DETR-ResNet101: Optimized for Qualcomm Devices

DETR is a machine learning model that can detect objects (trained on COCO dataset).

This is based on the implementation of DETR-ResNet101 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 2.37, ONNX Runtime 1.23.0	Download
QNN_DLC	float	Universal	QAIRT 2.42	Download
TFLITE	float	Universal	QAIRT 2.42, TFLite 2.17.0	Download

For more device-specific assets and performance metrics, visit DETR-ResNet101 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 DETR-ResNet101 on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.object_detection

Model Stats:

• Model checkpoint: ResNet101
• Input resolution: 480x480
• Number of parameters: 60.3M
• Model size (float): 230 MB

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
DETR-ResNet101	ONNX	float	Snapdragon® X Elite	24.803 ms	115 - 115 MB	NPU
DETR-ResNet101	ONNX	float	Snapdragon® 8 Gen 3 Mobile	18.062 ms	1 - 451 MB	NPU
DETR-ResNet101	ONNX	float	Qualcomm® QCS8550 (Proxy)	24.774 ms	0 - 3 MB	NPU
DETR-ResNet101	ONNX	float	Qualcomm® QCS9075	41.363 ms	5 - 12 MB	NPU
DETR-ResNet101	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	14.941 ms	1 - 332 MB	NPU
DETR-ResNet101	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	11.12 ms	5 - 278 MB	NPU
DETR-ResNet101	QNN_DLC	float	Snapdragon® X Elite	27.117 ms	5 - 5 MB	NPU
DETR-ResNet101	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	19.81 ms	5 - 471 MB	NPU
DETR-ResNet101	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	138.374 ms	1 - 335 MB	NPU
DETR-ResNet101	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	26.71 ms	5 - 7 MB	NPU
DETR-ResNet101	QNN_DLC	float	Qualcomm® SA8775P	41.241 ms	0 - 334 MB	NPU
DETR-ResNet101	QNN_DLC	float	Qualcomm® QCS9075	46.187 ms	5 - 11 MB	NPU
DETR-ResNet101	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	56.534 ms	2 - 364 MB	NPU
DETR-ResNet101	QNN_DLC	float	Qualcomm® SA7255P	138.374 ms	1 - 335 MB	NPU
DETR-ResNet101	QNN_DLC	float	Qualcomm® SA8295P	43.987 ms	0 - 251 MB	NPU
DETR-ResNet101	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	14.805 ms	1 - 342 MB	NPU
DETR-ResNet101	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	11.74 ms	5 - 361 MB	NPU
DETR-ResNet101	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	19.793 ms	0 - 537 MB	NPU
DETR-ResNet101	TFLITE	float	Qualcomm® QCS8275 (Proxy)	138.24 ms	0 - 403 MB	NPU
DETR-ResNet101	TFLITE	float	Qualcomm® QCS8550 (Proxy)	26.657 ms	0 - 3 MB	NPU
DETR-ResNet101	TFLITE	float	Qualcomm® SA8775P	41.124 ms	0 - 400 MB	NPU
DETR-ResNet101	TFLITE	float	Qualcomm® QCS9075	41.507 ms	0 - 125 MB	NPU
DETR-ResNet101	TFLITE	float	Qualcomm® QCS8450 (Proxy)	54.877 ms	0 - 420 MB	NPU
DETR-ResNet101	TFLITE	float	Qualcomm® SA7255P	138.24 ms	0 - 403 MB	NPU
DETR-ResNet101	TFLITE	float	Qualcomm® SA8295P	43.769 ms	0 - 307 MB	NPU
DETR-ResNet101	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	15.264 ms	0 - 411 MB	NPU
DETR-ResNet101	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	11.203 ms	0 - 426 MB	NPU

License

• The license for the original implementation of DETR-ResNet101 can be found here.

References

• End-to-End Object Detection with Transformers
• 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.