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 2.45	Download
QNN_DLC	w8a8	Universal	QAIRT 2.45	Download
TFLITE	float	Universal	QAIRT 2.45	Download
TFLITE	w8a8	Universal	QAIRT 2.45	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 - 78 MB	NPU
ResNet101	ONNX	float	Snapdragon® 8 Elite Mobile	1.874 ms	0 - 78 MB	NPU
ResNet101	ONNX	float	Snapdragon® X2 Elite	1.622 ms	86 - 86 MB	NPU
ResNet101	ONNX	float	Snapdragon® X Elite	3.296 ms	85 - 85 MB	NPU
ResNet101	ONNX	float	Snapdragon® X Elite	3.296 ms	85 - 85 MB	NPU
ResNet101	ONNX	float	Snapdragon® 8 Gen 3 Mobile	2.237 ms	0 - 131 MB	NPU
ResNet101	ONNX	float	Qualcomm® QCS8550 (Proxy)	3.127 ms	0 - 57 MB	NPU
ResNet101	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	1.874 ms	0 - 78 MB	NPU
ResNet101	ONNX	float	Qualcomm® QCS9075	5.127 ms	0 - 4 MB	NPU
ResNet101	ONNX	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.805 ms	0 - 76 MB	NPU
ResNet101	ONNX	w8a8	Snapdragon® 8 Elite Mobile	0.839 ms	0 - 75 MB	NPU
ResNet101	ONNX	w8a8	Snapdragon® X2 Elite	0.561 ms	43 - 43 MB	NPU
ResNet101	ONNX	w8a8	Snapdragon® X Elite	1.29 ms	43 - 43 MB	NPU
ResNet101	ONNX	w8a8	Snapdragon® X Elite	1.29 ms	43 - 43 MB	NPU
ResNet101	ONNX	w8a8	Snapdragon® 8 Gen 3 Mobile	0.972 ms	0 - 140 MB	NPU
ResNet101	ONNX	w8a8	Qualcomm® QCS6490	57.059 ms	9 - 57 MB	CPU
ResNet101	ONNX	w8a8	Qualcomm® QCS8550 (Proxy)	1.281 ms	0 - 53 MB	NPU
ResNet101	ONNX	w8a8	Snapdragon® 7 Gen 4 Mobile	39.553 ms	8 - 19 MB	CPU
ResNet101	ONNX	w8a8	Qualcomm® QCM6690	42.426 ms	11 - 22 MB	CPU
ResNet101	ONNX	w8a8	Qualcomm® QCS9075	1.337 ms	0 - 3 MB	NPU
ResNet101	ONNX	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.839 ms	0 - 75 MB	NPU
ResNet101	ONNX	w8a8	Snapdragon® 7 Gen 4 Mobile	39.553 ms	8 - 19 MB	CPU
ResNet101	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	1.637 ms	1 - 67 MB	NPU
ResNet101	QNN_DLC	float	Snapdragon® 8 Elite Mobile	1.956 ms	1 - 66 MB	NPU
ResNet101	QNN_DLC	float	Snapdragon® X2 Elite	1.938 ms	1 - 1 MB	NPU
ResNet101	QNN_DLC	float	Snapdragon® X Elite	3.524 ms	1 - 1 MB	NPU
ResNet101	QNN_DLC	float	Snapdragon® X Elite	3.524 ms	1 - 1 MB	NPU
ResNet101	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	2.416 ms	0 - 119 MB	NPU
ResNet101	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	3.341 ms	1 - 9 MB	NPU
ResNet101	QNN_DLC	float	Qualcomm® SA8775P	5.428 ms	1 - 67 MB	NPU
ResNet101	QNN_DLC	float	Qualcomm® SA8775P	5.428 ms	1 - 67 MB	NPU
ResNet101	QNN_DLC	float	Qualcomm® SA8775P	5.428 ms	1 - 67 MB	NPU
ResNet101	QNN_DLC	float	Qualcomm® SA7255P	18.345 ms	1 - 65 MB	NPU
ResNet101	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	5.94 ms	0 - 89 MB	NPU
ResNet101	QNN_DLC	float	Qualcomm® SA8295P	5.6 ms	0 - 35 MB	NPU
ResNet101	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	1.956 ms	1 - 66 MB	NPU
ResNet101	QNN_DLC	float	Qualcomm® QCS9075	5.283 ms	1 - 3 MB	NPU
ResNet101	QNN_DLC	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.736 ms	0 - 77 MB	NPU
ResNet101	QNN_DLC	w8a8	Snapdragon® 8 Elite Mobile	0.786 ms	0 - 75 MB	NPU
ResNet101	QNN_DLC	w8a8	Snapdragon® X2 Elite	0.641 ms	0 - 0 MB	NPU
ResNet101	QNN_DLC	w8a8	Snapdragon® X Elite	1.286 ms	0 - 0 MB	NPU
