	YoloR is a machine learning model that predicts bounding boxes and classes of objects in an image.

	This is based on the implementation of Yolo-R found [here](https://github.com/WongKinYiu/yolor).
	This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.65.0/src/qai_hub_models/models/yolor) 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/qualcomm/ai-hub-models/blob/v0.65.0/src/qai_hub_models/models/yolor) 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 [Yolo-R on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.65.0/src/qai_hub_models/models/yolor) for usage instructions.


	## Model Details

	Model Type: Model_use_case.object_detection

	Model Stats:
	- Input resolution: 640x640
	- Model checkpoint: yolor_p6
	- Model size (float): 17.9 MB
	- Number of parameters: 4.68M

	## Performance Summary
	\| Model \| Runtime \| Precision \| Chipset \| Inference Time (ms) \| Peak Memory Range (MB) \| Primary Compute Unit
	\|---\|---\|---\|---\|---\|---\|---
	\| Yolo-R \| ONNX \| w8a16 \| Snapdragon® 8 Elite Gen 5 For Galaxy Mobile \| 14.486 ms \| 1 - 328 MB \| NPU
	\| Yolo-R \| ONNX \| w8a16 \| Snapdragon® 8 Elite For Galaxy Mobile \| 13.576 ms \| 1 - 320 MB \| NPU
	\| Yolo-R \| ONNX \| w8a16 \| Snapdragon® X2 Elite \| 15.19 ms \| 2 - 2 MB \| NPU
	\| Yolo-R \| ONNX \| w8a16 \| Snapdragon® X Elite \| 23.229 ms \| 37 - 37 MB \| NPU
	\| Yolo-R \| ONNX \| w8a16 \| Snapdragon® 8 Gen 3 Mobile \| 15.874 ms \| 3 - 393 MB \| NPU
	\| Yolo-R \| ONNX \| w8a16 \| Snapdragon® 8 Gen 1 Mobile \| 30.311 ms \| 0 - 389 MB \| NPU
	\| Yolo-R \| ONNX \| w8a16 \| Qualcomm® Dragonwing™ IQ-8275 \| 21.484 ms \| 1 - 7 MB \| NPU
	\| Yolo-R \| ONNX \| w8a16 \| Qualcomm® Dragonwing™ QCS8550 (Proxy) \| 22.502 ms \| 0 - 40 MB \| NPU
	\| Yolo-R \| ONNX \| w8a16 \| Qualcomm® QCS8450 \| 30.311 ms \| 0 - 389 MB \| NPU
	\| Yolo-R \| ONNX \| w8a16 \| Qualcomm® Dragonwing™ IQ-9075 \| 23.232 ms \| 1 - 6 MB \| NPU
	\| Yolo-R \| ONNX \| w8a16 \| Qualcomm® Dragonwing™ IQ-X7181 \| 23.229 ms \| 37 - 37 MB \| NPU
	\| Yolo-R \| ONNX \| w8a16 \| Qualcomm® Dragonwing™ Q-7790 \| 34.113 ms \| 3 - 307 MB \| NPU
	\| Yolo-R \| ONNX \| w8a16 \| Qualcomm® Dragonwing™ Q-8750 \| 13.576 ms \| 1 - 320 MB \| NPU
	\| Yolo-R \| ONNX \| w8a16 \| Snapdragon® 7 Gen 4 Mobile \| 34.113 ms \| 3 - 307 MB \| NPU
	\| Yolo-R \| QNN_DLC \| w8a16 \| Snapdragon® 8 Elite Gen 5 For Galaxy Mobile \| 5.738 ms \| 1 - 313 MB \| NPU
	\| Yolo-R \| QNN_DLC \| w8a16 \| Snapdragon® 8 Elite For Galaxy Mobile \| 7.379 ms \| 2 - 307 MB \| NPU
	\| Yolo-R \| QNN_DLC \| w8a16 \| Snapdragon® X2 Elite \| 6.978 ms \| 2 - 2 MB \| NPU
	\| Yolo-R \| QNN_DLC \| w8a16 \| Snapdragon® X Elite \| 16.004 ms \| 2 - 2 MB \| NPU
	\| Yolo-R \| QNN_DLC \| w8a16 \| Snapdragon® 8 Gen 3 Mobile \| 9.907 ms \| 2 - 370 MB \| NPU
	\| Yolo-R \| QNN_DLC \| w8a16 \| Snapdragon® 8 Gen 1 Mobile \| 23.056 ms \| 2 - 371 MB \| NPU
