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 2.45, ONNX Runtime 1.27.1 Download
ONNX w8a8 Universal QAIRT 2.45, ONNX Runtime 1.27.1 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:

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

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
FFNet-78S ONNX float Snapdragon® X2 Elite 18.598 ms 24 - 24 MB NPU
FFNet-78S ONNX float Snapdragon® X Elite 37.94 ms 31 - 31 MB NPU
FFNet-78S ONNX float Snapdragon® 8 Gen 3 Mobile 27.105 ms 29 - 346 MB NPU
FFNet-78S ONNX float Snapdragon® 8 Gen 1 Mobile 60.273 ms 13 - 294 MB NPU
FFNet-78S ONNX float Qualcomm® Dragonwing™ IQ-8275 58.076 ms 24 - 51 MB NPU
FFNet-78S ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 37.904 ms 25 - 69 MB NPU
FFNet-78S ONNX float Qualcomm® QCS8450 60.273 ms 13 - 294 MB NPU
FFNet-78S ONNX float Qualcomm® Dragonwing™ IQ-9075 56.791 ms 24 - 51 MB NPU
FFNet-78S ONNX float Qualcomm® Dragonwing™ IQ-X7181 37.94 ms 31 - 31 MB NPU
FFNet-78S ONNX float Qualcomm® Dragonwing™ Q-8750 21.29 ms 8 - 206 MB NPU
FFNet-78S ONNX float Snapdragon® 8 Elite Mobile 21.29 ms 8 - 206 MB NPU
FFNet-78S ONNX float Snapdragon® 8 Elite Gen 5 Mobile 17.874 ms 5 - 228 MB NPU
FFNet-78S ONNX w8a8 Snapdragon® X2 Elite 7.964 ms 7 - 7 MB NPU
FFNet-78S ONNX w8a8 Snapdragon® X Elite 13.392 ms 22 - 22 MB NPU
FFNet-78S ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 8.539 ms 7 - 299 MB NPU
FFNet-78S ONNX w8a8 Snapdragon® 8 Gen 1 Mobile 17.729 ms 7 - 299 MB NPU
FFNet-78S ONNX w8a8 Qualcomm® Dragonwing™ QCS6490 56.496 ms 6 - 9 MB NPU
FFNet-78S ONNX w8a8 Qualcomm® Dragonwing™ IQ-8275 12.899 ms 6 - 10 MB NPU
FFNet-78S ONNX w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 12.836 ms 0 - 36 MB NPU
FFNet-78S ONNX w8a8 Qualcomm® QCS8450 17.729 ms 7 - 299 MB NPU
FFNet-78S ONNX w8a8 Qualcomm® Dragonwing™ IQ-9075 13.193 ms 6 - 9 MB NPU
FFNet-78S ONNX w8a8 Qualcomm® Dragonwing™ IQ-X7181 13.392 ms 22 - 22 MB NPU
FFNet-78S ONNX w8a8 Qualcomm® Dragonwing™ Q-6690 153.379 ms 6 - 237 MB NPU
FFNet-78S ONNX w8a8 Qualcomm® Dragonwing™ Q-7790 17.83 ms 7 - 256 MB NPU
FFNet-78S ONNX w8a8 Qualcomm® Dragonwing™ Q-8750 8.766 ms 1 - 215 MB NPU
FFNet-78S ONNX w8a8 Snapdragon® 8 Elite Mobile 8.766 ms 1 - 215 MB NPU
FFNet-78S ONNX w8a8 Snapdragon® 8 Elite Gen 5 Mobile 7.409 ms 2 - 220 MB NPU
FFNet-78S ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 17.83 ms 7 - 256 MB NPU
FFNet-78S QNN_DLC float Snapdragon® X2 Elite 18.091 ms 24 - 24 MB NPU
FFNet-78S QNN_DLC float Snapdragon® X Elite 44.223 ms 24 - 24 MB NPU
FFNet-78S QNN_DLC float Snapdragon® 8 Gen 3 Mobile 29.446 ms 24 - 325 MB NPU
FFNet-78S QNN_DLC float Snapdragon® 8 Gen 1 Mobile 85.773 ms 4 - 287 MB NPU
