ResNet101: Optimized for Qualcomm Devices

ResNet101 is a machine learning model that can classify images from the Imagenet dataset. It can also be used as a backbone in building more complex models for specific use cases.

This is based on the implementation of 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 2.42, ONNX Runtime 1.24.3	Download
ONNX	w8a8	Universal	QAIRT 2.42, ONNX Runtime 1.24.3	Download
QNN_DLC	float	Universal	QAIRT 2.43	Download
QNN_DLC	w8a8	Universal	QAIRT 2.43	Download
TFLITE	float	Universal	QAIRT 2.43, TFLite 2.19.1	Download
TFLITE	w8a8	Universal	QAIRT 2.43, TFLite 2.19.1	Download

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

Model Details

Model Type: Model_use_case.image_classification

Model Stats:

• Model checkpoint: Imagenet
• Input resolution: 224x224
• Number of parameters: 44.5M
• Model size (float): 170 MB
• Model size (w8a8): 43.9 MB

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
ResNet101	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	1.604 ms	1 - 78 MB	NPU
ResNet101	ONNX	float	Snapdragon® X2 Elite	1.619 ms	86 - 86 MB	NPU
ResNet101	ONNX	float	Snapdragon® X Elite	3.32 ms	85 - 85 MB	NPU
ResNet101	ONNX	float	Snapdragon® 8 Gen 3 Mobile	2.254 ms	0 - 132 MB	NPU
ResNet101	ONNX	float	Qualcomm® QCS8550 (Proxy)	3.083 ms	0 - 99 MB	NPU
ResNet101	ONNX	float	Qualcomm® QCS9075	5.149 ms	1 - 4 MB	NPU
ResNet101	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	1.885 ms	0 - 78 MB	NPU
ResNet101	ONNX	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.812 ms	0 - 79 MB	NPU
ResNet101	ONNX	w8a8	Snapdragon® X2 Elite	0.561 ms	43 - 43 MB	NPU
ResNet101	ONNX	w8a8	Snapdragon® X Elite	1.296 ms	43 - 43 MB	NPU
ResNet101	ONNX	w8a8	Snapdragon® 8 Gen 3 Mobile	0.979 ms	0 - 141 MB	NPU
ResNet101	ONNX	w8a8	Qualcomm® QCS6490	57.039 ms	8 - 56 MB	CPU
ResNet101	ONNX	w8a8	Qualcomm® QCS8550 (Proxy)	1.28 ms	0 - 68 MB	NPU
ResNet101	ONNX	w8a8	Qualcomm® QCS9075	1.331 ms	0 - 3 MB	NPU
ResNet101	ONNX	w8a8	Qualcomm® QCM6690	41.995 ms	9 - 20 MB	CPU
ResNet101	ONNX	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.841 ms	0 - 75 MB	NPU
ResNet101	ONNX	w8a8	Snapdragon® 7 Gen 4 Mobile	39.654 ms	10 - 21 MB	CPU
ResNet101	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	1.619 ms	0 - 68 MB	NPU
ResNet101	QNN_DLC	float	Snapdragon® X2 Elite	2.042 ms	1 - 1 MB	NPU
ResNet101	QNN_DLC	float	Snapdragon® X Elite	3.553 ms	1 - 1 MB	NPU
ResNet101	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	2.414 ms	1 - 128 MB	NPU
ResNet101	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	18.265 ms	1 - 66 MB	NPU
ResNet101	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	3.334 ms	1 - 2 MB	NPU
ResNet101	QNN_DLC	float	Qualcomm® SA8775P	5.415 ms	1 - 70 MB	NPU
ResNet101	QNN_DLC	float	Qualcomm® QCS9075	5.305 ms	1 - 3 MB	NPU
ResNet101	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	5.929 ms	0 - 90 MB	NPU
ResNet101	QNN_DLC	float	Qualcomm® SA7255P	18.265 ms	1 - 66 MB	NPU
ResNet101	QNN_DLC	float	Qualcomm® SA8295P	5.641 ms	1 - 43 MB	NPU
