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 1.25.0	Download
ONNX	w8a8	Universal	QAIRT 2.42, ONNX Runtime 1.25.0	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	0.396 ms	1 - 32 MB	NPU
GoogLeNet	ONNX	float	Snapdragon® X2 Elite	0.415 ms	212 - 212 MB	NPU
GoogLeNet	ONNX	float	Snapdragon® X Elite	0.86 ms	180 - 180 MB	NPU
GoogLeNet	ONNX	float	Snapdragon® 8 Gen 3 Mobile	0.557 ms	0 - 54 MB	NPU
GoogLeNet	ONNX	float	Qualcomm® QCS8550 (Proxy)	0.844 ms	0 - 38 MB	NPU
GoogLeNet	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	0.473 ms	0 - 27 MB	NPU
GoogLeNet	ONNX	float	Qualcomm® QCS9075	1.546 ms	1 - 46 MB	NPU
GoogLeNet	ONNX	float	Qualcomm® QCS8750	0.473 ms	0 - 27 MB	NPU
GoogLeNet	ONNX	float	Qualcomm® QCS7181	0.86 ms	180 - 180 MB	NPU
GoogLeNet	ONNX	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.185 ms	0 - 37 MB	NPU
GoogLeNet	ONNX	w8a8	Snapdragon® X2 Elite	0.164 ms	211 - 211 MB	NPU
GoogLeNet	ONNX	w8a8	Snapdragon® X Elite	0.289 ms	149 - 149 MB	NPU
GoogLeNet	ONNX	w8a8	Snapdragon® 8 Gen 3 Mobile	0.229 ms	0 - 51 MB	NPU
GoogLeNet	ONNX	w8a8	Qualcomm® QCS6490	13.8 ms	8 - 18 MB	CPU
GoogLeNet	ONNX	w8a8	Qualcomm® QCS8550 (Proxy)	0.304 ms	0 - 24 MB	NPU
GoogLeNet	ONNX	w8a8	Snapdragon® 7 Gen 4 Mobile	7.085 ms	8 - 17 MB	CPU
GoogLeNet	ONNX	w8a8	Qualcomm® QCM6690	9.196 ms	9 - 18 MB	CPU
GoogLeNet	ONNX	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.192 ms	0 - 33 MB	NPU
GoogLeNet	ONNX	w8a8	Qualcomm® QCS9075	0.431 ms	0 - 52 MB	NPU
GoogLeNet	ONNX	w8a8	Qualcomm® QCS7790	7.085 ms	8 - 17 MB	CPU
GoogLeNet	ONNX	w8a8	Qualcomm® QCS8750	0.192 ms	0 - 33 MB	NPU
GoogLeNet	ONNX	w8a8	Qualcomm® QCS7181	0.289 ms	149 - 149 MB	NPU
GoogLeNet	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	0.37 ms	1 - 31 MB	NPU
GoogLeNet	QNN_DLC	float	Snapdragon® X2 Elite	0.506 ms	1 - 1 MB	NPU
GoogLeNet	QNN_DLC	float	Snapdragon® X Elite	0.959 ms	1 - 1 MB	NPU
GoogLeNet	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	0.563 ms	0 - 43 MB	NPU
GoogLeNet	QNN_DLC	float	Qualcomm® QCS8275	5.026 ms	1 - 27 MB	NPU
GoogLeNet	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	0.811 ms	1 - 2 MB	NPU
GoogLeNet	QNN_DLC	float	Qualcomm® SA8775P	1.541 ms	1 - 29 MB	NPU
GoogLeNet	QNN_DLC	float	Qualcomm® SA8650P	1.541 ms	1 - 29 MB	NPU
GoogLeNet	QNN_DLC	float	Qualcomm® SA8255P	1.541 ms	1 - 29 MB	NPU
GoogLeNet	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	1.747 ms	0 - 45 MB	NPU
GoogLeNet	QNN_DLC	float	Qualcomm® SA8295P	1.792 ms	0 - 24 MB	NPU
GoogLeNet	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	0.459 ms	0 - 31 MB	NPU
GoogLeNet	QNN_DLC	float	Qualcomm® SA7255P	5.026 ms	1 - 27 MB	NPU
GoogLeNet	QNN_DLC	float	Qualcomm® QCS9075	1.511 ms	1 - 3 MB	NPU
GoogLeNet	QNN_DLC	float	Qualcomm® QCS8750	0.459 ms	0 - 31 MB	NPU
GoogLeNet	QNN_DLC	float	Qualcomm® QCS7181	0.959 ms	1 - 1 MB	NPU
GoogLeNet	QNN_DLC	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.14 ms	0 - 33 MB	NPU
GoogLeNet	QNN_DLC	w8a8	Snapdragon® X2 Elite	0.219 ms	0 - 0 MB	NPU
GoogLeNet	QNN_DLC	w8a8	Snapdragon® X Elite	0.337 ms	0 - 0 MB	NPU
GoogLeNet	QNN_DLC	w8a8	Snapdragon® 8 Gen 3 Mobile	0.187 ms	0 - 45 MB	NPU
GoogLeNet	QNN_DLC	w8a8	Qualcomm® QCS6490	1.04 ms	0 - 2 MB	NPU
