FFNet-78S-LowRes: Optimized for Qualcomm Devices

FFNet-78S-LowRes is a "fuss-free network" that segments street scene images with per-pixel classes like road, sidewalk, and pedestrian. Trained on the Cityscapes dataset.

This is based on the implementation of FFNet-78S-LowRes 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 FFNet-78S-LowRes 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 FFNet-78S-LowRes on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.semantic_segmentation

Model Stats:

• Model checkpoint: ffnet78S_BCC_cityscapes_state_dict_quarts_pre_down
• Input resolution: 1024x512
• Number of output classes: 19
• Number of parameters: 26.8M
• Model size (float): 102 MB
• Model size (w8a8): 26.0 MB

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
FFNet-78S-LowRes	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	3.837 ms	7 - 182 MB	NPU
FFNet-78S-LowRes	ONNX	float	Snapdragon® X2 Elite	4.275 ms	47 - 47 MB	NPU
FFNet-78S-LowRes	ONNX	float	Snapdragon® X Elite	8.172 ms	46 - 46 MB	NPU
FFNet-78S-LowRes	ONNX	float	Snapdragon® 8 Gen 3 Mobile	5.544 ms	3 - 209 MB	NPU
FFNet-78S-LowRes	ONNX	float	Qualcomm® QCS8550 (Proxy)	7.787 ms	0 - 52 MB	NPU
FFNet-78S-LowRes	ONNX	float	Qualcomm® QCS9075	12.785 ms	6 - 15 MB	NPU
FFNet-78S-LowRes	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	4.531 ms	3 - 170 MB	NPU
FFNet-78S-LowRes	ONNX	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	1.27 ms	0 - 61 MB	NPU
FFNet-78S-LowRes	ONNX	w8a8	Snapdragon® X2 Elite	1.32 ms	25 - 25 MB	NPU
FFNet-78S-LowRes	ONNX	w8a8	Snapdragon® X Elite	3.002 ms	25 - 25 MB	NPU
FFNet-78S-LowRes	ONNX	w8a8	Snapdragon® 8 Gen 3 Mobile	1.982 ms	2 - 120 MB	NPU
FFNet-78S-LowRes	ONNX	w8a8	Qualcomm® QCS6490	111.991 ms	56 - 114 MB	CPU
FFNet-78S-LowRes	ONNX	w8a8	Qualcomm® QCS8550 (Proxy)	2.774 ms	0 - 29 MB	NPU
FFNet-78S-LowRes	ONNX	w8a8	Qualcomm® QCS9075	3.315 ms	1 - 4 MB	NPU
FFNet-78S-LowRes	ONNX	w8a8	Qualcomm® QCM6690	118.539 ms	62 - 72 MB	CPU
FFNet-78S-LowRes	ONNX	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	1.509 ms	0 - 65 MB	NPU
FFNet-78S-LowRes	ONNX	w8a8	Snapdragon® 7 Gen 4 Mobile	119.316 ms	60 - 70 MB	CPU
FFNet-78S-LowRes	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	6.643 ms	6 - 54 MB	NPU
FFNet-78S-LowRes	QNN_DLC	float	Snapdragon® X2 Elite	7.627 ms	6 - 6 MB	NPU
FFNet-78S-LowRes	QNN_DLC	float	Snapdragon® X Elite	15.381 ms	6 - 6 MB	NPU
FFNet-78S-LowRes	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	9.788 ms	6 - 84 MB	NPU
FFNet-78S-LowRes	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	51.189 ms	2 - 45 MB	NPU
FFNet-78S-LowRes	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	14.598 ms	6 - 8 MB	NPU
FFNet-78S-LowRes	QNN_DLC	float	Qualcomm® SA8775P	19.17 ms	1 - 46 MB	NPU
FFNet-78S-LowRes	QNN_DLC	float	Qualcomm® QCS9075	18.403 ms	6 - 14 MB	NPU
FFNet-78S-LowRes	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	26.565 ms	6 - 75 MB	NPU
FFNet-78S-LowRes	QNN_DLC	float	Qualcomm® SA7255P	51.189 ms	2 - 45 MB	NPU
FFNet-78S-LowRes	QNN_DLC	float	Qualcomm® SA8295P	21.18 ms	0 - 34 MB	NPU
FFNet-78S-LowRes	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	8.123 ms	6 - 51 MB	NPU
