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 1.24.3	Download
ONNX	w8a8	Universal	QAIRT 2.42, ONNX Runtime 1.24.3	Download
QNN_DLC	float	Universal	QAIRT 2.43	Download
QNN_DLC	w8a8	Universal	QAIRT 2.43	Download
TFLITE	float	Universal	QAIRT 2.43, TFLite 2.19.1	Download
TFLITE	w8a8	Universal	QAIRT 2.43, TFLite 2.19.1	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	3.823 ms	14 - 189 MB	NPU
FFNet-78S-LowRes	ONNX	float	Snapdragon® X2 Elite	4.239 ms	47 - 47 MB	NPU
FFNet-78S-LowRes	ONNX	float	Snapdragon® X Elite	8.194 ms	46 - 46 MB	NPU
FFNet-78S-LowRes	ONNX	float	Snapdragon® 8 Gen 3 Mobile	5.554 ms	1 - 206 MB	NPU
FFNet-78S-LowRes	ONNX	float	Qualcomm® QCS8550 (Proxy)	7.811 ms	0 - 52 MB	NPU
FFNet-78S-LowRes	ONNX	float	Qualcomm® QCS9075	13.066 ms	6 - 15 MB	NPU
FFNet-78S-LowRes	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	4.549 ms	2 - 170 MB	NPU
FFNet-78S-LowRes	ONNX	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	1.271 ms	0 - 61 MB	NPU
FFNet-78S-LowRes	ONNX	w8a8	Snapdragon® X2 Elite	1.316 ms	25 - 25 MB	NPU
FFNet-78S-LowRes	ONNX	w8a8	Snapdragon® X Elite	2.977 ms	25 - 25 MB	NPU
FFNet-78S-LowRes	ONNX	w8a8	Snapdragon® 8 Gen 3 Mobile	1.983 ms	0 - 116 MB	NPU
FFNet-78S-LowRes	ONNX	w8a8	Qualcomm® QCS6490	109.301 ms	56 - 116 MB	CPU
FFNet-78S-LowRes	ONNX	w8a8	Qualcomm® QCS8550 (Proxy)	2.767 ms	0 - 30 MB	NPU
FFNet-78S-LowRes	ONNX	w8a8	Qualcomm® QCS9075	3.324 ms	1 - 4 MB	NPU
FFNet-78S-LowRes	ONNX	w8a8	Qualcomm® QCM6690	118.786 ms	62 - 72 MB	CPU
FFNet-78S-LowRes	ONNX	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	1.504 ms	0 - 63 MB	NPU
FFNet-78S-LowRes	ONNX	w8a8	Snapdragon® 7 Gen 4 Mobile	119.009 ms	62 - 72 MB	CPU
FFNet-78S-LowRes	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	6.63 ms	6 - 54 MB	NPU
FFNet-78S-LowRes	QNN_DLC	float	Snapdragon® X2 Elite	7.638 ms	6 - 6 MB	NPU
FFNet-78S-LowRes	QNN_DLC	float	Snapdragon® X Elite	15.4 ms	6 - 6 MB	NPU
FFNet-78S-LowRes	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	9.762 ms	6 - 84 MB	NPU
FFNet-78S-LowRes	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	51.188 ms	2 - 45 MB	NPU
FFNet-78S-LowRes	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	14.568 ms	6 - 150 MB	NPU
FFNet-78S-LowRes	QNN_DLC	float	Qualcomm® SA8775P	19.136 ms	0 - 44 MB	NPU
FFNet-78S-LowRes	QNN_DLC	float	Qualcomm® QCS9075	18.281 ms	6 - 14 MB	NPU
FFNet-78S-LowRes	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	26.567 ms	6 - 73 MB	NPU
FFNet-78S-LowRes	QNN_DLC	float	Qualcomm® SA7255P	51.188 ms	2 - 45 MB	NPU
FFNet-78S-LowRes	QNN_DLC	float	Qualcomm® SA8295P	21.16 ms	0 - 35 MB	NPU
FFNet-78S-LowRes	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	8.122 ms	0 - 45 MB	NPU
FFNet-78S-LowRes	QNN_DLC	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	1.856 ms	2 - 56 MB	NPU
FFNet-78S-LowRes	QNN_DLC	w8a8	Snapdragon® X2 Elite	2.153 ms	2 - 2 MB	NPU