GoogLeNet	QNN_DLC	w8a8	Qualcomm® QCS8275	0.822 ms	0 - 29 MB	NPU
GoogLeNet	QNN_DLC	w8a8	Qualcomm® QCS8550 (Proxy)	0.243 ms	0 - 2 MB	NPU
GoogLeNet	QNN_DLC	w8a8	Qualcomm® SA8775P	0.41 ms	0 - 31 MB	NPU
GoogLeNet	QNN_DLC	w8a8	Qualcomm® SA8650P	0.41 ms	0 - 31 MB	NPU
GoogLeNet	QNN_DLC	w8a8	Qualcomm® SA8255P	0.41 ms	0 - 31 MB	NPU
GoogLeNet	QNN_DLC	w8a8	Qualcomm® SA7255P	0.822 ms	0 - 29 MB	NPU
GoogLeNet	QNN_DLC	w8a8	Snapdragon® 7 Gen 4 Mobile	0.331 ms	0 - 30 MB	NPU
GoogLeNet	QNN_DLC	w8a8	Qualcomm® SA8295P	0.613 ms	0 - 28 MB	NPU
GoogLeNet	QNN_DLC	w8a8	Qualcomm® QCM6690	2.37 ms	0 - 33 MB	NPU
GoogLeNet	QNN_DLC	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.152 ms	0 - 30 MB	NPU
GoogLeNet	QNN_DLC	w8a8	Qualcomm® QCS9075	0.329 ms	0 - 2 MB	NPU
GoogLeNet	QNN_DLC	w8a8	Qualcomm® QCS8450 (Proxy)	0.413 ms	0 - 46 MB	NPU
GoogLeNet	QNN_DLC	w8a8	Qualcomm® QCS7790	0.331 ms	0 - 30 MB	NPU
GoogLeNet	QNN_DLC	w8a8	Qualcomm® QCS8750	0.152 ms	0 - 30 MB	NPU
GoogLeNet	QNN_DLC	w8a8	Qualcomm® QCS7181	0.337 ms	0 - 0 MB	NPU
GoogLeNet	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	0.374 ms	0 - 38 MB	NPU
GoogLeNet	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	0.567 ms	0 - 53 MB	NPU
GoogLeNet	TFLITE	float	Qualcomm® QCS8275	5.03 ms	0 - 33 MB	NPU
GoogLeNet	TFLITE	float	Qualcomm® QCS8550 (Proxy)	0.819 ms	0 - 2 MB	NPU
GoogLeNet	TFLITE	float	Qualcomm® SA8775P	1.555 ms	0 - 35 MB	NPU
GoogLeNet	TFLITE	float	Qualcomm® SA8650P	1.555 ms	0 - 35 MB	NPU
GoogLeNet	TFLITE	float	Qualcomm® SA8255P	1.555 ms	0 - 35 MB	NPU
GoogLeNet	TFLITE	float	Qualcomm® QCS8450 (Proxy)	1.772 ms	0 - 55 MB	NPU
GoogLeNet	TFLITE	float	Qualcomm® SA8295P	1.798 ms	0 - 31 MB	NPU
GoogLeNet	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	0.456 ms	0 - 34 MB	NPU
GoogLeNet	TFLITE	float	Qualcomm® SA7255P	5.03 ms	0 - 33 MB	NPU
GoogLeNet	TFLITE	float	Qualcomm® QCS9075	1.526 ms	0 - 16 MB	NPU
GoogLeNet	TFLITE	float	Qualcomm® QCS8750	0.456 ms	0 - 34 MB	NPU
GoogLeNet	TFLITE	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.139 ms	0 - 32 MB	NPU
GoogLeNet	TFLITE	w8a8	Snapdragon® 8 Gen 3 Mobile	0.185 ms	0 - 43 MB	NPU
GoogLeNet	TFLITE	w8a8	Qualcomm® QCS6490	0.959 ms	0 - 8 MB	NPU
GoogLeNet	TFLITE	w8a8	Qualcomm® QCS8275	0.83 ms	0 - 28 MB	NPU
GoogLeNet	TFLITE	w8a8	Qualcomm® QCS8550 (Proxy)	0.243 ms	0 - 2 MB	NPU
GoogLeNet	TFLITE	w8a8	Qualcomm® SA8775P	0.429 ms	0 - 30 MB	NPU
GoogLeNet	TFLITE	w8a8	Qualcomm® SA8650P	0.429 ms	0 - 30 MB	NPU
GoogLeNet	TFLITE	w8a8	Qualcomm® SA8255P	0.429 ms	0 - 30 MB	NPU
GoogLeNet	TFLITE	w8a8	Qualcomm® SA7255P	0.83 ms	0 - 28 MB	NPU
GoogLeNet	TFLITE	w8a8	Snapdragon® 7 Gen 4 Mobile	0.33 ms	0 - 29 MB	NPU
GoogLeNet	TFLITE	w8a8	Qualcomm® SA8295P	0.645 ms	0 - 26 MB	NPU
GoogLeNet	TFLITE	w8a8	Qualcomm® QCM6690	2.262 ms	0 - 29 MB	NPU
GoogLeNet	TFLITE	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.16 ms	0 - 33 MB	NPU
GoogLeNet	TFLITE	w8a8	Qualcomm® QCS9075	0.347 ms	0 - 9 MB	NPU
GoogLeNet	TFLITE	w8a8	Qualcomm® QCS8450 (Proxy)	0.424 ms	0 - 44 MB	NPU
GoogLeNet	TFLITE	w8a8	Qualcomm® QCS7790	0.33 ms	0 - 29 MB	NPU
GoogLeNet	TFLITE	w8a8	Qualcomm® QCS8750	0.16 ms	0 - 33 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.