FFNet-78S QNN_DLC float Qualcomm® Dragonwing™ IQ-8275 62.81 ms 24 - 53 MB NPU
FFNet-78S QNN_DLC float Qualcomm® Dragonwing™ IQ-8275 188.077 ms 24 - 234 MB NPU
FFNet-78S QNN_DLC float Qualcomm® Dragonwing™ QCS8550 (Proxy) 42.927 ms 24 - 27 MB NPU
FFNet-78S QNN_DLC float Qualcomm® SA8775P 60.867 ms 24 - 234 MB NPU
FFNet-78S QNN_DLC float Qualcomm® SA8650P 60.867 ms 24 - 234 MB NPU
FFNet-78S QNN_DLC float Qualcomm® SA8255P 60.867 ms 24 - 234 MB NPU
FFNet-78S QNN_DLC float Qualcomm® QCS8450 85.773 ms 4 - 287 MB NPU
FFNet-78S QNN_DLC float Qualcomm® Dragonwing™ IQ-9075 61.747 ms 26 - 54 MB NPU
FFNet-78S QNN_DLC float Qualcomm® Dragonwing™ IQ-X7181 44.223 ms 24 - 24 MB NPU
FFNet-78S QNN_DLC float Qualcomm® Dragonwing™ Q-8750 21.69 ms 14 - 242 MB NPU
FFNet-78S QNN_DLC float Qualcomm® SA7255P 188.077 ms 24 - 234 MB NPU
FFNet-78S QNN_DLC float Qualcomm® SA8295P 66.524 ms 24 - 228 MB NPU
FFNet-78S QNN_DLC float Snapdragon® 8 Elite Mobile 21.69 ms 14 - 242 MB NPU
FFNet-78S QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 15.696 ms 9 - 261 MB NPU
FFNet-78S QNN_DLC w8a8 Snapdragon® X2 Elite 7.036 ms 6 - 6 MB NPU
FFNet-78S QNN_DLC w8a8 Snapdragon® X Elite 17.797 ms 6 - 6 MB NPU
FFNet-78S QNN_DLC w8a8 Snapdragon® 8 Gen 3 Mobile 11.598 ms 6 - 294 MB NPU
FFNet-78S QNN_DLC w8a8 Snapdragon® 8 Gen 1 Mobile 23.669 ms 6 - 291 MB NPU
FFNet-78S QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS6490 64.118 ms 6 - 14 MB NPU
FFNet-78S QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-8275 16.58 ms 6 - 15 MB NPU
FFNet-78S QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-8275 39.079 ms 6 - 226 MB NPU
FFNet-78S QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 16.74 ms 6 - 177 MB NPU
FFNet-78S QNN_DLC w8a8 Qualcomm® SA8775P 17.202 ms 6 - 226 MB NPU
FFNet-78S QNN_DLC w8a8 Qualcomm® SA8650P 17.202 ms 6 - 226 MB NPU
FFNet-78S QNN_DLC w8a8 Qualcomm® SA8255P 17.202 ms 6 - 226 MB NPU
FFNet-78S QNN_DLC w8a8 Qualcomm® QCS8450 23.669 ms 6 - 291 MB NPU
FFNet-78S QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-9075 18.586 ms 6 - 14 MB NPU
FFNet-78S QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-X7181 17.797 ms 6 - 6 MB NPU
FFNet-78S QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-6690 165.576 ms 6 - 253 MB NPU
FFNet-78S QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-7790 22.229 ms 6 - 243 MB NPU
FFNet-78S QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-8750 8.075 ms 6 - 239 MB NPU
FFNet-78S QNN_DLC w8a8 Qualcomm® SA7255P 39.079 ms 6 - 226 MB NPU
FFNet-78S QNN_DLC w8a8 Qualcomm® SA8295P 23.332 ms 6 - 227 MB NPU
FFNet-78S QNN_DLC w8a8 Snapdragon® 8 Elite Mobile 8.075 ms 6 - 239 MB NPU
FFNet-78S QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 Mobile 5.961 ms 6 - 251 MB NPU
