Inception-v3: Optimized for Qualcomm Devices

InceptionNetV3 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 Inception-v3 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 Inception-v3 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 Inception-v3 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: 23.9M
• Model size (float): 90.9 MB
• Model size (w8a8): 23.3 MB

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
Inception-v3	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	0.805 ms	0 - 39 MB	NPU
Inception-v3	ONNX	float	Snapdragon® X2 Elite	0.694 ms	46 - 46 MB	NPU
Inception-v3	ONNX	float	Snapdragon® X Elite	1.52 ms	46 - 46 MB	NPU
Inception-v3	ONNX	float	Snapdragon® 8 Gen 3 Mobile	1.058 ms	0 - 61 MB	NPU
Inception-v3	ONNX	float	Qualcomm® QCS8550 (Proxy)	1.492 ms	0 - 61 MB	NPU
Inception-v3	ONNX	float	Qualcomm® QCS9075	2.175 ms	0 - 4 MB	NPU
Inception-v3	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	0.935 ms	0 - 40 MB	NPU
Inception-v3	ONNX	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.414 ms	0 - 57 MB	NPU
Inception-v3	ONNX	w8a8	Snapdragon® X2 Elite	0.277 ms	23 - 23 MB	NPU
Inception-v3	ONNX	w8a8	Snapdragon® X Elite	0.716 ms	23 - 23 MB	NPU
Inception-v3	ONNX	w8a8	Snapdragon® 8 Gen 3 Mobile	0.515 ms	0 - 96 MB	NPU
Inception-v3	ONNX	w8a8	Qualcomm® QCS6490	25.097 ms	10 - 39 MB	CPU
Inception-v3	ONNX	w8a8	Qualcomm® QCS8550 (Proxy)	0.662 ms	0 - 27 MB	NPU
Inception-v3	ONNX	w8a8	Qualcomm® QCS9075	0.744 ms	0 - 3 MB	NPU
Inception-v3	ONNX	w8a8	Qualcomm® QCM6690	17.944 ms	10 - 20 MB	CPU
Inception-v3	ONNX	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.435 ms	0 - 52 MB	NPU
Inception-v3	ONNX	w8a8	Snapdragon® 7 Gen 4 Mobile	14.035 ms	15 - 25 MB	CPU
Inception-v3	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	0.759 ms	1 - 36 MB	NPU
Inception-v3	QNN_DLC	float	Snapdragon® X2 Elite	0.771 ms	1 - 1 MB	NPU
Inception-v3	QNN_DLC	float	Snapdragon® X Elite	1.426 ms	1 - 1 MB	NPU
Inception-v3	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	1.024 ms	0 - 55 MB	NPU
Inception-v3	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	7.861 ms	1 - 33 MB	NPU
Inception-v3	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	1.367 ms	1 - 2 MB	NPU
Inception-v3	QNN_DLC	float	Qualcomm® SA8775P	2.233 ms	1 - 33 MB	NPU
Inception-v3	QNN_DLC	float	Qualcomm® QCS9075	2.049 ms	1 - 3 MB	NPU
Inception-v3	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	2.337 ms	0 - 54 MB	NPU
Inception-v3	QNN_DLC	float	Qualcomm® SA7255P	7.861 ms	1 - 33 MB	NPU
Inception-v3	QNN_DLC	float	Qualcomm® SA8295P	2.667 ms	0 - 30 MB	NPU
Inception-v3	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	0.881 ms	1 - 36 MB	NPU
Inception-v3	QNN_DLC	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.368 ms	0 - 52 MB	NPU
Inception-v3	QNN_DLC	w8a8	Snapdragon® X2 Elite	0.346 ms	0 - 0 MB	NPU
