Hugging Face's logo

qualcomm
/
FFNet-78S

Image Segmentation
PyTorch
android
Model card Files
xet
 Community

FFNet-78S: Optimized for Qualcomm Devices

FFNet-78S 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 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 2.45 Download
QNN_DLC w8a8 Universal QAIRT 2.45 Download
TFLITE float Universal QAIRT 2.45 Download
TFLITE w8a8 Universal QAIRT 2.45 Download

For more device-specific assets and performance metrics, visit FFNet-78S 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 on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.semantic_segmentation

Model Stats:

  • Model checkpoint: ffnet78S_dBBB_cityscapes_state_dict_quarts
  • Input resolution: 2048x1024
  • Number of output classes: 19
  • Number of parameters: 27.5M
  • Model size (float): 105 MB
  • Model size (w8a8): 26.7 MB

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
FFNet-78S ONNX float Snapdragon® 8 Elite Gen 5 Mobile 17.331 ms 29 - 258 MB NPU
FFNet-78S ONNX float Snapdragon® 8 Elite Mobile 20.164 ms 5 - 209 MB NPU
FFNet-78S ONNX float Snapdragon® X2 Elite 18.11 ms 30 - 30 MB NPU
FFNet-78S ONNX float Snapdragon® X Elite 37.783 ms 30 - 30 MB NPU
FFNet-78S ONNX float Snapdragon® X Elite 37.783 ms 30 - 30 MB NPU
FFNet-78S ONNX float Snapdragon® 8 Gen 3 Mobile 27.096 ms 5 - 310 MB NPU
FFNet-78S ONNX float Qualcomm® QCS8550 (Proxy) 38.12 ms 24 - 55 MB NPU
FFNet-78S ONNX float Qualcomm® QCS9075 59.529 ms 24 - 51 MB NPU
FFNet-78S ONNX float Snapdragon® 8 Elite For Galaxy Mobile 20.164 ms 5 - 209 MB NPU
FFNet-78S ONNX w8a8 Snapdragon® 8 Elite Gen 5 Mobile 7.286 ms 2 - 221 MB NPU
FFNet-78S ONNX w8a8 Snapdragon® 8 Elite Mobile 8.798 ms 1 - 213 MB NPU
FFNet-78S ONNX w8a8 Snapdragon® X2 Elite 7.927 ms 22 - 22 MB NPU
FFNet-78S ONNX w8a8 Snapdragon® X Elite 14.856 ms 21 - 21 MB NPU
FFNet-78S ONNX w8a8 Snapdragon® X Elite 14.856 ms 21 - 21 MB NPU
FFNet-78S ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 11.627 ms 7 - 297 MB NPU
FFNet-78S ONNX w8a8 Qualcomm® QCS6490 487.616 ms 162 - 229 MB CPU
FFNet-78S ONNX w8a8 Qualcomm® QCS8550 (Proxy) 15.366 ms 0 - 24 MB NPU
FFNet-78S ONNX w8a8 Qualcomm® QCS9075 14.492 ms 6 - 9 MB NPU
FFNet-78S ONNX w8a8 Qualcomm® QCM6690 535.944 ms 139 - 149 MB CPU
FFNet-78S ONNX w8a8 Snapdragon® 8 Elite For Galaxy Mobile 8.798 ms 1 - 213 MB NPU
FFNet-78S ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 534.417 ms 175 - 185 MB CPU
FFNet-78S ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 534.417 ms 175 - 185 MB CPU