	\| Yolo-R \| QNN_DLC \| w8a16 \| Qualcomm® Dragonwing™ QCS6490 \| 56.814 ms \| 2 - 7 MB \| NPU
	\| Yolo-R \| QNN_DLC \| w8a16 \| Qualcomm® Dragonwing™ IQ-8275 \| 13.95 ms \| 2 - 8 MB \| NPU
	\| Yolo-R \| QNN_DLC \| w8a16 \| Qualcomm® Dragonwing™ QCS8550 (Proxy) \| 15.109 ms \| 2 - 5 MB \| NPU
	\| Yolo-R \| QNN_DLC \| w8a16 \| Qualcomm® SA8650P \| 15.488 ms \| 1 - 310 MB \| NPU
	\| Yolo-R \| QNN_DLC \| w8a16 \| Qualcomm® SA8255P \| 15.488 ms \| 1 - 310 MB \| NPU
	\| Yolo-R \| QNN_DLC \| w8a16 \| Qualcomm® QCS8450 \| 23.056 ms \| 2 - 371 MB \| NPU
	\| Yolo-R \| QNN_DLC \| w8a16 \| Qualcomm® Dragonwing™ IQ-9075 \| 15.461 ms \| 0 - 5 MB \| NPU
	\| Yolo-R \| QNN_DLC \| w8a16 \| Qualcomm® Dragonwing™ IQ-X7181 \| 16.004 ms \| 2 - 2 MB \| NPU
	\| Yolo-R \| QNN_DLC \| w8a16 \| Qualcomm® Dragonwing™ Q-6690 \| 170.895 ms \| 2 - 343 MB \| NPU
	\| Yolo-R \| QNN_DLC \| w8a16 \| Qualcomm® Dragonwing™ Q-7790 \| 21.866 ms \| 2 - 318 MB \| NPU
	\| Yolo-R \| QNN_DLC \| w8a16 \| Qualcomm® Dragonwing™ Q-8750 \| 7.379 ms \| 2 - 307 MB \| NPU
	\| Yolo-R \| QNN_DLC \| w8a16 \| Qualcomm® SA8295P \| 19.914 ms \| 0 - 301 MB \| NPU
	\| Yolo-R \| QNN_DLC \| w8a16 \| Snapdragon® 7 Gen 4 Mobile \| 21.866 ms \| 2 - 318 MB \| NPU
	\| Yolo-R \| TFLITE \| float \| Snapdragon® 8 Elite Gen 5 For Galaxy Mobile \| 15.188 ms \| 0 - 285 MB \| NPU
	\| Yolo-R \| TFLITE \| float \| Snapdragon® 8 Elite For Galaxy Mobile \| 18.086 ms \| 1 - 275 MB \| NPU
	\| Yolo-R \| TFLITE \| float \| Snapdragon® 8 Gen 3 Mobile \| 48.145 ms \| 0 - 398 MB \| NPU
	\| Yolo-R \| TFLITE \| float \| Snapdragon® 8 Gen 1 Mobile \| 56.554 ms \| 0 - 438 MB \| NPU
	\| Yolo-R \| TFLITE \| float \| Qualcomm® Dragonwing™ IQ-8275 \| 64.291 ms \| 1 - 86 MB \| NPU
	\| Yolo-R \| TFLITE \| float \| Qualcomm® Dragonwing™ QCS8550 (Proxy) \| 67.898 ms \| 0 - 2 MB \| NPU
	\| Yolo-R \| TFLITE \| float \| Qualcomm® SA8775P \| 133.821 ms \| 17 - 41 MB \| GPU
	\| Yolo-R \| TFLITE \| float \| Qualcomm® SA8650P \| 133.821 ms \| 17 - 41 MB \| GPU
	\| Yolo-R \| TFLITE \| float \| Qualcomm® SA8255P \| 133.821 ms \| 17 - 41 MB \| GPU
	\| Yolo-R \| TFLITE \| float \| Qualcomm® QCS8450 \| 56.554 ms \| 0 - 438 MB \| NPU
	\| Yolo-R \| TFLITE \| float \| Qualcomm® Dragonwing™ IQ-9075 \| 71.3 ms \| 0 - 85 MB \| NPU
	\| Yolo-R \| TFLITE \| float \| Qualcomm® Dragonwing™ Q-8750 \| 18.086 ms \| 1 - 275 MB \| NPU
	\| Yolo-R \| TFLITE \| float \| Qualcomm® SA7255P \| 129.396 ms \| 1 - 285 MB \| NPU
	\| Yolo-R \| TFLITE \| float \| Qualcomm® SA8295P \| 53.337 ms \| 1 - 329 MB \| NPU

	## License
	* The license for the original implementation of Yolo-R can be found
	[here](https://github.com/WongKinYiu/yolor/blob/main/LICENSE).

	## References
	* [You Only Learn One Representation: Unified Network for Multiple Tasks](https://arxiv.org/abs/2105.04206)
	* [Source Model Implementation](https://github.com/WongKinYiu/yolor)

	## 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).