Conditional-DETR-ResNet50: 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 Conditional-DETR-ResNet50 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 1.24.1	Download
ONNX	w8a16	Universal	QAIRT 2.42, ONNX Runtime 1.24.1	Download
QNN_DLC	float	Universal	QAIRT 2.43	Download
QNN_DLC	w8a16	Universal	QAIRT 2.43	Download
TFLITE	float	Universal	QAIRT 2.43, TFLite 2.17.0	Download

For more device-specific assets and performance metrics, visit Conditional-DETR-ResNet50 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 Conditional-DETR-ResNet50 on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.object_detection

Model Stats:

• Model checkpoint: ResNet50
• Input resolution: 480x480
• Number of parameters: 43.6M
• Model size (float): 166 MB

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
Conditional-DETR-ResNet50	ONNX	float	Snapdragon® X Elite	19.947 ms	81 - 81 MB	NPU
Conditional-DETR-ResNet50	ONNX	float	Snapdragon® 8 Gen 3 Mobile	14.9 ms	0 - 483 MB	NPU
Conditional-DETR-ResNet50	ONNX	float	Qualcomm® QCS8550 (Proxy)	19.711 ms	0 - 95 MB	NPU
Conditional-DETR-ResNet50	ONNX	float	Qualcomm® QCS9075	30.305 ms	5 - 12 MB	NPU
Conditional-DETR-ResNet50	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	11.03 ms	4 - 397 MB	NPU
Conditional-DETR-ResNet50	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	8.401 ms	5 - 405 MB	NPU
Conditional-DETR-ResNet50	ONNX	float	Snapdragon® X2 Elite	8.902 ms	82 - 82 MB	NPU
Conditional-DETR-ResNet50	QNN_DLC	float	Snapdragon® X Elite	23.157 ms	5 - 5 MB	NPU
Conditional-DETR-ResNet50	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	16.79 ms	0 - 428 MB	NPU
Conditional-DETR-ResNet50	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	98.036 ms	1 - 327 MB	NPU
Conditional-DETR-ResNet50	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	22.728 ms	5 - 8 MB	NPU
Conditional-DETR-ResNet50	QNN_DLC	float	Qualcomm® SA8775P	32.054 ms	0 - 325 MB	NPU
Conditional-DETR-ResNet50	QNN_DLC	float	Qualcomm® QCS9075	36.985 ms	5 - 11 MB	NPU
Conditional-DETR-ResNet50	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	46.556 ms	3 - 372 MB	NPU
Conditional-DETR-ResNet50	QNN_DLC	float	Qualcomm® SA7255P	98.036 ms	1 - 327 MB	NPU
Conditional-DETR-ResNet50	QNN_DLC	float	Qualcomm® SA8295P	34.228 ms	0 - 281 MB	NPU
Conditional-DETR-ResNet50	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	11.57 ms	5 - 341 MB	NPU
Conditional-DETR-ResNet50	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	8.777 ms	5 - 347 MB	NPU
Conditional-DETR-ResNet50	QNN_DLC	float	Snapdragon® X2 Elite	10.299 ms	5 - 5 MB	NPU
Conditional-DETR-ResNet50	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	16.962 ms	0 - 463 MB	NPU
Conditional-DETR-ResNet50	TFLITE	float	Qualcomm® QCS8275 (Proxy)	92.723 ms	0 - 363 MB	NPU
Conditional-DETR-ResNet50	TFLITE	float	Qualcomm® QCS8550 (Proxy)	22.327 ms	0 - 3 MB	NPU
Conditional-DETR-ResNet50	TFLITE	float	Qualcomm® SA8775P	138.15 ms	0 - 421 MB	NPU
Conditional-DETR-ResNet50	TFLITE	float	Qualcomm® QCS9075	33.268 ms	0 - 93 MB	NPU
Conditional-DETR-ResNet50	TFLITE	float	Qualcomm® QCS8450 (Proxy)	45.381 ms	0 - 405 MB	NPU
Conditional-DETR-ResNet50	TFLITE	float	Qualcomm® SA7255P	92.723 ms	0 - 363 MB	NPU
Conditional-DETR-ResNet50	TFLITE	float	Qualcomm® SA8295P	34.397 ms	0 - 310 MB	NPU
Conditional-DETR-ResNet50	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	11.883 ms	0 - 368 MB	NPU
Conditional-DETR-ResNet50	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	9.301 ms	0 - 378 MB	NPU

License

• The license for the original implementation of Conditional-DETR-ResNet50 can be found here.

References

• Conditional {DETR} for Fast Training Convergence
• 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.