GoogLeNet: Optimized for Qualcomm Devices

GoogLeNet 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 GoogLeNet 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 GoogLeNet 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 GoogLeNet 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: 6.62M
• Model size (float): 25.3 MB
• Model size (w8a8): 6.54 MB

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
GoogLeNet	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	0.394 ms	0 - 31 MB	NPU
GoogLeNet	ONNX	float	Snapdragon® 8 Elite Mobile	0.477 ms	0 - 31 MB	NPU
GoogLeNet	ONNX	float	Snapdragon® X2 Elite	0.415 ms	13 - 13 MB	NPU
GoogLeNet	ONNX	float	Snapdragon® X Elite	0.985 ms	13 - 13 MB	NPU
GoogLeNet	ONNX	float	Snapdragon® X Elite	0.985 ms	13 - 13 MB	NPU
GoogLeNet	ONNX	float	Snapdragon® 8 Gen 3 Mobile	0.566 ms	0 - 46 MB	NPU
GoogLeNet	ONNX	float	Qualcomm® QCS8550 (Proxy)	0.842 ms	0 - 11 MB	NPU
GoogLeNet	ONNX	float	Qualcomm® QCS9075	1.547 ms	1 - 3 MB	NPU
GoogLeNet	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	0.477 ms	0 - 31 MB	NPU
GoogLeNet	ONNX	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.182 ms	0 - 34 MB	NPU
GoogLeNet	ONNX	w8a8	Snapdragon® 8 Elite Mobile	0.192 ms	0 - 30 MB	NPU
GoogLeNet	ONNX	w8a8	Snapdragon® X2 Elite	0.166 ms	7 - 7 MB	NPU
GoogLeNet	ONNX	w8a8	Snapdragon® X Elite	0.418 ms	7 - 7 MB	NPU
GoogLeNet	ONNX	w8a8	Snapdragon® X Elite	0.418 ms	7 - 7 MB	NPU
GoogLeNet	ONNX	w8a8	Snapdragon® 8 Gen 3 Mobile	0.229 ms	0 - 49 MB	NPU
GoogLeNet	ONNX	w8a8	Qualcomm® QCS6490	13.788 ms	7 - 17 MB	CPU
GoogLeNet	ONNX	w8a8	Qualcomm® QCS8550 (Proxy)	0.304 ms	0 - 9 MB	NPU
GoogLeNet	ONNX	w8a8	Qualcomm® QCS9075	0.432 ms	0 - 3 MB	NPU
GoogLeNet	ONNX	w8a8	Qualcomm® QCM6690	9.31 ms	6 - 15 MB	CPU
GoogLeNet	ONNX	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.192 ms	0 - 30 MB	NPU
GoogLeNet	ONNX	w8a8	Snapdragon® 7 Gen 4 Mobile	7.139 ms	7 - 16 MB	CPU
GoogLeNet	ONNX	w8a8	Snapdragon® 7 Gen 4 Mobile	7.139 ms	7 - 16 MB	CPU
GoogLeNet	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	0.374 ms	1 - 31 MB	NPU
GoogLeNet	QNN_DLC	float	Snapdragon® 8 Elite Mobile	0.453 ms	0 - 31 MB	NPU
GoogLeNet	QNN_DLC	float	Snapdragon® X2 Elite	0.528 ms	1 - 1 MB	NPU
GoogLeNet	QNN_DLC	float	Snapdragon® X Elite	0.986 ms	1 - 1 MB	NPU
GoogLeNet	QNN_DLC	float	Snapdragon® X Elite	0.986 ms	1 - 1 MB	NPU
GoogLeNet	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	0.56 ms	0 - 43 MB	NPU
GoogLeNet	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	5.009 ms	1 - 25 MB	NPU
GoogLeNet	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	0.814 ms	1 - 2 MB	NPU
GoogLeNet	QNN_DLC	float	Qualcomm® SA8775P	1.543 ms	1 - 29 MB	NPU
GoogLeNet	QNN_DLC	float	Qualcomm® SA8775P	1.543 ms	1 - 29 MB	NPU
GoogLeNet	QNN_DLC	float	Qualcomm® SA8775P	1.543 ms	1 - 29 MB	NPU
GoogLeNet	QNN_DLC	float	Qualcomm® QCS9075	1.514 ms	3 - 5 MB	NPU
GoogLeNet	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	1.752 ms	0 - 45 MB	NPU
GoogLeNet	QNN_DLC	float	Qualcomm® SA7255P	5.009 ms	1 - 25 MB	NPU
GoogLeNet	QNN_DLC	float	Qualcomm® SA8295P	1.804 ms	0 - 24 MB	NPU
GoogLeNet	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	0.453 ms	0 - 31 MB	NPU
GoogLeNet	QNN_DLC	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.144 ms	0 - 32 MB	NPU
GoogLeNet	QNN_DLC	w8a8	Snapdragon® 8 Elite Mobile	0.156 ms	0 - 33 MB	NPU
GoogLeNet	QNN_DLC	w8a8	Snapdragon® X2 Elite	0.217 ms	0 - 0 MB	NPU
GoogLeNet	QNN_DLC	w8a8	Snapdragon® X Elite	0.351 ms	0 - 0 MB	NPU
