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® X2 Elite	4.213 ms	47 - 47 MB	NPU
FFNet-78S-LowRes	ONNX	float	Snapdragon® X Elite	8.211 ms	46 - 46 MB	NPU
FFNet-78S-LowRes	ONNX	float	Snapdragon® 8 Gen 3 Mobile	5.547 ms	3 - 208 MB	NPU
FFNet-78S-LowRes	ONNX	float	Qualcomm® QCS8550 (Proxy)	7.789 ms	6 - 9 MB	NPU
FFNet-78S-LowRes	ONNX	float	Qualcomm® QCS9075	12.703 ms	6 - 15 MB	NPU
FFNet-78S-LowRes	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	4.544 ms	2 - 170 MB	NPU
FFNet-78S-LowRes	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	3.833 ms	1 - 176 MB	NPU
FFNet-78S-LowRes	ONNX	w8a8	Snapdragon® X2 Elite	1.322 ms	25 - 25 MB	NPU
FFNet-78S-LowRes	ONNX	w8a8	Snapdragon® X Elite	2.967 ms	25 - 25 MB	NPU
FFNet-78S-LowRes	ONNX	w8a8	Snapdragon® 8 Gen 3 Mobile	1.982 ms	0 - 118 MB	NPU
FFNet-78S-LowRes	ONNX	w8a8	Qualcomm® QCS6490	109.341 ms	56 - 114 MB	CPU
FFNet-78S-LowRes	ONNX	w8a8	Qualcomm® QCS8550 (Proxy)	2.769 ms	0 - 37 MB	NPU
FFNet-78S-LowRes	ONNX	w8a8	Qualcomm® QCS9075	3.336 ms	1 - 4 MB	NPU
FFNet-78S-LowRes	ONNX	w8a8	Qualcomm® QCM6690	118.851 ms	66 - 76 MB	CPU
FFNet-78S-LowRes	ONNX	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	1.508 ms	0 - 62 MB	NPU
FFNet-78S-LowRes	ONNX	w8a8	Snapdragon® 7 Gen 4 Mobile	119.111 ms	58 - 68 MB	CPU
FFNet-78S-LowRes	ONNX	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	1.27 ms	0 - 63 MB	NPU
FFNet-78S-LowRes	QNN_DLC	float	Snapdragon® X2 Elite	7.628 ms	6 - 6 MB	NPU
FFNet-78S-LowRes	QNN_DLC	float	Snapdragon® X Elite	15.389 ms	6 - 6 MB	NPU
FFNet-78S-LowRes	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	9.775 ms	6 - 82 MB	NPU
FFNet-78S-LowRes	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	51.166 ms	1 - 42 MB	NPU
FFNet-78S-LowRes	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	14.628 ms	6 - 173 MB	NPU
FFNet-78S-LowRes	QNN_DLC	float	Qualcomm® SA8775P	19.177 ms	0 - 46 MB	NPU
FFNet-78S-LowRes	QNN_DLC	float	Qualcomm® QCS9075	18.317 ms	6 - 14 MB	NPU
FFNet-78S-LowRes	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	26.634 ms	6 - 73 MB	NPU
FFNet-78S-LowRes	QNN_DLC	float	Qualcomm® SA7255P	51.166 ms	1 - 42 MB	NPU
FFNet-78S-LowRes	QNN_DLC	float	Qualcomm® SA8295P	21.172 ms	0 - 40 MB	NPU
FFNet-78S-LowRes	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	8.128 ms	0 - 48 MB	NPU
FFNet-78S-LowRes	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	6.626 ms	5 - 54 MB	NPU
FFNet-78S-LowRes	QNN_DLC	w8a8	Snapdragon® X2 Elite	2.129 ms	2 - 2 MB	NPU
FFNet-78S-LowRes	QNN_DLC	w8a8	Snapdragon® X Elite	5.053 ms	2 - 2 MB	NPU
FFNet-78S-LowRes	QNN_DLC	w8a8	Snapdragon® 8 Gen 3 Mobile	3.303 ms	0 - 101 MB	NPU
