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 1.24.1	Download
ONNX	w8a8	Universal	QAIRT 2.42, ONNX Runtime 1.24.1	Download
QNN_DLC	float	Universal	QAIRT 2.43	Download
QNN_DLC	w8a8	Universal	QAIRT 2.43	Download
TFLITE	float	Universal	QAIRT 2.43, TFLite 2.17.0	Download
TFLITE	w8a8	Universal	QAIRT 2.43, TFLite 2.17.0	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	1.607 ms	1 - 77 MB	NPU
ResNet101	ONNX	float	Snapdragon® X2 Elite	1.631 ms	86 - 86 MB	NPU
ResNet101	ONNX	float	Snapdragon® X Elite	3.315 ms	85 - 85 MB	NPU
ResNet101	ONNX	float	Snapdragon® 8 Gen 3 Mobile	2.239 ms	0 - 130 MB	NPU
ResNet101	ONNX	float	Qualcomm® QCS8550 (Proxy)	3.099 ms	0 - 109 MB	NPU
ResNet101	ONNX	float	Qualcomm® QCS9075	5.14 ms	1 - 4 MB	NPU
ResNet101	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	1.856 ms	0 - 75 MB	NPU
ResNet101	ONNX	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.801 ms	0 - 76 MB	NPU
ResNet101	ONNX	w8a8	Snapdragon® X2 Elite	0.565 ms	43 - 43 MB	NPU
ResNet101	ONNX	w8a8	Snapdragon® X Elite	1.293 ms	43 - 43 MB	NPU
ResNet101	ONNX	w8a8	Snapdragon® 8 Gen 3 Mobile	0.975 ms	0 - 141 MB	NPU
ResNet101	ONNX	w8a8	Qualcomm® QCS6490	55.571 ms	9 - 57 MB	CPU
ResNet101	ONNX	w8a8	Qualcomm® QCS8550 (Proxy)	1.283 ms	0 - 51 MB	NPU
ResNet101	ONNX	w8a8	Qualcomm® QCS9075	1.336 ms	0 - 3 MB	NPU
ResNet101	ONNX	w8a8	Qualcomm® QCM6690	42.049 ms	10 - 21 MB	CPU
ResNet101	ONNX	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.839 ms	0 - 75 MB	NPU
ResNet101	ONNX	w8a8	Snapdragon® 7 Gen 4 Mobile	39.574 ms	9 - 20 MB	CPU
ResNet101	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	1.623 ms	1 - 69 MB	NPU
ResNet101	QNN_DLC	float	Snapdragon® X2 Elite	1.987 ms	1 - 1 MB	NPU
ResNet101	QNN_DLC	float	Snapdragon® X Elite	3.563 ms	1 - 1 MB	NPU
ResNet101	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	2.428 ms	1 - 126 MB	NPU
ResNet101	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	18.259 ms	1 - 67 MB	NPU
ResNet101	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	3.329 ms	0 - 4 MB	NPU
ResNet101	QNN_DLC	float	Qualcomm® SA8775P	5.41 ms	1 - 70 MB	NPU
ResNet101	QNN_DLC	float	Qualcomm® QCS9075	5.304 ms	3 - 5 MB	NPU
ResNet101	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	5.923 ms	0 - 91 MB	NPU
ResNet101	QNN_DLC	float	Qualcomm® SA7255P	18.259 ms	1 - 67 MB	NPU
ResNet101	QNN_DLC	float	Qualcomm® SA8295P	5.648 ms	1 - 43 MB	NPU
ResNet101	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	1.959 ms	0 - 67 MB	NPU
ResNet101	QNN_DLC	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.741 ms	0 - 73 MB	NPU
ResNet101	QNN_DLC	w8a8	Snapdragon® X2 Elite	0.619 ms	0 - 0 MB	NPU
