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 2.42, ONNX Runtime 1.24.3	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:

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

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
ResNet34-SSD	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	38.083 ms	0 - 503 MB	NPU
ResNet34-SSD	ONNX	float	Snapdragon® X2 Elite	42.948 ms	30 - 30 MB	NPU
ResNet34-SSD	ONNX	float	Snapdragon® X Elite	91.439 ms	29 - 29 MB	NPU
ResNet34-SSD	ONNX	float	Snapdragon® 8 Gen 3 Mobile	62.737 ms	2 - 515 MB	NPU
ResNet34-SSD	ONNX	float	Qualcomm® QCS8550 (Proxy)	90.435 ms	0 - 32 MB	NPU
ResNet34-SSD	ONNX	float	Qualcomm® QCS9075	152.805 ms	16 - 36 MB	NPU
ResNet34-SSD	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	50.221 ms	1 - 431 MB	NPU
ResNet34-SSD	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	52.144 ms	16 - 551 MB	NPU
ResNet34-SSD	QNN_DLC	float	Snapdragon® X2 Elite	61.954 ms	17 - 17 MB	NPU
ResNet34-SSD	QNN_DLC	float	Snapdragon® X Elite	129.337 ms	17 - 17 MB	NPU
ResNet34-SSD	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	84.716 ms	16 - 607 MB	NPU
ResNet34-SSD	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	481.457 ms	16 - 385 MB	NPU
ResNet34-SSD	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	129.514 ms	17 - 20 MB	NPU
ResNet34-SSD	QNN_DLC	float	Qualcomm® QCS9075	194.011 ms	17 - 35 MB	NPU
ResNet34-SSD	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	260.877 ms	4 - 508 MB	NPU
ResNet34-SSD	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	67.232 ms	16 - 394 MB	NPU
ResNet34-SSD	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	74.9 ms	0 - 564 MB	NPU
ResNet34-SSD	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	108.177 ms	0 - 547 MB	NPU
ResNet34-SSD	TFLITE	float	Qualcomm® QCS8275 (Proxy)	513.551 ms	0 - 377 MB	NPU
ResNet34-SSD	TFLITE	float	Qualcomm® QCS8550 (Proxy)	143.313 ms	0 - 4 MB	NPU
ResNet34-SSD	TFLITE	float	Qualcomm® QCS9075	199.657 ms	0 - 64 MB	NPU
ResNet34-SSD	TFLITE	float	Qualcomm® QCS8450 (Proxy)	232.566 ms	1 - 616 MB	NPU
ResNet34-SSD	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	86.771 ms	19 - 421 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