You can deploy this model and start earning money today!

qualcomm/
PSPNet

Views

No views yet

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 2.45, ONNX Runtime 1.27.1	Download
QNN_DLC	float	Universal	QAIRT 2.45	Download
TFLITE	float	Universal	QAIRT 2.45	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:

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

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
PSPNet	ONNX	float	Snapdragon® X2 Elite	832.612 ms	528 - 528 MB	NPU
PSPNet	ONNX	float	Snapdragon® X Elite	1335.437 ms	267 - 267 MB	NPU
PSPNet	ONNX	float	Snapdragon® 8 Gen 3 Mobile	954.711 ms	0 - 1844 MB	NPU
PSPNet	ONNX	float	Snapdragon® 8 Gen 1 Mobile	2247.017 ms	47 - 904 MB	NPU
PSPNet	ONNX	float	Qualcomm® Dragonwing™ IQ-8275	1394.431 ms	14 - 20 MB	NPU
PSPNet	ONNX	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	1143.919 ms	0 - 160 MB	NPU
PSPNet	ONNX	float	Qualcomm® QCS8450	2247.017 ms	47 - 904 MB	NPU
PSPNet	ONNX	float	Qualcomm® Dragonwing™ IQ-9075	1418.156 ms	8 - 13 MB	NPU
PSPNet	ONNX	float	Qualcomm® Dragonwing™ IQ-X7181	1335.437 ms	267 - 267 MB	NPU
PSPNet	ONNX	float	Qualcomm® Dragonwing™ Q-8750	651.51 ms	119 - 1591 MB	NPU
PSPNet	ONNX	float	Snapdragon® 8 Elite Mobile	651.51 ms	119 - 1591 MB	NPU
PSPNet	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	718.505 ms	135 - 1731 MB	NPU
PSPNet	QNN_DLC	float	Snapdragon® X2 Elite	2495.773 ms	3 - 3 MB	NPU
PSPNet	QNN_DLC	float	Snapdragon® X Elite	2538.555 ms	3 - 3 MB	NPU
PSPNet	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	1837.963 ms	55 - 1708 MB	NPU
PSPNet	QNN_DLC	float	Snapdragon® 8 Gen 1 Mobile	1601.931 ms	1 - 851 MB	NPU
PSPNet	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-8275	2523.411 ms	3 - 136 MB	NPU
PSPNet	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-8275	5283.318 ms	2 - 1307 MB	NPU
PSPNet	QNN_DLC	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	2494.466 ms	3 - 947 MB	NPU
PSPNet	QNN_DLC	float	Qualcomm® SA8775P	2615.805 ms	2 - 1307 MB	NPU
PSPNet	QNN_DLC	float	Qualcomm® SA8650P	2615.805 ms	2 - 1307 MB	NPU
PSPNet	QNN_DLC	float	Qualcomm® SA8255P	2615.805 ms	2 - 1307 MB	NPU
PSPNet	QNN_DLC	float	Qualcomm® QCS8450	1601.931 ms	1 - 851 MB	NPU
PSPNet	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-9075	3340.187 ms	5 - 137 MB	NPU
PSPNet	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-X7181	2538.555 ms	3 - 3 MB	NPU
PSPNet	QNN_DLC	float	Qualcomm® Dragonwing™ Q-8750	2168.014 ms	0 - 1311 MB	NPU
PSPNet	QNN_DLC	float	Qualcomm® SA7255P	5283.318 ms	2 - 1307 MB	NPU
PSPNet	QNN_DLC	float	Qualcomm® SA8295P	1365.366 ms	3 - 647 MB	NPU
PSPNet	QNN_DLC	float	Snapdragon® 8 Elite Mobile	2168.014 ms	0 - 1311 MB	NPU
PSPNet	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	2328.585 ms	0 - 1364 MB	NPU
PSPNet	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	2112.072 ms	127 - 1832 MB	NPU
PSPNet	TFLITE	float	Snapdragon® 8 Gen 1 Mobile	1877.964 ms	24 - 953 MB	NPU
PSPNet	TFLITE	float	Qualcomm® Dragonwing™ IQ-8275	2876.19 ms	0 - 276 MB	NPU
PSPNet	TFLITE	float	Qualcomm® Dragonwing™ IQ-8275	5954.347 ms	103 - 1502 MB	NPU
PSPNet	TFLITE	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	2811.238 ms	38 - 42 MB	NPU
PSPNet	TFLITE	float	Qualcomm® SA8775P	2961.091 ms	108 - 1506 MB	NPU
PSPNet	TFLITE	float	Qualcomm® SA8650P	2961.091 ms	108 - 1506 MB	NPU
PSPNet	TFLITE	float	Qualcomm® SA8255P	2961.091 ms	108 - 1506 MB	NPU
PSPNet	TFLITE	float	Qualcomm® QCS8450	1877.964 ms	24 - 953 MB	NPU
PSPNet	TFLITE	float	Qualcomm® Dragonwing™ IQ-9075	2933.881 ms	108 - 383 MB	NPU
PSPNet	TFLITE	float	Qualcomm® Dragonwing™ Q-8750	2168.575 ms	1 - 1408 MB	NPU
PSPNet	TFLITE	float	Qualcomm® SA7255P	5954.347 ms	103 - 1502 MB	NPU
PSPNet	TFLITE	float	Qualcomm® SA8295P	1418.676 ms	125 - 835 MB	NPU
PSPNet	TFLITE	float	Snapdragon® 8 Elite Mobile	2168.575 ms	1 - 1408 MB	NPU
PSPNet	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	2324.393 ms	0 - 1452 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.

qualcomm/PSPNet