Yolo-v3

qualcomm/Yolo-v3

Yolo-v3 is a object detection model from qualcomm. Use it when you need objects located in an image. It is set up for pytorch. The card lists the license as agpl-3.0.

Downloads · 30 days

19% of all-time downloads

All-time downloads

199

Public

Repo size

429 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.md9.1 KB · 84%

At a glance

Task: Object Detection
Library: pytorch
License: agpl-3.0
Access: Public
Created: Dec 12, 2024
Updated: Sep 23, 2026
SHA: 983d095e

Model card

From the Hugging Face model README

Yolo-v3: Optimized for Qualcomm Devices

YoloV3 is a machine learning model that predicts bounding boxes and classes of objects in an image.

This is based on the implementation of Yolo-v3 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 Yolo-v3 on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.object_detection

Model Stats:

Input resolution: 416p (416x416)
Model checkpoint: YoloV3 Tiny
Model size (float): 43.9 MB
Model size (w8a16): 16.9 MB
Number of parameters: 11.5M

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
Yolo-v3	ONNX	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	1.852 ms	0 - 144 MB	NPU
Yolo-v3	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	2.453 ms	1 - 148 MB	NPU
Yolo-v3	ONNX	float	Snapdragon® X2 Elite	2.378 ms	5 - 5 MB	NPU
Yolo-v3	ONNX	float	Snapdragon® X Elite	4.013 ms	19 - 19 MB	NPU
Yolo-v3	ONNX	float	Snapdragon® 8 Gen 3 Mobile	3.15 ms	3 - 165 MB	NPU
Yolo-v3	ONNX	float	Snapdragon® 8 Gen 1 Mobile	9.601 ms	5 - 188 MB	NPU
Yolo-v3	ONNX	float	Qualcomm® Dragonwing™ IQ-8275	6.696 ms	5 - 9 MB	NPU
Yolo-v3	ONNX	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	3.93 ms	0 - 21 MB	NPU
Yolo-v3	ONNX	float	Qualcomm® QCS8450	9.601 ms	5 - 188 MB	NPU
Yolo-v3	ONNX	float	Qualcomm® Dragonwing™ IQ-9075	5.857 ms	5 - 8 MB	NPU
Yolo-v3	ONNX	float	Qualcomm® Dragonwing™ IQ-X7181	4.013 ms	19 - 19 MB	NPU
Yolo-v3	ONNX	float	Qualcomm® Dragonwing™ Q-8750	2.453 ms	1 - 148 MB	NPU
Yolo-v3	ONNX	w8a16	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	1.404 ms	2 - 62 MB	NPU
Yolo-v3	ONNX	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	1.807 ms	0 - 53 MB	NPU
Yolo-v3	ONNX	w8a16	Snapdragon® X2 Elite	1.592 ms	2 - 2 MB	NPU
Yolo-v3	ONNX	w8a16	Snapdragon® X Elite	3.787 ms	10 - 10 MB	NPU
Yolo-v3	ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	2.527 ms	0 - 90 MB	NPU
Yolo-v3	ONNX	w8a16	Snapdragon® 8 Gen 1 Mobile	4.442 ms	3 - 92 MB	NPU
Yolo-v3	ONNX	w8a16	Qualcomm® Dragonwing™ QCS6490	13.141 ms	2 - 6 MB	NPU
Yolo-v3	ONNX	w8a16	Qualcomm® Dragonwing™ IQ-8275	3.734 ms	0 - 4 MB	NPU
Yolo-v3	ONNX	w8a16	Qualcomm® Dragonwing™ QCS8550 (Proxy)	3.69 ms	0 - 12 MB	NPU
Yolo-v3	ONNX	w8a16	Qualcomm® QCS8450	4.442 ms	3 - 92 MB	NPU
Yolo-v3	ONNX	w8a16	Qualcomm® Dragonwing™ IQ-9075	3.846 ms	2 - 6 MB	NPU
Yolo-v3	ONNX	w8a16	Qualcomm® Dragonwing™ IQ-X7181	3.787 ms	10 - 10 MB	NPU
Yolo-v3	ONNX	w8a16	Qualcomm® Dragonwing™ Q-6690	40.78 ms	3 - 179 MB	NPU
Yolo-v3	ONNX	w8a16	Qualcomm® Dragonwing™ Q-7790	5.452 ms	2 - 175 MB	NPU
Yolo-v3	ONNX	w8a16	Qualcomm® Dragonwing™ Q-8750	1.807 ms	0 - 53 MB	NPU
Yolo-v3	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	5.452 ms	2 - 175 MB	NPU
Yolo-v3	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	1.685 ms	4 - 143 MB	NPU
Yolo-v3	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	2.216 ms	0 - 140 MB	NPU
Yolo-v3	QNN_DLC	float	Snapdragon® X2 Elite	2.358 ms	5 - 5 MB	NPU
Yolo-v3	QNN_DLC	float	Snapdragon® X Elite	3.831 ms	5 - 5 MB	NPU
Yolo-v3	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	2.77 ms	5 - 156 MB	NPU