Inception-v3	QNN_DLC	w8a8	Snapdragon® X Elite	0.665 ms	0 - 0 MB	NPU
Inception-v3	QNN_DLC	w8a8	Snapdragon® 8 Gen 3 Mobile	0.469 ms	0 - 73 MB	NPU
Inception-v3	QNN_DLC	w8a8	Qualcomm® QCS6490	2.291 ms	0 - 2 MB	NPU
Inception-v3	QNN_DLC	w8a8	Qualcomm® QCS8275 (Proxy)	1.545 ms	0 - 48 MB	NPU
Inception-v3	QNN_DLC	w8a8	Qualcomm® QCS8550 (Proxy)	0.623 ms	0 - 103 MB	NPU
Inception-v3	QNN_DLC	w8a8	Qualcomm® SA8775P	0.774 ms	0 - 51 MB	NPU
Inception-v3	QNN_DLC	w8a8	Qualcomm® QCS9075	0.621 ms	0 - 2 MB	NPU
Inception-v3	QNN_DLC	w8a8	Qualcomm® QCM6690	5.762 ms	0 - 51 MB	NPU
Inception-v3	QNN_DLC	w8a8	Qualcomm® QCS8450 (Proxy)	0.89 ms	0 - 76 MB	NPU
Inception-v3	QNN_DLC	w8a8	Qualcomm® SA7255P	1.545 ms	0 - 48 MB	NPU
Inception-v3	QNN_DLC	w8a8	Qualcomm® SA8295P	1.16 ms	0 - 48 MB	NPU
Inception-v3	QNN_DLC	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.415 ms	0 - 52 MB	NPU
Inception-v3	QNN_DLC	w8a8	Snapdragon® 7 Gen 4 Mobile	0.958 ms	0 - 50 MB	NPU
Inception-v3	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	0.762 ms	0 - 67 MB	NPU
Inception-v3	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	1.03 ms	0 - 117 MB	NPU
Inception-v3	TFLITE	float	Qualcomm® QCS8275 (Proxy)	7.83 ms	0 - 65 MB	NPU
Inception-v3	TFLITE	float	Qualcomm® QCS8550 (Proxy)	1.364 ms	0 - 2 MB	NPU
Inception-v3	TFLITE	float	Qualcomm® SA8775P	2.264 ms	0 - 65 MB	NPU
Inception-v3	TFLITE	float	Qualcomm® QCS9075	2.055 ms	0 - 48 MB	NPU
Inception-v3	TFLITE	float	Qualcomm® QCS8450 (Proxy)	2.349 ms	0 - 117 MB	NPU
Inception-v3	TFLITE	float	Qualcomm® SA7255P	7.83 ms	0 - 65 MB	NPU
Inception-v3	TFLITE	float	Qualcomm® SA8295P	2.674 ms	0 - 62 MB	NPU
Inception-v3	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	0.872 ms	0 - 64 MB	NPU
Inception-v3	TFLITE	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.373 ms	0 - 51 MB	NPU
Inception-v3	TFLITE	w8a8	Snapdragon® 8 Gen 3 Mobile	0.493 ms	0 - 77 MB	NPU
Inception-v3	TFLITE	w8a8	Qualcomm® QCS6490	2.29 ms	0 - 25 MB	NPU
Inception-v3	TFLITE	w8a8	Qualcomm® QCS8275 (Proxy)	1.623 ms	0 - 48 MB	NPU
Inception-v3	TFLITE	w8a8	Qualcomm® QCS8550 (Proxy)	0.641 ms	0 - 2 MB	NPU
Inception-v3	TFLITE	w8a8	Qualcomm® SA8775P	0.861 ms	0 - 51 MB	NPU
Inception-v3	TFLITE	w8a8	Qualcomm® QCS9075	0.719 ms	0 - 25 MB	NPU
Inception-v3	TFLITE	w8a8	Qualcomm® QCM6690	5.848 ms	0 - 53 MB	NPU
Inception-v3	TFLITE	w8a8	Qualcomm® QCS8450 (Proxy)	0.942 ms	0 - 79 MB	NPU
Inception-v3	TFLITE	w8a8	Qualcomm® SA7255P	1.623 ms	0 - 48 MB	NPU
Inception-v3	TFLITE	w8a8	Qualcomm® SA8295P	1.285 ms	0 - 47 MB	NPU
Inception-v3	TFLITE	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.413 ms	0 - 53 MB	NPU
Inception-v3	TFLITE	w8a8	Snapdragon® 7 Gen 4 Mobile	0.969 ms	0 - 51 MB	NPU

License

• The license for the original implementation of Inception-v3 can be found here.

References

• Rethinking the Inception Architecture for Computer Vision
• 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.