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 1.24.3	Download
ONNX	w8a16	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 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® 8 Elite Gen 5 Mobile	8.254 ms	5 - 334 MB	NPU
Conditional-DETR-ResNet50	ONNX	float	Snapdragon® 8 Elite Mobile	11.046 ms	3 - 329 MB	NPU
Conditional-DETR-ResNet50	ONNX	float	Snapdragon® X2 Elite	9.311 ms	82 - 82 MB	NPU
Conditional-DETR-ResNet50	ONNX	float	Snapdragon® X Elite	20.279 ms	81 - 81 MB	NPU
Conditional-DETR-ResNet50	ONNX	float	Snapdragon® X Elite	20.279 ms	81 - 81 MB	NPU
Conditional-DETR-ResNet50	ONNX	float	Snapdragon® 8 Gen 3 Mobile	15.036 ms	0 - 459 MB	NPU
Conditional-DETR-ResNet50	ONNX	float	Qualcomm® QCS8550 (Proxy)	20.047 ms	0 - 95 MB	NPU
Conditional-DETR-ResNet50	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	11.046 ms	3 - 329 MB	NPU
Conditional-DETR-ResNet50	ONNX	float	Qualcomm® QCS9075	30.052 ms	5 - 12 MB	NPU
Conditional-DETR-ResNet50	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	13.144 ms	5 - 353 MB	NPU
Conditional-DETR-ResNet50	QNN_DLC	float	Snapdragon® 8 Elite Mobile	14.834 ms	0 - 339 MB	NPU
Conditional-DETR-ResNet50	QNN_DLC	float	Snapdragon® X2 Elite	12.818 ms	5 - 5 MB	NPU
Conditional-DETR-ResNet50	QNN_DLC	float	Snapdragon® X Elite	25.945 ms	5 - 5 MB	NPU
Conditional-DETR-ResNet50	QNN_DLC	float	Snapdragon® X Elite	25.945 ms	5 - 5 MB	NPU
Conditional-DETR-ResNet50	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	19.833 ms	5 - 471 MB	NPU
Conditional-DETR-ResNet50	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	26.355 ms	5 - 421 MB	NPU
Conditional-DETR-ResNet50	QNN_DLC	float	Qualcomm® SA8775P	35.321 ms	1 - 349 MB	NPU
Conditional-DETR-ResNet50	QNN_DLC	float	Qualcomm® SA8775P	35.321 ms	1 - 349 MB	NPU
Conditional-DETR-ResNet50	QNN_DLC	float	Qualcomm® SA8775P	35.321 ms	1 - 349 MB	NPU
Conditional-DETR-ResNet50	QNN_DLC	float	Qualcomm® SA7255P	103.025 ms	1 - 345 MB	NPU
Conditional-DETR-ResNet50	QNN_DLC	float	Qualcomm® SA8295P	38.483 ms	0 - 300 MB	NPU
Conditional-DETR-ResNet50	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	14.834 ms	0 - 339 MB	NPU
Conditional-DETR-ResNet50	QNN_DLC	float	Qualcomm® QCS9075	41.944 ms	5 - 11 MB	NPU
Conditional-DETR-ResNet50	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	50.843 ms	3 - 409 MB	NPU
Conditional-DETR-ResNet50	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	8.992 ms	0 - 350 MB	NPU
Conditional-DETR-ResNet50	TFLITE	float	Snapdragon® 8 Elite Mobile	11.798 ms	0 - 341 MB	NPU
Conditional-DETR-ResNet50	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	16.331 ms	0 - 431 MB	NPU
Conditional-DETR-ResNet50	TFLITE	float	Qualcomm® QCS8550 (Proxy)	22.546 ms	0 - 3 MB	NPU
Conditional-DETR-ResNet50	TFLITE	float	Qualcomm® SA8775P	29.699 ms	0 - 370 MB	NPU
Conditional-DETR-ResNet50	TFLITE	float	Qualcomm® SA8775P	29.699 ms	0 - 370 MB	NPU
Conditional-DETR-ResNet50	TFLITE	float	Qualcomm® SA8775P	29.699 ms	0 - 370 MB	NPU
Conditional-DETR-ResNet50	TFLITE	float	Qualcomm® SA7255P	92.873 ms	0 - 335 MB	NPU
Conditional-DETR-ResNet50	TFLITE	float	Qualcomm® SA8295P	34.343 ms	0 - 283 MB	NPU
Conditional-DETR-ResNet50	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	11.798 ms	0 - 341 MB	NPU
Conditional-DETR-ResNet50	TFLITE	float	Qualcomm® QCS9075	33.126 ms	0 - 93 MB	NPU
Conditional-DETR-ResNet50	TFLITE	float	Qualcomm® QCS8450 (Proxy)	41.873 ms	0 - 375 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.