FFNet-78S QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 22.229 ms 6 - 243 MB NPU
FFNet-78S TFLITE float Snapdragon® 8 Gen 3 Mobile 29.442 ms 2 - 377 MB NPU
FFNet-78S TFLITE float Snapdragon® 8 Gen 1 Mobile 85.714 ms 3 - 363 MB NPU
FFNet-78S TFLITE float Qualcomm® Dragonwing™ IQ-8275 62.954 ms 0 - 83 MB NPU
FFNet-78S TFLITE float Qualcomm® Dragonwing™ IQ-8275 188.007 ms 3 - 245 MB NPU
FFNet-78S TFLITE float Qualcomm® Dragonwing™ QCS8550 (Proxy) 42.859 ms 3 - 5 MB NPU
FFNet-78S TFLITE float Qualcomm® SA8775P 61.012 ms 3 - 245 MB NPU
FFNet-78S TFLITE float Qualcomm® SA8650P 61.012 ms 3 - 245 MB NPU
FFNet-78S TFLITE float Qualcomm® SA8255P 61.012 ms 3 - 245 MB NPU
FFNet-78S TFLITE float Qualcomm® QCS8450 85.714 ms 3 - 363 MB NPU
FFNet-78S TFLITE float Qualcomm® Dragonwing™ IQ-9075 61.892 ms 0 - 82 MB NPU
FFNet-78S TFLITE float Qualcomm® Dragonwing™ Q-8750 21.702 ms 0 - 257 MB NPU
FFNet-78S TFLITE float Qualcomm® SA7255P 188.007 ms 3 - 245 MB NPU
FFNet-78S TFLITE float Qualcomm® SA8295P 66.473 ms 3 - 240 MB NPU
FFNet-78S TFLITE float Snapdragon® 8 Elite Mobile 21.702 ms 0 - 257 MB NPU
FFNet-78S TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 15.718 ms 2 - 282 MB NPU
FFNet-78S TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 6.445 ms 1 - 288 MB NPU
FFNet-78S TFLITE w8a8 Snapdragon® 8 Gen 1 Mobile 18.176 ms 1 - 290 MB NPU
FFNet-78S TFLITE w8a8 Qualcomm® Dragonwing™ QCS6490 50.463 ms 1 - 36 MB NPU
FFNet-78S TFLITE w8a8 Qualcomm® Dragonwing™ IQ-8275 9.774 ms 1 - 37 MB NPU
FFNet-78S TFLITE w8a8 Qualcomm® Dragonwing™ IQ-8275 26.248 ms 1 - 218 MB NPU
FFNet-78S TFLITE w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 9.065 ms 1 - 3 MB NPU
FFNet-78S TFLITE w8a8 Qualcomm® SA8775P 9.748 ms 1 - 220 MB NPU
FFNet-78S TFLITE w8a8 Qualcomm® SA8650P 9.748 ms 1 - 220 MB NPU
FFNet-78S TFLITE w8a8 Qualcomm® SA8255P 9.748 ms 1 - 220 MB NPU
FFNet-78S TFLITE w8a8 Qualcomm® QCS8450 18.176 ms 1 - 290 MB NPU
FFNet-78S TFLITE w8a8 Qualcomm® Dragonwing™ IQ-9075 9.505 ms 1 - 36 MB NPU
FFNet-78S TFLITE w8a8 Qualcomm® Dragonwing™ Q-6690 141.802 ms 1 - 246 MB NPU
FFNet-78S TFLITE w8a8 Qualcomm® Dragonwing™ Q-7790 14.575 ms 1 - 234 MB NPU
FFNet-78S TFLITE w8a8 Qualcomm® Dragonwing™ Q-8750 5.026 ms 1 - 231 MB NPU
FFNet-78S TFLITE w8a8 Qualcomm® SA7255P 26.248 ms 1 - 218 MB NPU
FFNet-78S TFLITE w8a8 Qualcomm® SA8295P 14.828 ms 0 - 220 MB NPU
FFNet-78S TFLITE w8a8 Snapdragon® 8 Elite Mobile 5.026 ms 1 - 231 MB NPU
FFNet-78S TFLITE w8a8 Snapdragon® 8 Elite Gen 5 Mobile 3.66 ms 1 - 242 MB NPU
FFNet-78S TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 14.575 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