Hugging Face's logo

qualcomm
/
FFNet-78S-LowRes

Image Segmentation
PyTorch
real_time
android
Model card Files
xet
 Community

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 2.45 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-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 3.835 ms 1 - 176 MB NPU
FFNet-78S-LowRes ONNX float Snapdragon® 8 Elite Mobile 4.547 ms 3 - 170 MB NPU
FFNet-78S-LowRes ONNX float Snapdragon® X2 Elite 4.235 ms 47 - 47 MB NPU
FFNet-78S-LowRes ONNX float Snapdragon® X Elite 8.192 ms 46 - 46 MB NPU
FFNet-78S-LowRes ONNX float Snapdragon® X Elite 8.192 ms 46 - 46 MB NPU
FFNet-78S-LowRes ONNX float Snapdragon® 8 Gen 3 Mobile 5.559 ms 1 - 207 MB NPU
FFNet-78S-LowRes ONNX float Qualcomm® QCS8550 (Proxy) 7.815 ms 0 - 52 MB NPU
FFNet-78S-LowRes ONNX float Qualcomm® QCS9075 12.974 ms 6 - 15 MB NPU
FFNet-78S-LowRes ONNX float Snapdragon® 8 Elite For Galaxy Mobile 4.547 ms 3 - 170 MB NPU
FFNet-78S-LowRes ONNX w8a8 Snapdragon® 8 Elite Gen 5 Mobile 1.27 ms 0 - 63 MB NPU
FFNet-78S-LowRes ONNX w8a8 Snapdragon® 8 Elite Mobile 1.505 ms 0 - 62 MB NPU
FFNet-78S-LowRes ONNX w8a8 Snapdragon® X2 Elite 1.324 ms 25 - 25 MB NPU
FFNet-78S-LowRes ONNX w8a8 Snapdragon® X Elite 3.006 ms 25 - 25 MB NPU
FFNet-78S-LowRes ONNX w8a8 Snapdragon® X Elite 3.006 ms 25 - 25 MB NPU
FFNet-78S-LowRes ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 1.985 ms 0 - 122 MB NPU
FFNet-78S-LowRes ONNX w8a8 Qualcomm® QCS6490 109.918 ms 56 - 114 MB CPU
FFNet-78S-LowRes ONNX w8a8 Qualcomm® QCS8550 (Proxy) 2.761 ms 0 - 29 MB NPU
FFNet-78S-LowRes ONNX w8a8 Qualcomm® QCS9075 3.33 ms 1 - 4 MB NPU
FFNet-78S-LowRes ONNX w8a8 Qualcomm® QCM6690 118.603 ms 65 - 75 MB CPU
FFNet-78S-LowRes ONNX w8a8 Snapdragon® 8 Elite For Galaxy Mobile 1.505 ms 0 - 62 MB NPU
FFNet-78S-LowRes ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 119.068 ms 62 - 73 MB CPU
FFNet-78S-LowRes ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 119.068 ms 62 - 73 MB CPU
FFNet-78S-LowRes QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 6.58 ms 6 - 55 MB NPU
FFNet-78S-LowRes QNN_DLC float Snapdragon® 8 Elite Mobile 8.082 ms 0 - 49 MB NPU
FFNet-78S-LowRes QNN_DLC float Snapdragon® X2 Elite 7.521 ms 6 - 6 MB NPU
FFNet-78S-LowRes QNN_DLC float Snapdragon® X Elite 15.457 ms 6 - 6 MB NPU
FFNet-78S-LowRes QNN_DLC float Snapdragon® X Elite 15.457 ms 6 - 6 MB NPU
FFNet-78S-LowRes QNN_DLC float Snapdragon® 8 Gen 3 Mobile 9.752 ms 6 - 78 MB NPU
FFNet-78S-LowRes QNN_DLC float Qualcomm® QCS8275 (Proxy) 51.206 ms 0 - 43 MB NPU
FFNet-78S-LowRes QNN_DLC float Qualcomm® QCS8550 (Proxy) 14.706 ms 6 - 8 MB NPU
FFNet-78S-LowRes QNN_DLC float Qualcomm® SA8775P 19.154 ms 0 - 44 MB NPU
FFNet-78S-LowRes QNN_DLC float Qualcomm® SA8775P 19.154 ms 0 - 44 MB NPU
FFNet-78S-LowRes QNN_DLC float Qualcomm® SA8775P 19.154 ms 0 - 44 MB NPU
FFNet-78S-LowRes QNN_DLC float Qualcomm® QCS9075 18.347 ms 6 - 14 MB NPU
FFNet-78S-LowRes QNN_DLC float Qualcomm® QCS8450 (Proxy) 26.436 ms 6 - 71 MB NPU
FFNet-78S-LowRes QNN_DLC float Qualcomm® SA7255P 51.206 ms 0 - 43 MB NPU