FFNet-78S-LowRes	QNN_DLC	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	1.853 ms	2 - 55 MB	NPU
FFNet-78S-LowRes	QNN_DLC	w8a8	Snapdragon® X2 Elite	2.142 ms	2 - 2 MB	NPU
FFNet-78S-LowRes	QNN_DLC	w8a8	Snapdragon® X Elite	5.035 ms	2 - 2 MB	NPU
FFNet-78S-LowRes	QNN_DLC	w8a8	Snapdragon® 8 Gen 3 Mobile	3.305 ms	2 - 99 MB	NPU
FFNet-78S-LowRes	QNN_DLC	w8a8	Qualcomm® QCS6490	14.72 ms	4 - 7 MB	NPU
FFNet-78S-LowRes	QNN_DLC	w8a8	Qualcomm® QCS8275 (Proxy)	10.5 ms	2 - 56 MB	NPU
FFNet-78S-LowRes	QNN_DLC	w8a8	Qualcomm® QCS8550 (Proxy)	4.66 ms	2 - 3 MB	NPU
FFNet-78S-LowRes	QNN_DLC	w8a8	Qualcomm® SA8775P	22.264 ms	2 - 56 MB	NPU
FFNet-78S-LowRes	QNN_DLC	w8a8	Qualcomm® QCS9075	6.846 ms	2 - 5 MB	NPU
FFNet-78S-LowRes	QNN_DLC	w8a8	Qualcomm® QCM6690	36.585 ms	2 - 191 MB	NPU
FFNet-78S-LowRes	QNN_DLC	w8a8	Qualcomm® QCS8450 (Proxy)	7.183 ms	2 - 100 MB	NPU
FFNet-78S-LowRes	QNN_DLC	w8a8	Qualcomm® SA7255P	10.5 ms	2 - 56 MB	NPU
FFNet-78S-LowRes	QNN_DLC	w8a8	Qualcomm® SA8295P	6.553 ms	0 - 51 MB	NPU
FFNet-78S-LowRes	QNN_DLC	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	2.235 ms	2 - 57 MB	NPU
FFNet-78S-LowRes	QNN_DLC	w8a8	Snapdragon® 7 Gen 4 Mobile	7.31 ms	2 - 187 MB	NPU
FFNet-78S-LowRes	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	6.63 ms	1 - 81 MB	NPU
FFNet-78S-LowRes	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	9.872 ms	1 - 159 MB	NPU
FFNet-78S-LowRes	TFLITE	float	Qualcomm® QCS8275 (Proxy)	51.066 ms	1 - 78 MB	NPU
FFNet-78S-LowRes	TFLITE	float	Qualcomm® QCS8550 (Proxy)	14.734 ms	1 - 3 MB	NPU
FFNet-78S-LowRes	TFLITE	float	Qualcomm® SA8775P	19.263 ms	1 - 79 MB	NPU
FFNet-78S-LowRes	TFLITE	float	Qualcomm® QCS9075	17.657 ms	0 - 60 MB	NPU
FFNet-78S-LowRes	TFLITE	float	Qualcomm® QCS8450 (Proxy)	26.401 ms	1 - 148 MB	NPU
FFNet-78S-LowRes	TFLITE	float	Qualcomm® SA7255P	51.066 ms	1 - 78 MB	NPU
FFNet-78S-LowRes	TFLITE	float	Qualcomm® SA8295P	21.006 ms	0 - 73 MB	NPU
FFNet-78S-LowRes	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	8.176 ms	1 - 83 MB	NPU
FFNet-78S-LowRes	TFLITE	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	1.299 ms	0 - 53 MB	NPU
FFNet-78S-LowRes	TFLITE	w8a8	Snapdragon® 8 Gen 3 Mobile	1.978 ms	7 - 113 MB	NPU
FFNet-78S-LowRes	TFLITE	w8a8	Qualcomm® QCS6490	9.64 ms	0 - 30 MB	NPU
FFNet-78S-LowRes	TFLITE	w8a8	Qualcomm® QCS8275 (Proxy)	7.277 ms	0 - 52 MB	NPU
FFNet-78S-LowRes	TFLITE	w8a8	Qualcomm® QCS8550 (Proxy)	2.789 ms	0 - 9 MB	NPU
FFNet-78S-LowRes	TFLITE	w8a8	Qualcomm® SA8775P	3.282 ms	0 - 54 MB	NPU
FFNet-78S-LowRes	TFLITE	w8a8	Qualcomm® QCS9075	3.268 ms	0 - 30 MB	NPU
FFNet-78S-LowRes	TFLITE	w8a8	Qualcomm® QCM6690	30.993 ms	0 - 187 MB	NPU
FFNet-78S-LowRes	TFLITE	w8a8	Qualcomm® QCS8450 (Proxy)	3.512 ms	0 - 101 MB	NPU
FFNet-78S-LowRes	TFLITE	w8a8	Qualcomm® SA7255P	7.277 ms	0 - 52 MB	NPU
FFNet-78S-LowRes	TFLITE	w8a8	Qualcomm® SA8295P	4.43 ms	0 - 49 MB	NPU
FFNet-78S-LowRes	TFLITE	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	1.49 ms	0 - 55 MB	NPU
FFNet-78S-LowRes	TFLITE	w8a8	Snapdragon® 7 Gen 4 Mobile	4.203 ms	0 - 180 MB	NPU

License

• The license for the original implementation of FFNet-78S-LowRes can be found here.

References

• Simple and Efficient Architectures for Semantic Segmentation
• 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.