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	0.399 ms	0 - 31 MB	NPU
GoogLeNet	ONNX	float	Snapdragon® X2 Elite	0.413 ms	13 - 13 MB	NPU
GoogLeNet	ONNX	float	Snapdragon® X Elite	0.978 ms	13 - 13 MB	NPU
GoogLeNet	ONNX	float	Snapdragon® 8 Gen 3 Mobile	0.565 ms	0 - 46 MB	NPU
GoogLeNet	ONNX	float	Qualcomm® QCS8550 (Proxy)	0.845 ms	0 - 6 MB	NPU
GoogLeNet	ONNX	float	Qualcomm® QCS9075	1.546 ms	1 - 3 MB	NPU
GoogLeNet	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	0.474 ms	0 - 31 MB	NPU
GoogLeNet	ONNX	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.186 ms	0 - 34 MB	NPU
GoogLeNet	ONNX	w8a8	Snapdragon® X2 Elite	0.179 ms	7 - 7 MB	NPU
GoogLeNet	ONNX	w8a8	Snapdragon® X Elite	0.415 ms	7 - 7 MB	NPU
GoogLeNet	ONNX	w8a8	Snapdragon® 8 Gen 3 Mobile	0.23 ms	0 - 48 MB	NPU
GoogLeNet	ONNX	w8a8	Qualcomm® QCS6490	13.778 ms	8 - 19 MB	CPU
GoogLeNet	ONNX	w8a8	Qualcomm® QCS8550 (Proxy)	0.3 ms	0 - 9 MB	NPU
GoogLeNet	ONNX	w8a8	Qualcomm® QCS9075	0.43 ms	0 - 3 MB	NPU
GoogLeNet	ONNX	w8a8	Qualcomm® QCM6690	9.237 ms	8 - 16 MB	CPU
GoogLeNet	ONNX	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.194 ms	0 - 36 MB	NPU
GoogLeNet	ONNX	w8a8	Snapdragon® 7 Gen 4 Mobile	7.071 ms	6 - 15 MB	CPU
GoogLeNet	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	0.374 ms	1 - 30 MB	NPU
GoogLeNet	QNN_DLC	float	Snapdragon® X2 Elite	0.51 ms	1 - 1 MB	NPU
GoogLeNet	QNN_DLC	float	Snapdragon® X Elite	0.963 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)	5.006 ms	1 - 26 MB	NPU
GoogLeNet	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	0.813 ms	1 - 2 MB	NPU
GoogLeNet	QNN_DLC	float	Qualcomm® SA8775P	1.537 ms	1 - 29 MB	NPU
GoogLeNet	QNN_DLC	float	Qualcomm® QCS9075	1.528 ms	1 - 3 MB	NPU
GoogLeNet	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	1.752 ms	0 - 45 MB	NPU
GoogLeNet	QNN_DLC	float	Qualcomm® SA7255P	5.006 ms	1 - 26 MB	NPU
GoogLeNet	QNN_DLC	float	Qualcomm® SA8295P	1.784 ms	0 - 24 MB	NPU
GoogLeNet	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	0.451 ms	0 - 27 MB	NPU
GoogLeNet	QNN_DLC	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.139 ms	0 - 32 MB	NPU
GoogLeNet	QNN_DLC	w8a8	Snapdragon® X2 Elite	0.23 ms	0 - 0 MB	NPU
GoogLeNet	QNN_DLC	w8a8	Snapdragon® X Elite	0.349 ms	0 - 0 MB	NPU
GoogLeNet	QNN_DLC	w8a8	Snapdragon® 8 Gen 3 Mobile	0.197 ms	0 - 44 MB	NPU
GoogLeNet	QNN_DLC	w8a8	Qualcomm® QCS6490	1.033 ms	0 - 2 MB	NPU
GoogLeNet	QNN_DLC	w8a8	Qualcomm® QCS8275 (Proxy)	0.804 ms	0 - 28 MB	NPU
GoogLeNet	QNN_DLC	w8a8	Qualcomm® QCS8550 (Proxy)	0.246 ms	0 - 2 MB	NPU
GoogLeNet	QNN_DLC	w8a8	Qualcomm® SA8775P	0.413 ms	0 - 30 MB	NPU
GoogLeNet	QNN_DLC	w8a8	Qualcomm® QCS9075	0.329 ms	2 - 4 MB	NPU
GoogLeNet	QNN_DLC	w8a8	Qualcomm® QCM6690	2.261 ms	0 - 29 MB	NPU
GoogLeNet	QNN_DLC	w8a8	Qualcomm® QCS8450 (Proxy)	0.424 ms	0 - 44 MB	NPU
GoogLeNet	QNN_DLC	w8a8	Qualcomm® SA7255P	0.804 ms	0 - 28 MB	NPU
GoogLeNet	QNN_DLC	w8a8	Qualcomm® SA8295P	0.618 ms	0 - 26 MB	NPU
GoogLeNet	QNN_DLC	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.155 ms	0 - 33 MB	NPU
GoogLeNet	QNN_DLC	w8a8	Snapdragon® 7 Gen 4 Mobile	0.33 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 Gen 3 Mobile	0.561 ms	0 - 54 MB	NPU
GoogLeNet	TFLITE	float	Qualcomm® QCS8275 (Proxy)	5.036 ms	0 - 33 MB	NPU
GoogLeNet	TFLITE	float	Qualcomm® QCS8550 (Proxy)	0.817 ms	0 - 2 MB	NPU
GoogLeNet	TFLITE	float	Qualcomm® SA8775P	1.564 ms	0 - 35 MB	NPU
GoogLeNet	TFLITE	float	Qualcomm® QCS9075	1.527 ms	0 - 16 MB	NPU
GoogLeNet	TFLITE	float	Qualcomm® QCS8450 (Proxy)	1.768 ms	0 - 56 MB	NPU
GoogLeNet	TFLITE	float	Qualcomm® SA7255P	5.036 ms	0 - 33 MB	NPU
GoogLeNet	TFLITE	float	Qualcomm® SA8295P	1.824 ms	0 - 31 MB	NPU
GoogLeNet	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	0.457 ms	0 - 38 MB	NPU
GoogLeNet	TFLITE	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.143 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	0.986 ms	0 - 9 MB	NPU
GoogLeNet	TFLITE	w8a8	Qualcomm® QCS8275 (Proxy)	0.817 ms	0 - 28 MB	NPU
GoogLeNet	TFLITE	w8a8	Qualcomm® QCS8550 (Proxy)	0.247 ms	0 - 90 MB	NPU
GoogLeNet	TFLITE	w8a8	Qualcomm® SA8775P	0.43 ms	0 - 30 MB	NPU
GoogLeNet	TFLITE	w8a8	Qualcomm® QCS9075	0.349 ms	0 - 9 MB	NPU
GoogLeNet	TFLITE	w8a8	Qualcomm® QCM6690	2.26 ms	0 - 30 MB	NPU
GoogLeNet	TFLITE	w8a8	Qualcomm® QCS8450 (Proxy)	0.426 ms	0 - 45 MB	NPU
GoogLeNet	TFLITE	w8a8	Qualcomm® SA7255P	0.817 ms	0 - 28 MB	NPU
GoogLeNet	TFLITE	w8a8	Qualcomm® SA8295P	0.643 ms	0 - 26 MB	NPU
GoogLeNet	TFLITE	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.157 ms	0 - 30 MB	NPU
GoogLeNet	TFLITE	w8a8	Snapdragon® 7 Gen 4 Mobile	0.34 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.