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 2.43	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 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	0.397 ms	0 - 31 MB	NPU
GoogLeNet	ONNX	float	Snapdragon® X2 Elite	0.586 ms	13 - 13 MB	NPU
GoogLeNet	ONNX	float	Snapdragon® X Elite	0.999 ms	13 - 13 MB	NPU
GoogLeNet	ONNX	float	Snapdragon® 8 Gen 3 Mobile	0.565 ms	0 - 50 MB	NPU
GoogLeNet	ONNX	float	Qualcomm® QCS8550 (Proxy)	0.845 ms	0 - 2 MB	NPU
GoogLeNet	ONNX	float	Qualcomm® QCS9075	1.561 ms	1 - 3 MB	NPU
GoogLeNet	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	0.475 ms	0 - 26 MB	NPU
GoogLeNet	ONNX	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.182 ms	0 - 35 MB	NPU
GoogLeNet	ONNX	w8a8	Snapdragon® X2 Elite	0.173 ms	7 - 7 MB	NPU
GoogLeNet	ONNX	w8a8	Snapdragon® X Elite	0.407 ms	7 - 7 MB	NPU
GoogLeNet	ONNX	w8a8	Snapdragon® 8 Gen 3 Mobile	0.225 ms	0 - 51 MB	NPU
GoogLeNet	ONNX	w8a8	Qualcomm® QCS6490	13.855 ms	6 - 17 MB	CPU
GoogLeNet	ONNX	w8a8	Qualcomm® QCS8550 (Proxy)	0.304 ms	0 - 31 MB	NPU
GoogLeNet	ONNX	w8a8	Qualcomm® QCS9075	0.459 ms	0 - 3 MB	NPU
GoogLeNet	ONNX	w8a8	Qualcomm® QCM6690	9.297 ms	8 - 17 MB	CPU
GoogLeNet	ONNX	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.195 ms	0 - 35 MB	NPU
GoogLeNet	ONNX	w8a8	Snapdragon® 7 Gen 4 Mobile	7.097 ms	7 - 16 MB	CPU
GoogLeNet	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	0.375 ms	1 - 31 MB	NPU
GoogLeNet	QNN_DLC	float	Snapdragon® X2 Elite	0.525 ms	1 - 1 MB	NPU
GoogLeNet	QNN_DLC	float	Snapdragon® X Elite	0.951 ms	1 - 1 MB	NPU
GoogLeNet	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	0.549 ms	0 - 45 MB	NPU
GoogLeNet	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	5.001 ms	1 - 28 MB	NPU
GoogLeNet	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	0.805 ms	1 - 2 MB	NPU
GoogLeNet	QNN_DLC	float	Qualcomm® SA8775P	1.533 ms	0 - 30 MB	NPU
GoogLeNet	QNN_DLC	float	Qualcomm® QCS9075	1.513 ms	1 - 3 MB	NPU
GoogLeNet	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	1.757 ms	0 - 45 MB	NPU
GoogLeNet	QNN_DLC	float	Qualcomm® SA7255P	5.001 ms	1 - 28 MB	NPU
GoogLeNet	QNN_DLC	float	Qualcomm® SA8295P	1.822 ms	0 - 25 MB	NPU
GoogLeNet	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	0.449 ms	1 - 28 MB	NPU
GoogLeNet	QNN_DLC	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.139 ms	0 - 30 MB	NPU
GoogLeNet	QNN_DLC	w8a8	Snapdragon® X2 Elite	0.224 ms	0 - 0 MB	NPU
GoogLeNet	QNN_DLC	w8a8	Snapdragon® X Elite	0.353 ms	0 - 0 MB	NPU
GoogLeNet	QNN_DLC	w8a8	Snapdragon® 8 Gen 3 Mobile	0.181 ms	0 - 42 MB	NPU