FFNet-78S-LowRes	QNN_DLC	w8a8	Qualcomm® QCS6490	14.972 ms	4 - 7 MB	NPU
FFNet-78S-LowRes	QNN_DLC	w8a8	Qualcomm® QCS8275 (Proxy)	10.523 ms	1 - 55 MB	NPU
FFNet-78S-LowRes	QNN_DLC	w8a8	Qualcomm® QCS8550 (Proxy)	4.669 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	6.866 ms	0 - 4 MB	NPU
FFNet-78S-LowRes	QNN_DLC	w8a8	Qualcomm® QCM6690	36.692 ms	2 - 191 MB	NPU
FFNet-78S-LowRes	QNN_DLC	w8a8	Qualcomm® QCS8450 (Proxy)	7.177 ms	2 - 99 MB	NPU
FFNet-78S-LowRes	QNN_DLC	w8a8	Qualcomm® SA7255P	10.523 ms	1 - 55 MB	NPU
FFNet-78S-LowRes	QNN_DLC	w8a8	Qualcomm® SA8295P	6.559 ms	2 - 53 MB	NPU
FFNet-78S-LowRes	QNN_DLC	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	2.23 ms	2 - 52 MB	NPU
FFNet-78S-LowRes	QNN_DLC	w8a8	Snapdragon® 7 Gen 4 Mobile	7.314 ms	2 - 187 MB	NPU
FFNet-78S-LowRes	QNN_DLC	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	1.855 ms	2 - 57 MB	NPU
FFNet-78S-LowRes	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	9.904 ms	1 - 161 MB	NPU
FFNet-78S-LowRes	TFLITE	float	Qualcomm® QCS8275 (Proxy)	51.044 ms	1 - 78 MB	NPU
FFNet-78S-LowRes	TFLITE	float	Qualcomm® QCS8550 (Proxy)	14.67 ms	1 - 3 MB	NPU
FFNet-78S-LowRes	TFLITE	float	Qualcomm® SA8775P	19.213 ms	1 - 80 MB	NPU
FFNet-78S-LowRes	TFLITE	float	Qualcomm® QCS9075	17.627 ms	0 - 60 MB	NPU
FFNet-78S-LowRes	TFLITE	float	Qualcomm® QCS8450 (Proxy)	26.5 ms	1 - 150 MB	NPU
FFNet-78S-LowRes	TFLITE	float	Qualcomm® SA7255P	51.044 ms	1 - 78 MB	NPU
FFNet-78S-LowRes	TFLITE	float	Qualcomm® SA8295P	20.97 ms	1 - 69 MB	NPU
FFNet-78S-LowRes	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	8.177 ms	1 - 83 MB	NPU
FFNet-78S-LowRes	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	6.624 ms	1 - 81 MB	NPU
FFNet-78S-LowRes	TFLITE	w8a8	Snapdragon® 8 Gen 3 Mobile	1.977 ms	0 - 101 MB	NPU
FFNet-78S-LowRes	TFLITE	w8a8	Qualcomm® QCS6490	9.709 ms	0 - 30 MB	NPU
FFNet-78S-LowRes	TFLITE	w8a8	Qualcomm® QCS8275 (Proxy)	7.294 ms	0 - 52 MB	NPU
FFNet-78S-LowRes	TFLITE	w8a8	Qualcomm® QCS8550 (Proxy)	2.79 ms	0 - 6 MB	NPU
FFNet-78S-LowRes	TFLITE	w8a8	Qualcomm® SA8775P	3.283 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	27.584 ms	0 - 187 MB	NPU
FFNet-78S-LowRes	TFLITE	w8a8	Qualcomm® QCS8450 (Proxy)	3.526 ms	0 - 101 MB	NPU
FFNet-78S-LowRes	TFLITE	w8a8	Qualcomm® SA7255P	7.294 ms	0 - 52 MB	NPU
FFNet-78S-LowRes	TFLITE	w8a8	Qualcomm® SA8295P	4.432 ms	0 - 49 MB	NPU
FFNet-78S-LowRes	TFLITE	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	1.488 ms	0 - 54 MB	NPU
FFNet-78S-LowRes	TFLITE	w8a8	Snapdragon® 7 Gen 4 Mobile	4.173 ms	0 - 181 MB	NPU
FFNet-78S-LowRes	TFLITE	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	1.298 ms	0 - 53 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.