FFNet-78S-LowRes	QNN_DLC	w8a8	Snapdragon® X Elite	5.02 ms	2 - 2 MB	NPU
FFNet-78S-LowRes	QNN_DLC	w8a8	Snapdragon® 8 Gen 3 Mobile	3.301 ms	2 - 102 MB	NPU
FFNet-78S-LowRes	QNN_DLC	w8a8	Qualcomm® QCS6490	14.819 ms	2 - 5 MB	NPU
FFNet-78S-LowRes	QNN_DLC	w8a8	Qualcomm® QCS8275 (Proxy)	10.515 ms	2 - 55 MB	NPU
FFNet-78S-LowRes	QNN_DLC	w8a8	Qualcomm® QCS8550 (Proxy)	4.666 ms	2 - 3 MB	NPU
FFNet-78S-LowRes	QNN_DLC	w8a8	Qualcomm® SA8775P	5.163 ms	2 - 57 MB	NPU
FFNet-78S-LowRes	QNN_DLC	w8a8	Qualcomm® QCS9075	6.842 ms	2 - 5 MB	NPU
FFNet-78S-LowRes	QNN_DLC	w8a8	Qualcomm® QCM6690	35.565 ms	2 - 189 MB	NPU
FFNet-78S-LowRes	QNN_DLC	w8a8	Qualcomm® QCS8450 (Proxy)	7.171 ms	2 - 104 MB	NPU
FFNet-78S-LowRes	QNN_DLC	w8a8	Qualcomm® SA7255P	10.515 ms	2 - 55 MB	NPU
FFNet-78S-LowRes	QNN_DLC	w8a8	Qualcomm® SA8295P	6.59 ms	2 - 53 MB	NPU
FFNet-78S-LowRes	QNN_DLC	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	2.234 ms	2 - 53 MB	NPU
FFNet-78S-LowRes	QNN_DLC	w8a8	Snapdragon® 7 Gen 4 Mobile	7.345 ms	2 - 184 MB	NPU
FFNet-78S-LowRes	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	6.629 ms	1 - 81 MB	NPU
FFNet-78S-LowRes	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	9.888 ms	0 - 159 MB	NPU
FFNet-78S-LowRes	TFLITE	float	Qualcomm® QCS8275 (Proxy)	51.069 ms	1 - 78 MB	NPU
FFNet-78S-LowRes	TFLITE	float	Qualcomm® QCS8550 (Proxy)	14.708 ms	1 - 3 MB	NPU
FFNet-78S-LowRes	TFLITE	float	Qualcomm® SA8775P	19.23 ms	1 - 79 MB	NPU
FFNet-78S-LowRes	TFLITE	float	Qualcomm® QCS9075	17.629 ms	0 - 60 MB	NPU
FFNet-78S-LowRes	TFLITE	float	Qualcomm® QCS8450 (Proxy)	26.323 ms	1 - 151 MB	NPU
FFNet-78S-LowRes	TFLITE	float	Qualcomm® SA7255P	51.069 ms	1 - 78 MB	NPU
FFNet-78S-LowRes	TFLITE	float	Qualcomm® SA8295P	20.986 ms	1 - 74 MB	NPU
FFNet-78S-LowRes	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	8.174 ms	1 - 83 MB	NPU
FFNet-78S-LowRes	TFLITE	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	1.299 ms	0 - 54 MB	NPU
FFNet-78S-LowRes	TFLITE	w8a8	Snapdragon® 8 Gen 3 Mobile	1.976 ms	0 - 105 MB	NPU
FFNet-78S-LowRes	TFLITE	w8a8	Qualcomm® QCS6490	9.312 ms	0 - 30 MB	NPU
FFNet-78S-LowRes	TFLITE	w8a8	Qualcomm® QCS8275 (Proxy)	7.291 ms	0 - 52 MB	NPU
FFNet-78S-LowRes	TFLITE	w8a8	Qualcomm® QCS8550 (Proxy)	2.791 ms	0 - 2 MB	NPU
FFNet-78S-LowRes	TFLITE	w8a8	Qualcomm® SA8775P	3.267 ms	0 - 54 MB	NPU
FFNet-78S-LowRes	TFLITE	w8a8	Qualcomm® QCS9075	3.267 ms	0 - 30 MB	NPU
FFNet-78S-LowRes	TFLITE	w8a8	Qualcomm® QCM6690	29.499 ms	0 - 184 MB	NPU
FFNet-78S-LowRes	TFLITE	w8a8	Qualcomm® QCS8450 (Proxy)	3.526 ms	0 - 101 MB	NPU
FFNet-78S-LowRes	TFLITE	w8a8	Qualcomm® SA7255P	7.291 ms	0 - 52 MB	NPU
FFNet-78S-LowRes	TFLITE	w8a8	Qualcomm® SA8295P	4.439 ms	0 - 50 MB	NPU
FFNet-78S-LowRes	TFLITE	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	1.494 ms	0 - 49 MB	NPU
FFNet-78S-LowRes	TFLITE	w8a8	Snapdragon® 7 Gen 4 Mobile	4.188 ms	0 - 181 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.