GoogLeNet	QNN_DLC	w8a8	Qualcomm® QCS6490	1.06 ms	2 - 4 MB	NPU
GoogLeNet	QNN_DLC	w8a8	Qualcomm® QCS8275 (Proxy)	0.795 ms	0 - 28 MB	NPU
GoogLeNet	QNN_DLC	w8a8	Qualcomm® QCS8550 (Proxy)	0.249 ms	0 - 66 MB	NPU
GoogLeNet	QNN_DLC	w8a8	Qualcomm® SA8775P	0.426 ms	0 - 29 MB	NPU
GoogLeNet	QNN_DLC	w8a8	Qualcomm® QCS9075	0.335 ms	0 - 2 MB	NPU
GoogLeNet	QNN_DLC	w8a8	Qualcomm® QCM6690	2.247 ms	0 - 28 MB	NPU
GoogLeNet	QNN_DLC	w8a8	Qualcomm® QCS8450 (Proxy)	0.417 ms	0 - 43 MB	NPU
GoogLeNet	QNN_DLC	w8a8	Qualcomm® SA7255P	0.795 ms	0 - 28 MB	NPU
GoogLeNet	QNN_DLC	w8a8	Qualcomm® SA8295P	0.602 ms	0 - 25 MB	NPU
GoogLeNet	QNN_DLC	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.153 ms	0 - 31 MB	NPU
GoogLeNet	QNN_DLC	w8a8	Snapdragon® 7 Gen 4 Mobile	0.331 ms	0 - 28 MB	NPU
GoogLeNet	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	0.381 ms	0 - 38 MB	NPU
GoogLeNet	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	0.548 ms	0 - 55 MB	NPU
GoogLeNet	TFLITE	float	Qualcomm® QCS8275 (Proxy)	5.001 ms	0 - 34 MB	NPU
GoogLeNet	TFLITE	float	Qualcomm® QCS8550 (Proxy)	0.808 ms	0 - 1 MB	NPU
GoogLeNet	TFLITE	float	Qualcomm® SA8775P	1.557 ms	0 - 37 MB	NPU
GoogLeNet	TFLITE	float	Qualcomm® QCS9075	1.525 ms	0 - 16 MB	NPU
GoogLeNet	TFLITE	float	Qualcomm® QCS8450 (Proxy)	1.78 ms	0 - 59 MB	NPU
GoogLeNet	TFLITE	float	Qualcomm® SA7255P	5.001 ms	0 - 34 MB	NPU
GoogLeNet	TFLITE	float	Qualcomm® SA8295P	1.777 ms	0 - 32 MB	NPU
GoogLeNet	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	0.454 ms	0 - 34 MB	NPU
GoogLeNet	TFLITE	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.146 ms	0 - 31 MB	NPU
GoogLeNet	TFLITE	w8a8	Snapdragon® 8 Gen 3 Mobile	0.185 ms	0 - 43 MB	NPU
GoogLeNet	TFLITE	w8a8	Qualcomm® QCS6490	1.022 ms	0 - 8 MB	NPU
GoogLeNet	TFLITE	w8a8	Qualcomm® QCS8275 (Proxy)	0.843 ms	0 - 28 MB	NPU
GoogLeNet	TFLITE	w8a8	Qualcomm® QCS8550 (Proxy)	0.237 ms	0 - 2 MB	NPU
GoogLeNet	TFLITE	w8a8	Qualcomm® SA8775P	0.44 ms	0 - 30 MB	NPU
GoogLeNet	TFLITE	w8a8	Qualcomm® QCS9075	0.355 ms	0 - 9 MB	NPU
GoogLeNet	TFLITE	w8a8	Qualcomm® QCM6690	2.241 ms	0 - 29 MB	NPU
GoogLeNet	TFLITE	w8a8	Qualcomm® QCS8450 (Proxy)	0.423 ms	0 - 44 MB	NPU
GoogLeNet	TFLITE	w8a8	Qualcomm® SA7255P	0.843 ms	0 - 28 MB	NPU
GoogLeNet	TFLITE	w8a8	Qualcomm® SA8295P	0.635 ms	0 - 26 MB	NPU
GoogLeNet	TFLITE	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.151 ms	0 - 28 MB	NPU
GoogLeNet	TFLITE	w8a8	Snapdragon® 7 Gen 4 Mobile	0.33 ms	0 - 29 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.