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 1.24.1	Download
ONNX	w8a16	Universal	QAIRT 2.42, ONNX Runtime 1.24.1	Download
QNN_DLC	float	Universal	QAIRT 2.43	Download
QNN_DLC	w8a16	Universal	QAIRT 2.43	Download
TFLITE	float	Universal	QAIRT 2.43, TFLite 2.17.0	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® X Elite	13.83 ms	22 - 22 MB	NPU
ResNet-Mixed-Convolution	ONNX	float	Snapdragon® 8 Gen 3 Mobile	9.602 ms	2 - 276 MB	NPU
ResNet-Mixed-Convolution	ONNX	float	Qualcomm® QCS8550 (Proxy)	13.162 ms	0 - 56 MB	NPU
ResNet-Mixed-Convolution	ONNX	float	Qualcomm® QCS9075	26.529 ms	2 - 5 MB	NPU
ResNet-Mixed-Convolution	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	7.818 ms	0 - 215 MB	NPU
ResNet-Mixed-Convolution	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	5.558 ms	2 - 221 MB	NPU
ResNet-Mixed-Convolution	ONNX	float	Snapdragon® X2 Elite	7.095 ms	22 - 22 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	6.385 ms	1 - 257 MB	NPU
ResNet-Mixed-Convolution	ONNX	w8a16	Qualcomm® QCS6490	1728.003 ms	47 - 64 MB	CPU
ResNet-Mixed-Convolution	ONNX	w8a16	Qualcomm® QCS8550 (Proxy)	8.508 ms	0 - 18 MB	NPU
ResNet-Mixed-Convolution	ONNX	w8a16	Qualcomm® QCS9075	9.052 ms	1 - 4 MB	NPU
ResNet-Mixed-Convolution	ONNX	w8a16	Qualcomm® QCM6690	903.451 ms	103 - 109 MB	CPU
ResNet-Mixed-Convolution	ONNX	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	5.215 ms	1 - 192 MB	NPU
ResNet-Mixed-Convolution	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	871.987 ms	136 - 142 MB	CPU
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	4.646 ms	12 - 12 MB	NPU
ResNet-Mixed-Convolution	QNN_DLC	float	Snapdragon® X Elite	13.998 ms	2 - 2 MB	NPU
ResNet-Mixed-Convolution	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	9.545 ms	0 - 284 MB	NPU
ResNet-Mixed-Convolution	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	97.144 ms	1 - 223 MB	NPU
ResNet-Mixed-Convolution	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	13.208 ms	2 - 5 MB	NPU
ResNet-Mixed-Convolution	QNN_DLC	float	Qualcomm® SA8775P	25.07 ms	1 - 223 MB	NPU
ResNet-Mixed-Convolution	QNN_DLC	float	Qualcomm® QCS9075	27.827 ms	4 - 8 MB	NPU
ResNet-Mixed-Convolution	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	27.657 ms	0 - 240 MB	NPU
ResNet-Mixed-Convolution	QNN_DLC	float	Qualcomm® SA7255P	97.144 ms	1 - 223 MB	NPU
ResNet-Mixed-Convolution	QNN_DLC	float	Qualcomm® SA8295P	26.762 ms	0 - 194 MB	NPU
ResNet-Mixed-Convolution	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	7.622 ms	2 - 227 MB	NPU
ResNet-Mixed-Convolution	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	5.733 ms	2 - 233 MB	NPU
ResNet-Mixed-Convolution	QNN_DLC	float	Snapdragon® X2 Elite	7.684 ms	2 - 2 MB	NPU
ResNet-Mixed-Convolution	QNN_DLC	w8a16	Snapdragon® X Elite	9.806 ms	1 - 1 MB	NPU
ResNet-Mixed-Convolution	QNN_DLC	w8a16	Snapdragon® 8 Gen 3 Mobile	6.638 ms	1 - 256 MB	NPU
ResNet-Mixed-Convolution	QNN_DLC	w8a16	Qualcomm® QCS6490	37.23 ms	3 - 6 MB	NPU
ResNet-Mixed-Convolution	QNN_DLC	w8a16	Qualcomm® QCS8275 (Proxy)	29.752 ms	1 - 190 MB	NPU
ResNet-Mixed-Convolution	QNN_DLC	w8a16	Qualcomm® QCS8550 (Proxy)	9.152 ms	1 - 4 MB	NPU
ResNet-Mixed-Convolution	QNN_DLC	w8a16	Qualcomm® SA8775P	9.413 ms	1 - 191 MB	NPU
ResNet-Mixed-Convolution	QNN_DLC	w8a16	Qualcomm® QCS9075	10.394 ms	1 - 4 MB	NPU
ResNet-Mixed-Convolution	QNN_DLC	w8a16	Qualcomm® QCM6690	183.549 ms	1 - 209 MB	NPU
ResNet-Mixed-Convolution	QNN_DLC	w8a16	Qualcomm® QCS8450 (Proxy)	13.258 ms	1 - 253 MB	NPU
ResNet-Mixed-Convolution	QNN_DLC	w8a16	Qualcomm® SA7255P	29.752 ms	1 - 190 MB	NPU
ResNet-Mixed-Convolution	QNN_DLC	w8a16	Qualcomm® SA8295P	16.301 ms	1 - 192 MB	NPU
ResNet-Mixed-Convolution	QNN_DLC	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	5.263 ms	1 - 189 MB	NPU
ResNet-Mixed-Convolution	QNN_DLC	w8a16	Snapdragon® 7 Gen 4 Mobile	15.829 ms	1 - 197 MB	NPU
ResNet-Mixed-Convolution	QNN_DLC	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	4.008 ms	1 - 189 MB	NPU
ResNet-Mixed-Convolution	QNN_DLC	w8a16	Snapdragon® X2 Elite	5.374 ms	1 - 1 MB	NPU
ResNet-Mixed-Convolution	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	216.262 ms	0 - 314 MB	NPU
ResNet-Mixed-Convolution	TFLITE	float	Qualcomm® QCS8275 (Proxy)	585.629 ms	0 - 248 MB	NPU
ResNet-Mixed-Convolution	TFLITE	float	Qualcomm® QCS8550 (Proxy)	309.699 ms	0 - 3 MB	NPU
ResNet-Mixed-Convolution	TFLITE	float	Qualcomm® SA8775P	293.466 ms	0 - 249 MB	NPU
ResNet-Mixed-Convolution	TFLITE	float	Qualcomm® QCS8450 (Proxy)	334.839 ms	0 - 281 MB	NPU
ResNet-Mixed-Convolution	TFLITE	float	Qualcomm® SA7255P	585.629 ms	0 - 248 MB	NPU
ResNet-Mixed-Convolution	TFLITE	float	Qualcomm® SA8295P	358.637 ms	0 - 232 MB	NPU
ResNet-Mixed-Convolution	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	201.617 ms	0 - 255 MB	NPU
ResNet-Mixed-Convolution	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	198.394 ms	0 - 251 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.