You can deploy this model and start earning money today!

qualcomm/
DETR-ResNet101-DC5

Name: DETR-ResNet101-DC5
Availability: InStock

Views

No views yet

DETR-ResNet101-DC5: 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-DC5 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 DETR-ResNet101-DC5 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-DC5 on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.object_detection

Model Stats:

Input resolution: 480x480
Model checkpoint: ResNet101-DC5
Model size (float): 232 MB

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
DETR-ResNet101-DC5	ONNX	float	Snapdragon® X2 Elite	23.641 ms	5 - 5 MB	NPU
DETR-ResNet101-DC5	ONNX	float	Snapdragon® X Elite	51.446 ms	116 - 116 MB	NPU
DETR-ResNet101-DC5	ONNX	float	Snapdragon® 8 Gen 3 Mobile	36.547 ms	3 - 568 MB	NPU
DETR-ResNet101-DC5	ONNX	float	Snapdragon® 8 Gen 1 Mobile	84.579 ms	6 - 481 MB	NPU
DETR-ResNet101-DC5	ONNX	float	Qualcomm® Dragonwing™ IQ-8275	72.658 ms	5 - 13 MB	NPU
DETR-ResNet101-DC5	ONNX	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	49.76 ms	0 - 126 MB	NPU
DETR-ResNet101-DC5	ONNX	float	Qualcomm® QCS8450	84.579 ms	6 - 481 MB	NPU
DETR-ResNet101-DC5	ONNX	float	Qualcomm® Dragonwing™ IQ-9075	69.461 ms	5 - 12 MB	NPU
DETR-ResNet101-DC5	ONNX	float	Qualcomm® Dragonwing™ IQ-X7181	51.446 ms	116 - 116 MB	NPU
DETR-ResNet101-DC5	ONNX	float	Qualcomm® Dragonwing™ Q-8750	27.213 ms	1 - 434 MB	NPU
DETR-ResNet101-DC5	ONNX	float	Snapdragon® 8 Elite Mobile	27.213 ms	1 - 434 MB	NPU
DETR-ResNet101-DC5	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	21.732 ms	3 - 445 MB	NPU
DETR-ResNet101-DC5	QNN_DLC	float	Snapdragon® X2 Elite	24.907 ms	5 - 5 MB	NPU
DETR-ResNet101-DC5	QNN_DLC	float	Snapdragon® X Elite	53.285 ms	5 - 5 MB	NPU
DETR-ResNet101-DC5	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	37.52 ms	0 - 550 MB	NPU
DETR-ResNet101-DC5	QNN_DLC	float	Snapdragon® 8 Gen 1 Mobile	108.415 ms	3 - 467 MB	NPU
DETR-ResNet101-DC5	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-8275	73.425 ms	5 - 12 MB	NPU
DETR-ResNet101-DC5	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-8275	220.242 ms	1 - 427 MB	NPU
DETR-ResNet101-DC5	QNN_DLC	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	51.206 ms	5 - 7 MB	NPU
DETR-ResNet101-DC5	QNN_DLC	float	Qualcomm® SA8775P	69.894 ms	1 - 426 MB	NPU
DETR-ResNet101-DC5	QNN_DLC	float	Qualcomm® SA8650P	69.894 ms	1 - 426 MB	NPU
DETR-ResNet101-DC5	QNN_DLC	float	Qualcomm® SA8255P	69.894 ms	1 - 426 MB	NPU
DETR-ResNet101-DC5	QNN_DLC	float	Qualcomm® QCS8450	108.415 ms	3 - 467 MB	NPU
DETR-ResNet101-DC5	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-9075	70.474 ms	5 - 11 MB	NPU
DETR-ResNet101-DC5	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-X7181	53.285 ms	5 - 5 MB	NPU
DETR-ResNet101-DC5	QNN_DLC	float	Qualcomm® Dragonwing™ Q-8750	28.061 ms	0 - 448 MB	NPU
DETR-ResNet101-DC5	QNN_DLC	float	Qualcomm® SA7255P	220.242 ms	1 - 427 MB	NPU
DETR-ResNet101-DC5	QNN_DLC	float	Qualcomm® SA8295P	86.061 ms	0 - 341 MB	NPU
DETR-ResNet101-DC5	QNN_DLC	float	Snapdragon® 8 Elite Mobile	28.061 ms	0 - 448 MB	NPU
DETR-ResNet101-DC5	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	22.654 ms	5 - 450 MB	NPU
DETR-ResNet101-DC5	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	37.358 ms	0 - 606 MB	NPU
DETR-ResNet101-DC5	TFLITE	float	Snapdragon® 8 Gen 1 Mobile	84.676 ms	1 - 477 MB	NPU
DETR-ResNet101-DC5	TFLITE	float	Qualcomm® Dragonwing™ IQ-8275	73.179 ms	0 - 127 MB	NPU
DETR-ResNet101-DC5	TFLITE	float	Qualcomm® Dragonwing™ IQ-8275	219.471 ms	0 - 471 MB	NPU
DETR-ResNet101-DC5	TFLITE	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	50.593 ms	0 - 3 MB	NPU
DETR-ResNet101-DC5	TFLITE	float	Qualcomm® SA8775P	69.578 ms	0 - 470 MB	NPU
DETR-ResNet101-DC5	TFLITE	float	Qualcomm® SA8650P	69.578 ms	0 - 470 MB	NPU
DETR-ResNet101-DC5	TFLITE	float	Qualcomm® SA8255P	69.578 ms	0 - 470 MB	NPU
DETR-ResNet101-DC5	TFLITE	float	Qualcomm® QCS8450	84.676 ms	1 - 477 MB	NPU
DETR-ResNet101-DC5	TFLITE	float	Qualcomm® Dragonwing™ IQ-9075	69.703 ms	0 - 126 MB	NPU
DETR-ResNet101-DC5	TFLITE	float	Qualcomm® Dragonwing™ Q-8750	28.041 ms	0 - 477 MB	NPU
DETR-ResNet101-DC5	TFLITE	float	Qualcomm® SA7255P	219.471 ms	0 - 471 MB	NPU
DETR-ResNet101-DC5	TFLITE	float	Qualcomm® SA8295P	76.591 ms	0 - 358 MB	NPU
DETR-ResNet101-DC5	TFLITE	float	Snapdragon® 8 Elite Mobile	28.041 ms	0 - 477 MB	NPU
DETR-ResNet101-DC5	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	22.347 ms	0 - 495 MB	NPU

License

The license for the original implementation of DETR-ResNet101-DC5 can be found here.

References

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.

qualcomm/DETR-ResNet101-DC5