ResNet-Mixed-Convolution: Optimized for Qualcomm Devices

ResNet Mixed Convolutions is a network with a mixture of 2D and 3D convolutions used for video understanding.

This is based on the implementation of ResNet-Mixed-Convolution 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	w8a16	Universal	QAIRT 2.42, ONNX Runtime 1.24.3	Download
QNN_DLC	float	Universal	QAIRT 2.43	Download
QNN_DLC	w8a16	Universal	QAIRT 2.43	Download
TFLITE	float	Universal	QAIRT 2.43, TFLite 2.19.1	Download

For more device-specific assets and performance metrics, visit ResNet-Mixed-Convolution 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 ResNet-Mixed-Convolution on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.video_classification

Model Stats:

• Model checkpoint: Kinetics-400
• Input resolution: 112x112
• Number of parameters: 11.7M
• Model size (float): 44.6 MB
• Model size (w8a16): 11.5 MB

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
ResNet-Mixed-Convolution	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	5.556 ms	2 - 221 MB	NPU
ResNet-Mixed-Convolution	ONNX	float	Snapdragon® X2 Elite	7.105 ms	22 - 22 MB	NPU
ResNet-Mixed-Convolution	ONNX	float	Snapdragon® X Elite	13.803 ms	22 - 22 MB	NPU
ResNet-Mixed-Convolution	ONNX	float	Snapdragon® 8 Gen 3 Mobile	9.613 ms	2 - 277 MB	NPU
ResNet-Mixed-Convolution	ONNX	float	Qualcomm® QCS8550 (Proxy)	13.166 ms	0 - 37 MB	NPU
ResNet-Mixed-Convolution	ONNX	float	Qualcomm® QCS9075	26.615 ms	2 - 5 MB	NPU
ResNet-Mixed-Convolution	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	7.828 ms	0 - 216 MB	NPU
ResNet-Mixed-Convolution	ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	3.512 ms	0 - 191 MB	NPU
ResNet-Mixed-Convolution	ONNX	w8a16	Snapdragon® X2 Elite	4.643 ms	12 - 12 MB	NPU
ResNet-Mixed-Convolution	ONNX	w8a16	Snapdragon® X Elite	9.075 ms	11 - 11 MB	NPU
ResNet-Mixed-Convolution	ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	6.39 ms	1 - 259 MB	NPU
ResNet-Mixed-Convolution	ONNX	w8a16	Qualcomm® QCS6490	1732.048 ms	45 - 62 MB	CPU
ResNet-Mixed-Convolution	ONNX	w8a16	Qualcomm® QCS8550 (Proxy)	8.525 ms	1 - 6 MB	NPU
ResNet-Mixed-Convolution	ONNX	w8a16	Qualcomm® QCS9075	9.054 ms	1 - 4 MB	NPU
ResNet-Mixed-Convolution	ONNX	w8a16	Qualcomm® QCM6690	895.403 ms	106 - 112 MB	CPU
ResNet-Mixed-Convolution	ONNX	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	5.263 ms	1 - 192 MB	NPU
ResNet-Mixed-Convolution	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	872.819 ms	112 - 120 MB	CPU
ResNet-Mixed-Convolution	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	5.731 ms	1 - 232 MB	NPU
ResNet-Mixed-Convolution	QNN_DLC	float	Snapdragon® X2 Elite	7.635 ms	2 - 2 MB	NPU
ResNet-Mixed-Convolution	QNN_DLC	float	Snapdragon® X Elite	14.008 ms	2 - 2 MB	NPU
ResNet-Mixed-Convolution	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	9.555 ms	0 - 284 MB	NPU
ResNet-Mixed-Convolution	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	97.14 ms	0 - 222 MB	NPU
ResNet-Mixed-Convolution	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	13.194 ms	2 - 5 MB	NPU
