ResNet34-SSD: Optimized for Qualcomm Devices

ResNet34-SSD is a single-stage object detection model that integrates the ResNet34 backbone with the SSD (Single Shot MultiBox Detector) framework. It is optimized for real-time detection tasks and supports multiple deployment backends including PyTorch, TensorFlow, and ONNX.

This is based on the implementation of ResNet34-SSD 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

There are two ways to deploy this model on your device:

Option 1: Download Pre-Exported Models

Below are pre-exported model assets ready for deployment.

Runtime	Precision	Chipset	SDK Versions	Download
ONNX	float	Universal	QAIRT 2.45, ONNX Runtime 1.27.1	Download
QNN_DLC	float	Universal	QAIRT 2.45	Download
TFLITE	float	Universal	QAIRT 2.45	Download

For more device-specific assets and performance metrics, visit ResNet34-SSD on Qualcomm® AI Hub.

Option 2: Export with Custom Configurations

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

This option is ideal if you need to customize the model beyond the default configuration provided here.

See our repository for ResNet34-SSD on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.object_detection

Model Stats:

Input resolution: 1x3x1200x1200
Model checkpoint: resnet34-ssd1200
Model size (float): 76.2 MB
Number of parameters: 20.0M

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
ResNet34-SSD	ONNX	float	Snapdragon® X2 Elite	43.227 ms	17 - 17 MB	NPU
ResNet34-SSD	ONNX	float	Snapdragon® X Elite	88.356 ms	30 - 30 MB	NPU
ResNet34-SSD	ONNX	float	Snapdragon® 8 Gen 3 Mobile	63.393 ms	17 - 518 MB	NPU
ResNet34-SSD	ONNX	float	Snapdragon® 8 Gen 1 Mobile	176.166 ms	1 - 428 MB	NPU
ResNet34-SSD	ONNX	float	Qualcomm® Dragonwing™ IQ-8275	142.042 ms	16 - 36 MB	NPU
ResNet34-SSD	ONNX	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	87.968 ms	0 - 36 MB	NPU
ResNet34-SSD	ONNX	float	Qualcomm® QCS8450	176.166 ms	1 - 428 MB	NPU
ResNet34-SSD	ONNX	float	Qualcomm® Dragonwing™ IQ-9075	143.91 ms	16 - 36 MB	NPU
ResNet34-SSD	ONNX	float	Qualcomm® Dragonwing™ IQ-X7181	88.356 ms	30 - 30 MB	NPU
ResNet34-SSD	ONNX	float	Qualcomm® Dragonwing™ Q-8750	52.011 ms	1 - 424 MB	NPU
ResNet34-SSD	ONNX	float	Snapdragon® 8 Elite Mobile	52.011 ms	1 - 424 MB	NPU
ResNet34-SSD	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	38.954 ms	0 - 492 MB	NPU
ResNet34-SSD	QNN_DLC	float	Snapdragon® X2 Elite	62.034 ms	17 - 17 MB	NPU
ResNet34-SSD	QNN_DLC	float	Snapdragon® X Elite	129.612 ms	17 - 17 MB	NPU
ResNet34-SSD	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	85.001 ms	16 - 604 MB	NPU
ResNet34-SSD	QNN_DLC	float	Snapdragon® 8 Gen 1 Mobile	260.874 ms	3 - 509 MB	NPU
ResNet34-SSD	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-8275	168.201 ms	17 - 35 MB	NPU
ResNet34-SSD	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-8275	482.663 ms	16 - 384 MB	NPU
ResNet34-SSD	QNN_DLC	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	129.04 ms	17 - 18 MB	NPU
ResNet34-SSD	QNN_DLC	float	Qualcomm® SA8775P	173.767 ms	16 - 385 MB	NPU
ResNet34-SSD	QNN_DLC	float	Qualcomm® SA8650P	173.767 ms	16 - 385 MB	NPU
ResNet34-SSD	QNN_DLC	float	Qualcomm® SA8255P	173.767 ms	16 - 385 MB	NPU
ResNet34-SSD	QNN_DLC	float	Qualcomm® QCS8450	260.874 ms	3 - 509 MB	NPU
ResNet34-SSD	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-9075	172.761 ms	17 - 35 MB	NPU
ResNet34-SSD	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-X7181	129.612 ms	17 - 17 MB	NPU
ResNet34-SSD	QNN_DLC	float	Qualcomm® Dragonwing™ Q-8750	67.171 ms	12 - 388 MB	NPU
ResNet34-SSD	QNN_DLC	float	Qualcomm® SA7255P	482.663 ms	16 - 384 MB	NPU
ResNet34-SSD	QNN_DLC	float	Qualcomm® SA8295P	183.467 ms	0 - 329 MB	NPU
ResNet34-SSD	QNN_DLC	float	Snapdragon® 8 Elite Mobile	67.171 ms	12 - 388 MB	NPU
ResNet34-SSD	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	52.284 ms	12 - 559 MB	NPU
ResNet34-SSD	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	107.67 ms	0 - 543 MB	NPU
ResNet34-SSD	TFLITE	float	Snapdragon® 8 Gen 1 Mobile	236.469 ms	0 - 619 MB	NPU
ResNet34-SSD	TFLITE	float	Qualcomm® Dragonwing™ IQ-8275	187.29 ms	0 - 66 MB	NPU
ResNet34-SSD	TFLITE	float	Qualcomm® Dragonwing™ IQ-8275	513.165 ms	0 - 378 MB	NPU
ResNet34-SSD	TFLITE	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	145.953 ms	0 - 4 MB	NPU
ResNet34-SSD	TFLITE	float	Qualcomm® SA8775P	183.807 ms	0 - 426 MB	NPU
ResNet34-SSD	TFLITE	float	Qualcomm® SA8650P	183.807 ms	0 - 426 MB	NPU
ResNet34-SSD	TFLITE	float	Qualcomm® SA8255P	183.807 ms	0 - 426 MB	NPU
ResNet34-SSD	TFLITE	float	Qualcomm® QCS8450	236.469 ms	0 - 619 MB	NPU
ResNet34-SSD	TFLITE	float	Qualcomm® Dragonwing™ IQ-9075	180.674 ms	0 - 65 MB	NPU
ResNet34-SSD	TFLITE	float	Qualcomm® Dragonwing™ Q-8750	87.444 ms	0 - 402 MB	NPU
ResNet34-SSD	TFLITE	float	Qualcomm® SA7255P	513.165 ms	0 - 378 MB	NPU
ResNet34-SSD	TFLITE	float	Qualcomm® SA8295P	202.27 ms	0 - 354 MB	NPU
ResNet34-SSD	TFLITE	float	Snapdragon® 8 Elite Mobile	87.444 ms	0 - 402 MB	NPU
ResNet34-SSD	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	72.293 ms	0 - 569 MB	NPU

License

The license for the original implementation of ResNet34-SSD can be found here.

References

Source Model Implementation

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.

Downloads last month: -; Downloads are not tracked for this model. How to track