ResNet101	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	1.953 ms	1 - 70 MB	NPU
ResNet101	QNN_DLC	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.74 ms	0 - 73 MB	NPU
ResNet101	QNN_DLC	w8a8	Snapdragon® X2 Elite	0.765 ms	0 - 0 MB	NPU
ResNet101	QNN_DLC	w8a8	Snapdragon® X Elite	1.285 ms	0 - 0 MB	NPU
ResNet101	QNN_DLC	w8a8	Snapdragon® 8 Gen 3 Mobile	0.964 ms	0 - 121 MB	NPU
ResNet101	QNN_DLC	w8a8	Qualcomm® QCS6490	4.559 ms	0 - 2 MB	NPU
ResNet101	QNN_DLC	w8a8	Qualcomm® QCS8275 (Proxy)	2.976 ms	0 - 70 MB	NPU
ResNet101	QNN_DLC	w8a8	Qualcomm® QCS8550 (Proxy)	1.271 ms	0 - 2 MB	NPU
ResNet101	QNN_DLC	w8a8	Qualcomm® SA8775P	1.548 ms	0 - 72 MB	NPU
ResNet101	QNN_DLC	w8a8	Qualcomm® QCS9075	1.321 ms	0 - 2 MB	NPU
ResNet101	QNN_DLC	w8a8	Qualcomm® QCM6690	11.73 ms	0 - 196 MB	NPU
ResNet101	QNN_DLC	w8a8	Qualcomm® QCS8450 (Proxy)	1.783 ms	0 - 123 MB	NPU
ResNet101	QNN_DLC	w8a8	Qualcomm® SA7255P	2.976 ms	0 - 70 MB	NPU
ResNet101	QNN_DLC	w8a8	Qualcomm® SA8295P	1.946 ms	0 - 68 MB	NPU
ResNet101	QNN_DLC	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.804 ms	0 - 71 MB	NPU
ResNet101	QNN_DLC	w8a8	Snapdragon® 7 Gen 4 Mobile	1.808 ms	0 - 80 MB	NPU
ResNet101	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	1.628 ms	0 - 129 MB	NPU
ResNet101	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	2.391 ms	0 - 185 MB	NPU
ResNet101	TFLITE	float	Qualcomm® QCS8275 (Proxy)	18.2 ms	0 - 124 MB	NPU
ResNet101	TFLITE	float	Qualcomm® QCS8550 (Proxy)	3.317 ms	0 - 3 MB	NPU
ResNet101	TFLITE	float	Qualcomm® SA8775P	5.423 ms	0 - 126 MB	NPU
ResNet101	TFLITE	float	Qualcomm® QCS9075	5.285 ms	0 - 88 MB	NPU
ResNet101	TFLITE	float	Qualcomm® QCS8450 (Proxy)	5.923 ms	0 - 159 MB	NPU
ResNet101	TFLITE	float	Qualcomm® SA7255P	18.2 ms	0 - 124 MB	NPU
ResNet101	TFLITE	float	Qualcomm® SA8295P	5.593 ms	0 - 97 MB	NPU
ResNet101	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	1.923 ms	0 - 126 MB	NPU
ResNet101	TFLITE	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.697 ms	0 - 72 MB	NPU
ResNet101	TFLITE	w8a8	Snapdragon® 8 Gen 3 Mobile	0.86 ms	0 - 135 MB	NPU
ResNet101	TFLITE	w8a8	Qualcomm® QCS6490	4.402 ms	0 - 45 MB	NPU
ResNet101	TFLITE	w8a8	Qualcomm® QCS8275 (Proxy)	2.743 ms	0 - 70 MB	NPU
ResNet101	TFLITE	w8a8	Qualcomm® QCS8550 (Proxy)	1.134 ms	0 - 52 MB	NPU
ResNet101	TFLITE	w8a8	Qualcomm® SA8775P	1.429 ms	0 - 73 MB	NPU
ResNet101	TFLITE	w8a8	Qualcomm® QCS9075	1.186 ms	0 - 45 MB	NPU
ResNet101	TFLITE	w8a8	Qualcomm® QCM6690	11.69 ms	0 - 197 MB	NPU
ResNet101	TFLITE	w8a8	Qualcomm® QCS8450 (Proxy)	1.646 ms	0 - 139 MB	NPU
ResNet101	TFLITE	w8a8	Qualcomm® SA7255P	2.743 ms	0 - 70 MB	NPU
ResNet101	TFLITE	w8a8	Qualcomm® SA8295P	1.806 ms	0 - 69 MB	NPU
ResNet101	TFLITE	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.759 ms	0 - 73 MB	NPU
ResNet101	TFLITE	w8a8	Snapdragon® 7 Gen 4 Mobile	1.671 ms	0 - 78 MB	NPU

License

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

References

• Deep Residual Learning for Image Recognition
• 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.