PidNet: Optimized for Qualcomm Devices

PIDNet (Proportional-Integral-Derivative Network) is a real-time semantic segmentation model based on PID controllers

This is based on the implementation of PidNet 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	w8a8	Universal	QAIRT 2.42, ONNX Runtime 1.24.1	Download
QNN_DLC	float	Universal	QAIRT 2.43	Download
QNN_DLC	w8a8	Universal	QAIRT 2.43	Download
TFLITE	float	Universal	QAIRT 2.43, TFLite 2.17.0	Download
TFLITE	w8a8	Universal	QAIRT 2.43, TFLite 2.17.0	Download

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

Model Details

Model Type: Model_use_case.semantic_segmentation

Model Stats:

Model checkpoint: PIDNet_S_Cityscapes_val.pt
Inference latency: RealTime
Input resolution: 1024x2048
Number of output classes: 19
Number of parameters: 8.06M
Model size (float): 29.1 MB
Model size (w8a8): 8.02 MB

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
PidNet	ONNX	float	Snapdragon® X Elite	34.015 ms	24 - 24 MB	NPU
PidNet	ONNX	float	Snapdragon® 8 Gen 3 Mobile	24.112 ms	29 - 342 MB	NPU
PidNet	ONNX	float	Qualcomm® QCS8550 (Proxy)	35.064 ms	24 - 27 MB	NPU
PidNet	ONNX	float	Qualcomm® QCS9075	47.377 ms	24 - 51 MB	NPU
PidNet	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	17.658 ms	5 - 224 MB	NPU
PidNet	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	13.393 ms	30 - 298 MB	NPU
PidNet	ONNX	float	Snapdragon® X2 Elite	14.124 ms	22 - 22 MB	NPU
PidNet	ONNX	w8a8	Snapdragon® X Elite	87.113 ms	133 - 133 MB	NPU
PidNet	ONNX	w8a8	Snapdragon® 8 Gen 3 Mobile	45.811 ms	109 - 369 MB	NPU
PidNet	ONNX	w8a8	Qualcomm® QCS6490	387.425 ms	197 - 216 MB	CPU
PidNet	ONNX	w8a8	Qualcomm® QCS8550 (Proxy)	59.747 ms	103 - 107 MB	NPU
PidNet	ONNX	w8a8	Qualcomm® QCS9075	67.759 ms	104 - 107 MB	NPU
PidNet	ONNX	w8a8	Qualcomm® QCM6690	347.832 ms	162 - 170 MB	CPU
PidNet	ONNX	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	43.964 ms	103 - 314 MB	NPU
PidNet	ONNX	w8a8	Snapdragon® 7 Gen 4 Mobile	328.18 ms	214 - 223 MB	CPU
PidNet	ONNX	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	45.73 ms	109 - 334 MB	NPU
PidNet	ONNX	w8a8	Snapdragon® X2 Elite	46.995 ms	134 - 134 MB	NPU
PidNet	QNN_DLC	float	Snapdragon® X Elite	40.278 ms	24 - 24 MB	NPU
PidNet	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	27.05 ms	23 - 340 MB	NPU
PidNet	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	121.017 ms	24 - 244 MB	NPU
PidNet	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	39.08 ms	24 - 305 MB	NPU
PidNet	QNN_DLC	float	Qualcomm® SA8775P	48.162 ms	24 - 244 MB	NPU
PidNet	QNN_DLC	float	Qualcomm® QCS9075	61.73 ms	24 - 52 MB	NPU
PidNet	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	75.854 ms	0 - 330 MB	NPU
PidNet	QNN_DLC	float	Qualcomm® SA7255P	121.017 ms	24 - 244 MB	NPU
PidNet	QNN_DLC	float	Qualcomm® SA8295P	52.915 ms	24 - 260 MB	NPU
PidNet	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	19.303 ms	17 - 262 MB	NPU
PidNet	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	12.288 ms	14 - 285 MB	NPU
