You can deploy this model and start earning money today!

qualcomm/
DETR-ResNet101

Name: DETR-ResNet101
Availability: InStock

Views

No views yet

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 2.45, ONNX Runtime 1.27.1	Download
ONNX	w8a16_mixed_int16	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 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:

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

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
DETR-ResNet101	ONNX	float	Snapdragon® X2 Elite	12.729 ms	5 - 5 MB	NPU
DETR-ResNet101	ONNX	float	Snapdragon® X Elite	24.81 ms	114 - 114 MB	NPU
DETR-ResNet101	ONNX	float	Snapdragon® 8 Gen 3 Mobile	18.517 ms	0 - 454 MB	NPU
DETR-ResNet101	ONNX	float	Snapdragon® 8 Gen 1 Mobile	49.408 ms	1 - 362 MB	NPU
DETR-ResNet101	ONNX	float	Qualcomm® Dragonwing™ IQ-8275	42.659 ms	5 - 13 MB	NPU
DETR-ResNet101	ONNX	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	24.807 ms	0 - 127 MB	NPU
DETR-ResNet101	ONNX	float	Qualcomm® QCS8450	49.408 ms	1 - 362 MB	NPU
DETR-ResNet101	ONNX	float	Qualcomm® Dragonwing™ IQ-9075	39.407 ms	5 - 12 MB	NPU
DETR-ResNet101	ONNX	float	Qualcomm® Dragonwing™ IQ-X7181	24.81 ms	114 - 114 MB	NPU
DETR-ResNet101	ONNX	float	Qualcomm® Dragonwing™ Q-8750	14.482 ms	2 - 328 MB	NPU
DETR-ResNet101	ONNX	float	Snapdragon® 8 Elite Mobile	14.482 ms	2 - 328 MB	NPU
DETR-ResNet101	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	11.83 ms	3 - 341 MB	NPU
DETR-ResNet101	ONNX	w8a16_mixed_int16	Snapdragon® 8 Gen 3 Mobile	50.545 ms	8 - 459 MB	NPU
DETR-ResNet101	ONNX	w8a16_mixed_int16	Qualcomm® Dragonwing™ Q-8750	43.052 ms	22 - 323 MB	NPU
DETR-ResNet101	ONNX	w8a16_mixed_int16	Snapdragon® 8 Elite Mobile	43.052 ms	22 - 323 MB	NPU
DETR-ResNet101	ONNX	w8a16_mixed_int16	Snapdragon® 8 Elite Gen 5 Mobile	35.184 ms	20 - 367 MB	NPU
DETR-ResNet101	QNN_DLC	float	Snapdragon® X2 Elite	12.798 ms	5 - 5 MB	NPU
DETR-ResNet101	QNN_DLC	float	Snapdragon® X Elite	27.211 ms	5 - 5 MB	NPU
DETR-ResNet101	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	19.708 ms	4 - 438 MB	NPU
DETR-ResNet101	QNN_DLC	float	Snapdragon® 8 Gen 1 Mobile	56.768 ms	5 - 343 MB	NPU
DETR-ResNet101	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-8275	43.921 ms	5 - 12 MB	NPU
DETR-ResNet101	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-8275	138.048 ms	1 - 319 MB	NPU
DETR-ResNet101	QNN_DLC	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	26.687 ms	5 - 447 MB	NPU
DETR-ResNet101	QNN_DLC	float	Qualcomm® SA8775P	41.164 ms	1 - 318 MB	NPU
DETR-ResNet101	QNN_DLC	float	Qualcomm® SA8650P	41.164 ms	1 - 318 MB	NPU
DETR-ResNet101	QNN_DLC	float	Qualcomm® SA8255P	41.164 ms	1 - 318 MB	NPU
DETR-ResNet101	QNN_DLC	float	Qualcomm® QCS8450	56.768 ms	5 - 343 MB	NPU
DETR-ResNet101	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-9075	41.762 ms	5 - 11 MB	NPU
DETR-ResNet101	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-X7181	27.211 ms	5 - 5 MB	NPU
DETR-ResNet101	QNN_DLC	float	Qualcomm® Dragonwing™ Q-8750	15.247 ms	0 - 323 MB	NPU
DETR-ResNet101	QNN_DLC	float	Qualcomm® SA7255P	138.048 ms	1 - 319 MB	NPU
DETR-ResNet101	QNN_DLC	float	Qualcomm® SA8295P	43.217 ms	0 - 233 MB	NPU
DETR-ResNet101	QNN_DLC	float	Snapdragon® 8 Elite Mobile	15.247 ms	0 - 323 MB	NPU
DETR-ResNet101	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	11.062 ms	5 - 347 MB	NPU
DETR-ResNet101	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	19.805 ms	0 - 493 MB	NPU
DETR-ResNet101	TFLITE	float	Snapdragon® 8 Gen 1 Mobile	55.223 ms	0 - 387 MB	NPU
DETR-ResNet101	TFLITE	float	Qualcomm® Dragonwing™ IQ-8275	44.253 ms	0 - 126 MB	NPU
DETR-ResNet101	TFLITE	float	Qualcomm® Dragonwing™ IQ-8275	138.137 ms	0 - 367 MB	NPU
DETR-ResNet101	TFLITE	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	26.761 ms	0 - 10 MB	NPU
DETR-ResNet101	TFLITE	float	Qualcomm® SA8775P	41.198 ms	0 - 367 MB	NPU
DETR-ResNet101	TFLITE	float	Qualcomm® SA8650P	41.198 ms	0 - 367 MB	NPU
DETR-ResNet101	TFLITE	float	Qualcomm® SA8255P	41.198 ms	0 - 367 MB	NPU
DETR-ResNet101	TFLITE	float	Qualcomm® QCS8450	55.223 ms	0 - 387 MB	NPU
DETR-ResNet101	TFLITE	float	Qualcomm® Dragonwing™ IQ-9075	41.574 ms	0 - 125 MB	NPU
DETR-ResNet101	TFLITE	float	Qualcomm® Dragonwing™ Q-8750	15.117 ms	0 - 376 MB	NPU
DETR-ResNet101	TFLITE	float	Qualcomm® SA7255P	138.137 ms	0 - 367 MB	NPU
DETR-ResNet101	TFLITE	float	Qualcomm® SA8295P	43.348 ms	0 - 274 MB	NPU
DETR-ResNet101	TFLITE	float	Snapdragon® 8 Elite Mobile	15.117 ms	0 - 376 MB	NPU
DETR-ResNet101	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	11.069 ms	0 - 392 MB	NPU

License

The license for the original implementation of DETR-ResNet101 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