FFNet-78S QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 15.436 ms 24 - 274 MB NPU
FFNet-78S QNN_DLC float Snapdragon® 8 Elite Mobile 21.756 ms 14 - 243 MB NPU
FFNet-78S QNN_DLC float Snapdragon® X2 Elite 18.005 ms 24 - 24 MB NPU
FFNet-78S QNN_DLC float Snapdragon® X Elite 44.191 ms 24 - 24 MB NPU
FFNet-78S QNN_DLC float Snapdragon® X Elite 44.191 ms 24 - 24 MB NPU
FFNet-78S QNN_DLC float Snapdragon® 8 Gen 3 Mobile 29.233 ms 0 - 298 MB NPU
FFNet-78S QNN_DLC float Qualcomm® QCS8275 (Proxy) 187.964 ms 24 - 234 MB NPU
FFNet-78S QNN_DLC float Qualcomm® QCS8550 (Proxy) 42.746 ms 24 - 26 MB NPU
FFNet-78S QNN_DLC float Qualcomm® SA8775P 60.874 ms 24 - 235 MB NPU
FFNet-78S QNN_DLC float Qualcomm® SA8775P 60.874 ms 24 - 235 MB NPU
FFNet-78S QNN_DLC float Qualcomm® SA8775P 60.874 ms 24 - 235 MB NPU
FFNet-78S QNN_DLC float Qualcomm® QCS9075 73.756 ms 24 - 52 MB NPU
FFNet-78S QNN_DLC float Qualcomm® QCS8450 (Proxy) 85.9 ms 3 - 285 MB NPU
FFNet-78S QNN_DLC float Qualcomm® SA7255P 187.964 ms 24 - 234 MB NPU
FFNet-78S QNN_DLC float Qualcomm® SA8295P 66.531 ms 24 - 228 MB NPU
FFNet-78S QNN_DLC float Snapdragon® 8 Elite For Galaxy Mobile 21.756 ms 14 - 243 MB NPU
FFNet-78S QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 Mobile 5.883 ms 6 - 251 MB NPU
FFNet-78S QNN_DLC w8a8 Snapdragon® 8 Elite Mobile 8.068 ms 6 - 239 MB NPU
FFNet-78S QNN_DLC w8a8 Snapdragon® X2 Elite 7.019 ms 6 - 6 MB NPU
FFNet-78S QNN_DLC w8a8 Snapdragon® X Elite 17.726 ms 6 - 6 MB NPU
FFNet-78S QNN_DLC w8a8 Snapdragon® X Elite 17.726 ms 6 - 6 MB NPU
FFNet-78S QNN_DLC w8a8 Snapdragon® 8 Gen 3 Mobile 11.631 ms 6 - 289 MB NPU
FFNet-78S QNN_DLC w8a8 Qualcomm® QCS6490 72.868 ms 3 - 11 MB NPU
FFNet-78S QNN_DLC w8a8 Qualcomm® QCS8275 (Proxy) 39.078 ms 6 - 225 MB NPU
FFNet-78S QNN_DLC w8a8 Qualcomm® QCS8550 (Proxy) 16.825 ms 6 - 36 MB NPU
FFNet-78S QNN_DLC w8a8 Qualcomm® SA8775P 17.188 ms 6 - 226 MB NPU
FFNet-78S QNN_DLC w8a8 Qualcomm® SA8775P 17.188 ms 6 - 226 MB NPU
FFNet-78S QNN_DLC w8a8 Qualcomm® SA8775P 17.188 ms 6 - 226 MB NPU
FFNet-78S QNN_DLC w8a8 Qualcomm® QCS9075 19.874 ms 6 - 14 MB NPU
FFNet-78S QNN_DLC w8a8 Qualcomm® QCM6690 163.694 ms 6 - 254 MB NPU
FFNet-78S QNN_DLC w8a8 Qualcomm® QCS8450 (Proxy) 23.832 ms 6 - 291 MB NPU
FFNet-78S QNN_DLC w8a8 Qualcomm® SA7255P 39.078 ms 6 - 225 MB NPU
FFNet-78S QNN_DLC w8a8 Qualcomm® SA8295P 23.305 ms 6 - 227 MB NPU
FFNet-78S QNN_DLC w8a8 Snapdragon® 8 Elite For Galaxy Mobile 8.068 ms 6 - 239 MB NPU
FFNet-78S QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 22.331 ms 6 - 243 MB NPU