PidNet	QNN_DLC	float	Snapdragon® X2 Elite	13.939 ms	24 - 24 MB	NPU
PidNet	QNN_DLC	w8a8	Snapdragon® X Elite	60.437 ms	6 - 6 MB	NPU
PidNet	QNN_DLC	w8a8	Snapdragon® 8 Gen 3 Mobile	43.247 ms	6 - 271 MB	NPU
PidNet	QNN_DLC	w8a8	Qualcomm® QCS8275 (Proxy)	111.149 ms	6 - 217 MB	NPU
PidNet	QNN_DLC	w8a8	Qualcomm® QCS8550 (Proxy)	57.761 ms	6 - 39 MB	NPU
PidNet	QNN_DLC	w8a8	Qualcomm® SA8775P	58.412 ms	6 - 218 MB	NPU
PidNet	QNN_DLC	w8a8	Qualcomm® QCS9075	61.598 ms	6 - 14 MB	NPU
PidNet	QNN_DLC	w8a8	Qualcomm® QCS8450 (Proxy)	64.081 ms	6 - 271 MB	NPU
PidNet	QNN_DLC	w8a8	Qualcomm® SA7255P	111.149 ms	6 - 217 MB	NPU
PidNet	QNN_DLC	w8a8	Qualcomm® SA8295P	66.477 ms	6 - 220 MB	NPU
PidNet	QNN_DLC	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	41.449 ms	6 - 242 MB	NPU
PidNet	QNN_DLC	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	47.509 ms	6 - 270 MB	NPU
PidNet	QNN_DLC	w8a8	Snapdragon® X2 Elite	48.329 ms	6 - 6 MB	NPU
PidNet	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	26.686 ms	1 - 332 MB	NPU
PidNet	TFLITE	float	Qualcomm® QCS8275 (Proxy)	121.024 ms	3 - 232 MB	NPU
PidNet	TFLITE	float	Qualcomm® QCS8550 (Proxy)	39.163 ms	3 - 5 MB	NPU
PidNet	TFLITE	float	Qualcomm® SA8775P	48.049 ms	2 - 232 MB	NPU
PidNet	TFLITE	float	Qualcomm® QCS9075	61.728 ms	0 - 45 MB	NPU
PidNet	TFLITE	float	Qualcomm® QCS8450 (Proxy)	76.279 ms	2 - 341 MB	NPU
PidNet	TFLITE	float	Qualcomm® SA7255P	121.024 ms	3 - 232 MB	NPU
PidNet	TFLITE	float	Qualcomm® SA8295P	52.947 ms	2 - 244 MB	NPU
PidNet	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	19.493 ms	1 - 254 MB	NPU
PidNet	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	12.243 ms	2 - 276 MB	NPU
PidNet	TFLITE	w8a8	Snapdragon® 8 Gen 3 Mobile	38.024 ms	1 - 267 MB	NPU
PidNet	TFLITE	w8a8	Qualcomm® QCS6490	206.162 ms	3 - 73 MB	NPU
PidNet	TFLITE	w8a8	Qualcomm® QCS8275 (Proxy)	98.59 ms	1 - 212 MB	NPU
PidNet	TFLITE	w8a8	Qualcomm® QCS8550 (Proxy)	50.375 ms	1 - 3 MB	NPU
PidNet	TFLITE	w8a8	Qualcomm® SA8775P	242.178 ms	0 - 212 MB	NPU
PidNet	TFLITE	w8a8	Qualcomm® QCS9075	53.962 ms	1 - 17 MB	NPU
PidNet	TFLITE	w8a8	Qualcomm® QCM6690	237.035 ms	1 - 194 MB	NPU
PidNet	TFLITE	w8a8	Qualcomm® QCS8450 (Proxy)	58.806 ms	0 - 268 MB	NPU
PidNet	TFLITE	w8a8	Qualcomm® SA7255P	98.59 ms	1 - 212 MB	NPU
PidNet	TFLITE	w8a8	Qualcomm® SA8295P	58.306 ms	1 - 215 MB	NPU
PidNet	TFLITE	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	38.39 ms	1 - 234 MB	NPU
PidNet	TFLITE	w8a8	Snapdragon® 7 Gen 4 Mobile	67.192 ms	2 - 221 MB	NPU
PidNet	TFLITE	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	40.864 ms	1 - 264 MB	NPU

License

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

References

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.

Downloads last month: -; Downloads are not tracked for this model. How to track

Paper for qualcomm/PidNet

PIDNet: A Real-time Semantic Segmentation Network Inspired by PID Controllers

Paper • 2206.02066 • Published Jun 4, 2022