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	38.442 ms	17 - 17 MB	NPU
ResNet34-SSD	ONNX	float	Snapdragon® X Elite	74.356 ms	28 - 28 MB	NPU
ResNet34-SSD	ONNX	float	Snapdragon® 8 Gen 3 Mobile	51.09 ms	2 - 476 MB	NPU
ResNet34-SSD	ONNX	float	Snapdragon® 8 Gen 1 Mobile	127.69 ms	1 - 381 MB	NPU
ResNet34-SSD	ONNX	float	Qualcomm® Dragonwing™ IQ-8275	126.98 ms	16 - 36 MB	NPU
ResNet34-SSD	ONNX	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	73.472 ms	0 - 31 MB	NPU
ResNet34-SSD	ONNX	float	Qualcomm® QCS8450	127.69 ms	1 - 381 MB	NPU
ResNet34-SSD	ONNX	float	Qualcomm® Dragonwing™ IQ-9075	119.369 ms	16 - 36 MB	NPU
ResNet34-SSD	ONNX	float	Qualcomm® Dragonwing™ IQ-X7181	74.356 ms	28 - 28 MB	NPU
ResNet34-SSD	ONNX	float	Qualcomm® Dragonwing™ Q-8750	43.309 ms	3 - 272 MB	NPU
ResNet34-SSD	ONNX	float	Snapdragon® 8 Elite Mobile	43.309 ms	3 - 272 MB	NPU
ResNet34-SSD	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	33.494 ms	1 - 287 MB	NPU
ResNet34-SSD	QNN_DLC	float	Snapdragon® X2 Elite	41.949 ms	17 - 17 MB	NPU
ResNet34-SSD	QNN_DLC	float	Snapdragon® X Elite	82.836 ms	17 - 17 MB	NPU
ResNet34-SSD	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	65.369 ms	16 - 385 MB	NPU
ResNet34-SSD	QNN_DLC	float	Snapdragon® 8 Gen 1 Mobile	156.304 ms	6 - 423 MB	NPU
ResNet34-SSD	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-8275	140.983 ms	17 - 36 MB	NPU
ResNet34-SSD	QNN_DLC	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	83.693 ms	17 - 42 MB	NPU
ResNet34-SSD	QNN_DLC	float	Qualcomm® SA8775P	125.468 ms	16 - 270 MB	NPU
ResNet34-SSD	QNN_DLC	float	Qualcomm® SA8650P	125.468 ms	16 - 270 MB	NPU
ResNet34-SSD	QNN_DLC	float	Qualcomm® SA8255P	125.468 ms	16 - 270 MB	NPU
ResNet34-SSD	QNN_DLC	float	Qualcomm® QCS8450	156.304 ms	6 - 423 MB	NPU
ResNet34-SSD	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-9075	125.389 ms	17 - 35 MB	NPU
ResNet34-SSD	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-X7181	82.836 ms	17 - 17 MB	NPU
ResNet34-SSD	QNN_DLC	float	Qualcomm® Dragonwing™ Q-8750	44.274 ms	16 - 281 MB	NPU
ResNet34-SSD	QNN_DLC	float	Qualcomm® SA7255P	435.133 ms	16 - 269 MB	NPU
ResNet34-SSD	QNN_DLC	float	Qualcomm® SA8295P	133.816 ms	0 - 224 MB	NPU
ResNet34-SSD	QNN_DLC	float	Snapdragon® 8 Elite Mobile	44.274 ms	16 - 281 MB	NPU
ResNet34-SSD	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	37.75 ms	12 - 373 MB	NPU
ResNet34-SSD	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	52.132 ms	1 - 531 MB	NPU
ResNet34-SSD	TFLITE	float	Snapdragon® 8 Gen 1 Mobile	147.077 ms	1 - 349 MB	NPU
ResNet34-SSD	TFLITE	float	Qualcomm® Dragonwing™ IQ-8275	127.175 ms	0 - 63 MB	NPU
ResNet34-SSD	TFLITE	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	74.787 ms	0 - 3 MB	NPU
ResNet34-SSD	TFLITE	float	Qualcomm® SA8775P	117.85 ms	1 - 318 MB	NPU
ResNet34-SSD	TFLITE	float	Qualcomm® SA8650P	117.85 ms	1 - 318 MB	NPU
ResNet34-SSD	TFLITE	float	Qualcomm® SA8255P	117.85 ms	1 - 318 MB	NPU
ResNet34-SSD	TFLITE	float	Qualcomm® QCS8450	147.077 ms	1 - 349 MB	NPU
ResNet34-SSD	TFLITE	float	Qualcomm® Dragonwing™ IQ-9075	118.152 ms	0 - 62 MB	NPU
ResNet34-SSD	TFLITE	float	Qualcomm® Dragonwing™ Q-8750	42.153 ms	0 - 290 MB	NPU
ResNet34-SSD	TFLITE	float	Qualcomm® SA7255P	419.768 ms	1 - 311 MB	NPU
ResNet34-SSD	TFLITE	float	Qualcomm® SA8295P	125.506 ms	1 - 230 MB	NPU
ResNet34-SSD	TFLITE	float	Snapdragon® 8 Elite Mobile	42.153 ms	0 - 290 MB	NPU
ResNet34-SSD	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	35.345 ms	0 - 384 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