FFNet-78S QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 22.331 ms 6 - 243 MB NPU
FFNet-78S TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 15.505 ms 0 - 279 MB NPU
FFNet-78S TFLITE float Snapdragon® 8 Elite Mobile 21.734 ms 1 - 262 MB NPU
FFNet-78S TFLITE float Snapdragon® 8 Gen 3 Mobile 29.637 ms 2 - 378 MB NPU
FFNet-78S TFLITE float Qualcomm® QCS8275 (Proxy) 187.995 ms 3 - 245 MB NPU
FFNet-78S TFLITE float Qualcomm® QCS8550 (Proxy) 42.788 ms 2 - 5 MB NPU
FFNet-78S TFLITE float Qualcomm® SA8775P 60.979 ms 2 - 245 MB NPU
FFNet-78S TFLITE float Qualcomm® SA8775P 60.979 ms 2 - 245 MB NPU
FFNet-78S TFLITE float Qualcomm® SA8775P 60.979 ms 2 - 245 MB NPU
FFNet-78S TFLITE float Qualcomm® QCS9075 73.546 ms 0 - 82 MB NPU
FFNet-78S TFLITE float Qualcomm® QCS8450 (Proxy) 87.08 ms 3 - 363 MB NPU
FFNet-78S TFLITE float Qualcomm® SA7255P 187.995 ms 3 - 245 MB NPU
FFNet-78S TFLITE float Qualcomm® SA8295P 66.446 ms 2 - 241 MB NPU
FFNet-78S TFLITE float Snapdragon® 8 Elite For Galaxy Mobile 21.734 ms 1 - 262 MB NPU
FFNet-78S TFLITE w8a8 Snapdragon® 8 Elite Gen 5 Mobile 3.578 ms 1 - 244 MB NPU
FFNet-78S TFLITE w8a8 Snapdragon® 8 Elite Mobile 5.031 ms 0 - 233 MB NPU
FFNet-78S TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 6.45 ms 1 - 290 MB NPU
FFNet-78S TFLITE w8a8 Qualcomm® QCS6490 57.317 ms 1 - 36 MB NPU
FFNet-78S TFLITE w8a8 Qualcomm® QCS8275 (Proxy) 26.244 ms 1 - 218 MB NPU
FFNet-78S TFLITE w8a8 Qualcomm® QCS8550 (Proxy) 9.099 ms 1 - 3 MB NPU
FFNet-78S TFLITE w8a8 Qualcomm® SA8775P 9.731 ms 1 - 219 MB NPU
FFNet-78S TFLITE w8a8 Qualcomm® SA8775P 9.731 ms 1 - 219 MB NPU
FFNet-78S TFLITE w8a8 Qualcomm® SA8775P 9.731 ms 1 - 219 MB NPU
FFNet-78S TFLITE w8a8 Qualcomm® QCS9075 11.162 ms 1 - 36 MB NPU
FFNet-78S TFLITE w8a8 Qualcomm® QCM6690 139.264 ms 1 - 248 MB NPU
FFNet-78S TFLITE w8a8 Qualcomm® QCS8450 (Proxy) 18.378 ms 1 - 291 MB NPU
FFNet-78S TFLITE w8a8 Qualcomm® SA7255P 26.244 ms 1 - 218 MB NPU
FFNet-78S TFLITE w8a8 Qualcomm® SA8295P 14.848 ms 1 - 222 MB NPU
FFNet-78S TFLITE w8a8 Snapdragon® 8 Elite For Galaxy Mobile 5.031 ms 0 - 233 MB NPU
FFNet-78S TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 14.614 ms 1 - 234 MB NPU
FFNet-78S TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 14.614 ms 1 - 234 MB NPU

License

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

References

Community

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
Image Segmentation
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Paper for qualcomm/FFNet-78S