GoogLeNet	QNN_DLC	w8a8	Snapdragon® X Elite	0.351 ms	0 - 0 MB	NPU
GoogLeNet	QNN_DLC	w8a8	Snapdragon® 8 Gen 3 Mobile	0.185 ms	0 - 43 MB	NPU
GoogLeNet	QNN_DLC	w8a8	Qualcomm® QCS6490	1.029 ms	0 - 2 MB	NPU
GoogLeNet	QNN_DLC	w8a8	Qualcomm® QCS8275 (Proxy)	0.793 ms	0 - 28 MB	NPU
GoogLeNet	QNN_DLC	w8a8	Qualcomm® QCS8550 (Proxy)	0.245 ms	0 - 1 MB	NPU
GoogLeNet	QNN_DLC	w8a8	Qualcomm® SA8775P	0.404 ms	0 - 30 MB	NPU
GoogLeNet	QNN_DLC	w8a8	Qualcomm® SA8775P	0.404 ms	0 - 30 MB	NPU
GoogLeNet	QNN_DLC	w8a8	Qualcomm® SA8775P	0.404 ms	0 - 30 MB	NPU
GoogLeNet	QNN_DLC	w8a8	Qualcomm® QCS9075	0.328 ms	2 - 4 MB	NPU
GoogLeNet	QNN_DLC	w8a8	Qualcomm® QCM6690	2.252 ms	0 - 29 MB	NPU
GoogLeNet	QNN_DLC	w8a8	Qualcomm® QCS8450 (Proxy)	0.414 ms	0 - 45 MB	NPU
GoogLeNet	QNN_DLC	w8a8	Qualcomm® SA7255P	0.793 ms	0 - 28 MB	NPU
GoogLeNet	QNN_DLC	w8a8	Qualcomm® SA8295P	0.637 ms	0 - 26 MB	NPU
GoogLeNet	QNN_DLC	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.156 ms	0 - 33 MB	NPU
GoogLeNet	QNN_DLC	w8a8	Snapdragon® 7 Gen 4 Mobile	0.334 ms	0 - 29 MB	NPU
GoogLeNet	QNN_DLC	w8a8	Snapdragon® 7 Gen 4 Mobile	0.334 ms	0 - 29 MB	NPU
GoogLeNet	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	0.373 ms	0 - 37 MB	NPU
GoogLeNet	TFLITE	float	Snapdragon® 8 Elite Mobile	0.456 ms	0 - 38 MB	NPU
GoogLeNet	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	0.568 ms	0 - 53 MB	NPU
GoogLeNet	TFLITE	float	Qualcomm® QCS8275 (Proxy)	5.017 ms	0 - 33 MB	NPU
GoogLeNet	TFLITE	float	Qualcomm® QCS8550 (Proxy)	0.816 ms	0 - 2 MB	NPU
GoogLeNet	TFLITE	float	Qualcomm® SA8775P	1.587 ms	0 - 35 MB	NPU
GoogLeNet	TFLITE	float	Qualcomm® SA8775P	1.587 ms	0 - 35 MB	NPU
GoogLeNet	TFLITE	float	Qualcomm® SA8775P	1.587 ms	0 - 35 MB	NPU
GoogLeNet	TFLITE	float	Qualcomm® QCS9075	1.526 ms	0 - 16 MB	NPU
GoogLeNet	TFLITE	float	Qualcomm® QCS8450 (Proxy)	1.768 ms	0 - 56 MB	NPU
GoogLeNet	TFLITE	float	Qualcomm® SA7255P	5.017 ms	0 - 33 MB	NPU
GoogLeNet	TFLITE	float	Qualcomm® SA8295P	1.808 ms	0 - 31 MB	NPU
GoogLeNet	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	0.456 ms	0 - 38 MB	NPU
GoogLeNet	TFLITE	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.141 ms	0 - 31 MB	NPU
GoogLeNet	TFLITE	w8a8	Snapdragon® 8 Elite Mobile	0.161 ms	0 - 28 MB	NPU
GoogLeNet	TFLITE	w8a8	Snapdragon® 8 Gen 3 Mobile	0.186 ms	0 - 43 MB	NPU
GoogLeNet	TFLITE	w8a8	Qualcomm® QCS6490	1.052 ms	0 - 9 MB	NPU
GoogLeNet	TFLITE	w8a8	Qualcomm® QCS8275 (Proxy)	0.837 ms	0 - 28 MB	NPU
GoogLeNet	TFLITE	w8a8	Qualcomm® QCS8550 (Proxy)	0.246 ms	0 - 91 MB	NPU
GoogLeNet	TFLITE	w8a8	Qualcomm® SA8775P	0.429 ms	0 - 30 MB	NPU
GoogLeNet	TFLITE	w8a8	Qualcomm® SA8775P	0.429 ms	0 - 30 MB	NPU
GoogLeNet	TFLITE	w8a8	Qualcomm® SA8775P	0.429 ms	0 - 30 MB	NPU
GoogLeNet	TFLITE	w8a8	Qualcomm® QCS9075	0.341 ms	0 - 9 MB	NPU
GoogLeNet	TFLITE	w8a8	Qualcomm® QCM6690	2.26 ms	0 - 30 MB	NPU
GoogLeNet	TFLITE	w8a8	Qualcomm® QCS8450 (Proxy)	0.43 ms	0 - 45 MB	NPU
GoogLeNet	TFLITE	w8a8	Qualcomm® SA7255P	0.837 ms	0 - 28 MB	NPU
GoogLeNet	TFLITE	w8a8	Qualcomm® SA8295P	0.636 ms	0 - 26 MB	NPU
GoogLeNet	TFLITE	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.161 ms	0 - 28 MB	NPU
GoogLeNet	TFLITE	w8a8	Snapdragon® 7 Gen 4 Mobile	0.33 ms	0 - 30 MB	NPU
GoogLeNet	TFLITE	w8a8	Snapdragon® 7 Gen 4 Mobile	0.33 ms	0 - 30 MB	NPU

License

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

References

• Going Deeper with Convolutions
• 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.