PSPNet: Optimized for Qualcomm Devices

PSPNet (Pyramid Scene Parsing Network) is a semantic segmentation model that captures global context information by applying pyramid pooling modules. It is designed to improve scene understanding by aggregating contextual features at multiple scales.

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 2.37, ONNX Runtime 1.23.0	Download
QNN_DLC	float	Universal	QAIRT 2.42	Download
TFLITE	float	Universal	QAIRT 2.42, TFLite 2.17.0	Download

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

Model Details

Model Type: Model_use_case.semantic_segmentation

Model Stats:

• Model checkpoint: pspnet101_ade20k.pth
• Input resolution: 1x3x473x473
• Number of parameters: 65.7M
• Model size (float): 251 MB

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
PSPNet	ONNX	float	Snapdragon® X Elite	1029.088 ms	265 - 265 MB	NPU
PSPNet	ONNX	float	Snapdragon® 8 Gen 3 Mobile	1007.674 ms	11 - 732 MB	NPU
PSPNet	ONNX	float	Qualcomm® QCS8550 (Proxy)	1313.456 ms	0 - 160 MB	NPU
PSPNet	ONNX	float	Qualcomm® QCS9075	1788.258 ms	8 - 13 MB	NPU
PSPNet	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	972.45 ms	128 - 706 MB	NPU
PSPNet	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	1063.045 ms	11 - 605 MB	NPU
PSPNet	QNN_DLC	float	Snapdragon® X Elite	531.831 ms	3 - 3 MB	NPU
PSPNet	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	406.212 ms	3 - 875 MB	NPU
PSPNet	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	1333.575 ms	0 - 718 MB	NPU
PSPNet	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	584.235 ms	3 - 5 MB	NPU
PSPNet	QNN_DLC	float	Qualcomm® QCS9075	1751.221 ms	3 - 135 MB	NPU
PSPNet	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	1693.424 ms	0 - 430 MB	NPU
PSPNet	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	295.116 ms	3 - 719 MB	NPU
PSPNet	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	272.52 ms	3 - 733 MB	NPU
PSPNet	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	511.644 ms	127 - 1180 MB	NPU
PSPNet	TFLITE	float	Qualcomm® QCS8275 (Proxy)	1630.453 ms	126 - 960 MB	NPU
PSPNet	TFLITE	float	Qualcomm® QCS8550 (Proxy)	603.698 ms	128 - 131 MB	NPU
PSPNet	TFLITE	float	Qualcomm® QCS9075	1766.35 ms	0 - 272 MB	NPU
PSPNet	TFLITE	float	Qualcomm® QCS8450 (Proxy)	1561.127 ms	53 - 628 MB	NPU
PSPNet	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	977.818 ms	116 - 871 MB	NPU
PSPNet	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	323.794 ms	0 - 836 MB	NPU

License

• The license for the original implementation of PSPNet can be found here.

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.