ResNet101	QNN_DLC	w8a8	Snapdragon® X Elite	1.28 ms	0 - 0 MB	NPU
ResNet101	QNN_DLC	w8a8	Snapdragon® 8 Gen 3 Mobile	0.986 ms	0 - 124 MB	NPU
ResNet101	QNN_DLC	w8a8	Qualcomm® QCS6490	4.535 ms	0 - 2 MB	NPU
ResNet101	QNN_DLC	w8a8	Qualcomm® QCS8275 (Proxy)	2.969 ms	0 - 70 MB	NPU
ResNet101	QNN_DLC	w8a8	Qualcomm® QCS8550 (Proxy)	1.261 ms	0 - 2 MB	NPU
ResNet101	QNN_DLC	w8a8	Qualcomm® SA8775P	5.605 ms	0 - 70 MB	NPU
ResNet101	QNN_DLC	w8a8	Qualcomm® QCS9075	1.325 ms	2 - 4 MB	NPU
ResNet101	QNN_DLC	w8a8	Qualcomm® QCM6690	11.643 ms	0 - 197 MB	NPU
ResNet101	QNN_DLC	w8a8	Qualcomm® QCS8450 (Proxy)	1.772 ms	0 - 121 MB	NPU
ResNet101	QNN_DLC	w8a8	Qualcomm® SA7255P	2.969 ms	0 - 70 MB	NPU
ResNet101	QNN_DLC	w8a8	Qualcomm® SA8295P	1.952 ms	0 - 68 MB	NPU
ResNet101	QNN_DLC	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.797 ms	0 - 71 MB	NPU
ResNet101	QNN_DLC	w8a8	Snapdragon® 7 Gen 4 Mobile	1.805 ms	0 - 80 MB	NPU
ResNet101	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	1.629 ms	0 - 127 MB	NPU
ResNet101	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	2.405 ms	0 - 190 MB	NPU
ResNet101	TFLITE	float	Qualcomm® QCS8275 (Proxy)	18.205 ms	0 - 124 MB	NPU
ResNet101	TFLITE	float	Qualcomm® QCS8550 (Proxy)	3.3 ms	0 - 3 MB	NPU
ResNet101	TFLITE	float	Qualcomm® SA8775P	5.443 ms	0 - 123 MB	NPU
ResNet101	TFLITE	float	Qualcomm® QCS9075	5.29 ms	0 - 88 MB	NPU
ResNet101	TFLITE	float	Qualcomm® QCS8450 (Proxy)	5.887 ms	0 - 159 MB	NPU
ResNet101	TFLITE	float	Qualcomm® SA7255P	18.205 ms	0 - 124 MB	NPU
ResNet101	TFLITE	float	Qualcomm® SA8295P	5.581 ms	0 - 96 MB	NPU
ResNet101	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	1.922 ms	0 - 117 MB	NPU
ResNet101	TFLITE	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.695 ms	0 - 70 MB	NPU
ResNet101	TFLITE	w8a8	Snapdragon® 8 Gen 3 Mobile	0.858 ms	0 - 132 MB	NPU
ResNet101	TFLITE	w8a8	Qualcomm® QCS6490	4.196 ms	0 - 45 MB	NPU
ResNet101	TFLITE	w8a8	Qualcomm® QCS8275 (Proxy)	2.759 ms	0 - 69 MB	NPU
ResNet101	TFLITE	w8a8	Qualcomm® QCS8550 (Proxy)	1.134 ms	0 - 2 MB	NPU
ResNet101	TFLITE	w8a8	Qualcomm® SA8775P	1.441 ms	0 - 71 MB	NPU
ResNet101	TFLITE	w8a8	Qualcomm® QCS9075	1.181 ms	0 - 45 MB	NPU
ResNet101	TFLITE	w8a8	Qualcomm® QCM6690	11.747 ms	0 - 190 MB	NPU
ResNet101	TFLITE	w8a8	Qualcomm® QCS8450 (Proxy)	1.645 ms	0 - 134 MB	NPU
ResNet101	TFLITE	w8a8	Qualcomm® SA7255P	2.759 ms	0 - 69 MB	NPU
ResNet101	TFLITE	w8a8	Qualcomm® SA8295P	1.797 ms	0 - 67 MB	NPU
ResNet101	TFLITE	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.737 ms	0 - 70 MB	NPU
ResNet101	TFLITE	w8a8	Snapdragon® 7 Gen 4 Mobile	1.669 ms	0 - 76 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.