ResNet101	QNN_DLC	w8a8	Snapdragon® X Elite	1.286 ms	0 - 0 MB	NPU
ResNet101	QNN_DLC	w8a8	Snapdragon® 8 Gen 3 Mobile	0.966 ms	0 - 120 MB	NPU
ResNet101	QNN_DLC	w8a8	Qualcomm® QCS6490	4.51 ms	0 - 2 MB	NPU
ResNet101	QNN_DLC	w8a8	Qualcomm® QCS8550 (Proxy)	1.271 ms	0 - 115 MB	NPU
ResNet101	QNN_DLC	w8a8	Qualcomm® SA8775P	1.529 ms	0 - 74 MB	NPU
ResNet101	QNN_DLC	w8a8	Qualcomm® SA8775P	1.529 ms	0 - 74 MB	NPU
ResNet101	QNN_DLC	w8a8	Qualcomm® SA8775P	1.529 ms	0 - 74 MB	NPU
ResNet101	QNN_DLC	w8a8	Snapdragon® 7 Gen 4 Mobile	1.793 ms	0 - 83 MB	NPU
ResNet101	QNN_DLC	w8a8	Qualcomm® QCM6690	11.697 ms	0 - 195 MB	NPU
ResNet101	QNN_DLC	w8a8	Qualcomm® QCS9075	1.318 ms	2 - 4 MB	NPU
ResNet101	QNN_DLC	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.786 ms	0 - 75 MB	NPU
ResNet101	QNN_DLC	w8a8	Qualcomm® QCS8450 (Proxy)	1.78 ms	0 - 124 MB	NPU
ResNet101	QNN_DLC	w8a8	Qualcomm® SA7255P	3.009 ms	0 - 72 MB	NPU
ResNet101	QNN_DLC	w8a8	Qualcomm® SA8295P	1.946 ms	0 - 71 MB	NPU
ResNet101	QNN_DLC	w8a8	Snapdragon® 7 Gen 4 Mobile	1.793 ms	0 - 83 MB	NPU
ResNet101	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	1.615 ms	0 - 112 MB	NPU
ResNet101	TFLITE	float	Snapdragon® 8 Elite Mobile	1.91 ms	0 - 112 MB	NPU
ResNet101	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	2.377 ms	0 - 173 MB	NPU
ResNet101	TFLITE	float	Qualcomm® QCS8550 (Proxy)	3.35 ms	0 - 2 MB	NPU
ResNet101	TFLITE	float	Qualcomm® SA8775P	5.431 ms	0 - 111 MB	NPU
ResNet101	TFLITE	float	Qualcomm® SA8775P	5.431 ms	0 - 111 MB	NPU
ResNet101	TFLITE	float	Qualcomm® SA8775P	5.431 ms	0 - 111 MB	NPU
ResNet101	TFLITE	float	Qualcomm® SA7255P	18.244 ms	0 - 107 MB	NPU
ResNet101	TFLITE	float	Qualcomm® QCS8450 (Proxy)	5.914 ms	0 - 145 MB	NPU
ResNet101	TFLITE	float	Qualcomm® SA8295P	5.551 ms	0 - 82 MB	NPU
ResNet101	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	1.91 ms	0 - 112 MB	NPU
ResNet101	TFLITE	float	Qualcomm® QCS9075	5.303 ms	0 - 88 MB	NPU
ResNet101	TFLITE	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.695 ms	0 - 74 MB	NPU
ResNet101	TFLITE	w8a8	Snapdragon® 8 Elite Mobile	0.737 ms	0 - 74 MB	NPU
ResNet101	TFLITE	w8a8	Snapdragon® 8 Gen 3 Mobile	0.864 ms	0 - 132 MB	NPU
ResNet101	TFLITE	w8a8	Qualcomm® QCS6490	4.341 ms	0 - 45 MB	NPU
ResNet101	TFLITE	w8a8	Qualcomm® QCS8550 (Proxy)	1.139 ms	0 - 2 MB	NPU
ResNet101	TFLITE	w8a8	Qualcomm® SA8775P	1.403 ms	0 - 74 MB	NPU
ResNet101	TFLITE	w8a8	Qualcomm® SA8775P	1.403 ms	0 - 74 MB	NPU
ResNet101	TFLITE	w8a8	Qualcomm® SA8775P	1.403 ms	0 - 74 MB	NPU
ResNet101	TFLITE	w8a8	Snapdragon® 7 Gen 4 Mobile	1.666 ms	0 - 78 MB	NPU
ResNet101	TFLITE	w8a8	Qualcomm® QCM6690	12.435 ms	0 - 191 MB	NPU
ResNet101	TFLITE	w8a8	Qualcomm® QCS9075	1.189 ms	0 - 45 MB	NPU
ResNet101	TFLITE	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.737 ms	0 - 74 MB	NPU
ResNet101	TFLITE	w8a8	Qualcomm® QCS8450 (Proxy)	1.651 ms	0 - 134 MB	NPU
ResNet101	TFLITE	w8a8	Qualcomm® SA7255P	2.756 ms	0 - 71 MB	NPU
ResNet101	TFLITE	w8a8	Qualcomm® SA8295P	1.857 ms	0 - 68 MB	NPU
ResNet101	TFLITE	w8a8	Snapdragon® 7 Gen 4 Mobile	1.666 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.