Yolo-v3	QNN_DLC	float	Snapdragon® 8 Gen 1 Mobile	9.543 ms	5 - 173 MB	NPU
Yolo-v3	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-8275	6.237 ms	5 - 12 MB	NPU
Yolo-v3	QNN_DLC	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	3.505 ms	4 - 5 MB	NPU
Yolo-v3	QNN_DLC	float	Qualcomm® QCS8450	9.543 ms	5 - 173 MB	NPU
Yolo-v3	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-9075	5.493 ms	5 - 11 MB	NPU
Yolo-v3	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-X7181	3.831 ms	5 - 5 MB	NPU
Yolo-v3	QNN_DLC	float	Qualcomm® Dragonwing™ Q-8750	2.216 ms	0 - 140 MB	NPU
Yolo-v3	QNN_DLC	float	Qualcomm® SA8295P	9.269 ms	0 - 147 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	1.383 ms	0 - 53 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	1.826 ms	0 - 50 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Snapdragon® X2 Elite	1.778 ms	2 - 2 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Snapdragon® X Elite	4.002 ms	2 - 2 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Snapdragon® 8 Gen 3 Mobile	2.56 ms	2 - 81 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Snapdragon® 8 Gen 1 Mobile	4.428 ms	2 - 85 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Qualcomm® Dragonwing™ QCS6490	12.586 ms	2 - 6 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-8275	3.765 ms	1 - 6 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Qualcomm® Dragonwing™ QCS8550 (Proxy)	3.697 ms	2 - 71 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Qualcomm® SA8650P	4.058 ms	1 - 47 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Qualcomm® SA8255P	4.058 ms	1 - 47 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Qualcomm® QCS8450	4.428 ms	2 - 85 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-9075	3.813 ms	1 - 5 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Qualcomm® Dragonwing™ IQ-X7181	4.002 ms	2 - 2 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Qualcomm® Dragonwing™ Q-6690	37.498 ms	2 - 170 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Qualcomm® Dragonwing™ Q-7790	4.753 ms	2 - 169 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Qualcomm® Dragonwing™ Q-8750	1.826 ms	0 - 50 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Qualcomm® SA8295P	5.374 ms	0 - 46 MB	NPU
Yolo-v3	QNN_DLC	w8a16	Snapdragon® 7 Gen 4 Mobile	4.753 ms	2 - 169 MB	NPU
Yolo-v3	TFLITE	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	1.641 ms	0 - 140 MB	NPU
Yolo-v3	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	2.138 ms	0 - 145 MB	NPU
Yolo-v3	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	2.693 ms	0 - 175 MB	NPU
Yolo-v3	TFLITE	float	Snapdragon® 8 Gen 1 Mobile	8.691 ms	0 - 193 MB	NPU
Yolo-v3	TFLITE	float	Qualcomm® Dragonwing™ IQ-8275	6.158 ms	0 - 32 MB	NPU
Yolo-v3	TFLITE	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	3.43 ms	0 - 87 MB	NPU
Yolo-v3	TFLITE	float	Qualcomm® SA8775P	5.518 ms	0 - 143 MB	NPU
Yolo-v3	TFLITE	float	Qualcomm® SA8650P	5.518 ms	0 - 143 MB	NPU
Yolo-v3	TFLITE	float	Qualcomm® SA8255P	5.518 ms	0 - 143 MB	NPU
Yolo-v3	TFLITE	float	Qualcomm® QCS8450	8.691 ms	0 - 193 MB	NPU
Yolo-v3	TFLITE	float	Qualcomm® Dragonwing™ IQ-9075	5.323 ms	0 - 31 MB	NPU
Yolo-v3	TFLITE	float	Qualcomm® Dragonwing™ Q-8750	2.138 ms	0 - 145 MB	NPU
Yolo-v3	TFLITE	float	Qualcomm® SA7255P	75.857 ms	1 - 21 MB	GPU
Yolo-v3	TFLITE	float	Qualcomm® SA8295P	8.902 ms	0 - 148 MB	NPU

License

The license for the original implementation of Yolo-v3 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.

Task: Object Detection
Library: pytorch
License: agpl-3.0
Created: Dec 12, 2024
Updated: Sep 23, 2026