ResNet-Mixed-Convolution	QNN_DLC	float	Qualcomm® SA8775P	25.079 ms	1 - 223 MB	NPU
ResNet-Mixed-Convolution	QNN_DLC	float	Qualcomm® QCS9075	28.005 ms	2 - 6 MB	NPU
ResNet-Mixed-Convolution	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	27.501 ms	0 - 243 MB	NPU
ResNet-Mixed-Convolution	QNN_DLC	float	Qualcomm® SA7255P	97.14 ms	0 - 222 MB	NPU
ResNet-Mixed-Convolution	QNN_DLC	float	Qualcomm® SA8295P	26.769 ms	0 - 193 MB	NPU
ResNet-Mixed-Convolution	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	7.637 ms	2 - 227 MB	NPU
ResNet-Mixed-Convolution	QNN_DLC	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	4.007 ms	1 - 189 MB	NPU
ResNet-Mixed-Convolution	QNN_DLC	w8a16	Snapdragon® X2 Elite	5.355 ms	1 - 1 MB	NPU
ResNet-Mixed-Convolution	QNN_DLC	w8a16	Snapdragon® X Elite	9.841 ms	1 - 1 MB	NPU
ResNet-Mixed-Convolution	QNN_DLC	w8a16	Snapdragon® 8 Gen 3 Mobile	6.625 ms	1 - 256 MB	NPU
ResNet-Mixed-Convolution	QNN_DLC	w8a16	Qualcomm® QCS6490	37.376 ms	1 - 4 MB	NPU
ResNet-Mixed-Convolution	QNN_DLC	w8a16	Qualcomm® QCS8275 (Proxy)	29.748 ms	1 - 190 MB	NPU
ResNet-Mixed-Convolution	QNN_DLC	w8a16	Qualcomm® QCS8550 (Proxy)	9.171 ms	1 - 71 MB	NPU
ResNet-Mixed-Convolution	QNN_DLC	w8a16	Qualcomm® SA8775P	9.398 ms	1 - 191 MB	NPU
ResNet-Mixed-Convolution	QNN_DLC	w8a16	Qualcomm® QCS9075	10.389 ms	3 - 6 MB	NPU
ResNet-Mixed-Convolution	QNN_DLC	w8a16	Qualcomm® QCM6690	180.673 ms	1 - 209 MB	NPU
ResNet-Mixed-Convolution	QNN_DLC	w8a16	Qualcomm® QCS8450 (Proxy)	12.955 ms	1 - 255 MB	NPU
ResNet-Mixed-Convolution	QNN_DLC	w8a16	Qualcomm® SA7255P	29.748 ms	1 - 190 MB	NPU
ResNet-Mixed-Convolution	QNN_DLC	w8a16	Qualcomm® SA8295P	16.299 ms	1 - 192 MB	NPU
ResNet-Mixed-Convolution	QNN_DLC	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	5.283 ms	1 - 187 MB	NPU
ResNet-Mixed-Convolution	QNN_DLC	w8a16	Snapdragon® 7 Gen 4 Mobile	15.776 ms	1 - 198 MB	NPU
ResNet-Mixed-Convolution	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	199.643 ms	0 - 251 MB	NPU
ResNet-Mixed-Convolution	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	217.074 ms	0 - 312 MB	NPU
ResNet-Mixed-Convolution	TFLITE	float	Qualcomm® QCS8275 (Proxy)	585.624 ms	0 - 249 MB	NPU
ResNet-Mixed-Convolution	TFLITE	float	Qualcomm® QCS8550 (Proxy)	298.884 ms	0 - 2 MB	NPU
ResNet-Mixed-Convolution	TFLITE	float	Qualcomm® SA8775P	296.628 ms	0 - 248 MB	NPU
ResNet-Mixed-Convolution	TFLITE	float	Qualcomm® QCS9075	328.659 ms	0 - 28 MB	NPU
ResNet-Mixed-Convolution	TFLITE	float	Qualcomm® QCS8450 (Proxy)	331.006 ms	1 - 280 MB	NPU
ResNet-Mixed-Convolution	TFLITE	float	Qualcomm® SA7255P	585.624 ms	0 - 249 MB	NPU
ResNet-Mixed-Convolution	TFLITE	float	Qualcomm® SA8295P	365.06 ms	0 - 232 MB	NPU
ResNet-Mixed-Convolution	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	203.6 ms	0 - 248 MB	NPU

License

• The license for the original implementation of ResNet-Mixed-Convolution can be found here.

References

• A Closer Look at Spatiotemporal Convolutions for Action Recognition
• 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.