FFNet-78S-LowRes QNN_DLC float Qualcomm® SA8295P 20.983 ms 0 - 40 MB NPU
FFNet-78S-LowRes QNN_DLC float Snapdragon® 8 Elite For Galaxy Mobile 8.082 ms 0 - 49 MB NPU
FFNet-78S-LowRes QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 Mobile 1.9 ms 2 - 58 MB NPU
FFNet-78S-LowRes QNN_DLC w8a8 Snapdragon® 8 Elite Mobile 2.357 ms 2 - 55 MB NPU
FFNet-78S-LowRes QNN_DLC w8a8 Snapdragon® X2 Elite 2.186 ms 2 - 2 MB NPU
FFNet-78S-LowRes QNN_DLC w8a8 Snapdragon® X Elite 5.106 ms 2 - 2 MB NPU
FFNet-78S-LowRes QNN_DLC w8a8 Snapdragon® X Elite 5.106 ms 2 - 2 MB NPU
FFNet-78S-LowRes QNN_DLC w8a8 Snapdragon® 8 Gen 3 Mobile 3.356 ms 2 - 100 MB NPU
FFNet-78S-LowRes QNN_DLC w8a8 Qualcomm® QCS6490 15.124 ms 4 - 7 MB NPU
FFNet-78S-LowRes QNN_DLC w8a8 Qualcomm® QCS8275 (Proxy) 10.642 ms 2 - 56 MB NPU
FFNet-78S-LowRes QNN_DLC w8a8 Qualcomm® QCS8550 (Proxy) 4.775 ms 0 - 8 MB NPU
FFNet-78S-LowRes QNN_DLC w8a8 Qualcomm® SA8775P 5.235 ms 2 - 59 MB NPU
FFNet-78S-LowRes QNN_DLC w8a8 Qualcomm® SA8775P 5.235 ms 2 - 59 MB NPU
FFNet-78S-LowRes QNN_DLC w8a8 Qualcomm® SA8775P 5.235 ms 2 - 59 MB NPU
FFNet-78S-LowRes QNN_DLC w8a8 Qualcomm® QCS9075 7.012 ms 2 - 6 MB NPU
FFNet-78S-LowRes QNN_DLC w8a8 Qualcomm® QCM6690 35.579 ms 2 - 193 MB NPU
FFNet-78S-LowRes QNN_DLC w8a8 Qualcomm® QCS8450 (Proxy) 7.15 ms 2 - 100 MB NPU
FFNet-78S-LowRes QNN_DLC w8a8 Qualcomm® SA7255P 10.642 ms 2 - 56 MB NPU
FFNet-78S-LowRes QNN_DLC w8a8 Qualcomm® SA8295P 6.67 ms 1 - 53 MB NPU
FFNet-78S-LowRes QNN_DLC w8a8 Snapdragon® 8 Elite For Galaxy Mobile 2.357 ms 2 - 55 MB NPU
FFNet-78S-LowRes QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 7.322 ms 0 - 184 MB NPU
FFNet-78S-LowRes QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 7.322 ms 0 - 184 MB NPU
FFNet-78S-LowRes TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 6.576 ms 0 - 78 MB NPU
FFNet-78S-LowRes TFLITE float Snapdragon® 8 Elite Mobile 8.107 ms 0 - 80 MB NPU
FFNet-78S-LowRes TFLITE float Snapdragon® 8 Gen 3 Mobile 9.868 ms 1 - 154 MB NPU
FFNet-78S-LowRes TFLITE float Qualcomm® QCS8275 (Proxy) 51.044 ms 1 - 76 MB NPU
FFNet-78S-LowRes TFLITE float Qualcomm® QCS8550 (Proxy) 14.561 ms 1 - 3 MB NPU
FFNet-78S-LowRes TFLITE float Qualcomm® SA8775P 19.114 ms 1 - 77 MB NPU
FFNet-78S-LowRes TFLITE float Qualcomm® SA8775P 19.114 ms 1 - 77 MB NPU
FFNet-78S-LowRes TFLITE float Qualcomm® SA8775P 19.114 ms 1 - 77 MB NPU
FFNet-78S-LowRes TFLITE float Qualcomm® QCS9075 18.305 ms 0 - 60 MB NPU
FFNet-78S-LowRes TFLITE float Qualcomm® QCS8450 (Proxy) 26.19 ms 1 - 148 MB NPU
FFNet-78S-LowRes TFLITE float Qualcomm® SA7255P 51.044 ms 1 - 76 MB NPU
FFNet-78S-LowRes TFLITE float Qualcomm® SA8295P 20.986 ms 1 - 73 MB NPU
FFNet-78S-LowRes TFLITE float Snapdragon® 8 Elite For Galaxy Mobile 8.107 ms 0 - 80 MB NPU
FFNet-78S-LowRes TFLITE w8a8 Snapdragon® 8 Elite Gen 5 Mobile 1.338 ms 0 - 54 MB NPU
FFNet-78S-LowRes TFLITE w8a8 Snapdragon® 8 Elite Mobile 1.555 ms 0 - 51 MB NPU
FFNet-78S-LowRes TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 2.042 ms 0 - 104 MB NPU
FFNet-78S-LowRes TFLITE w8a8 Qualcomm® QCS6490 9.768 ms 0 - 30 MB NPU
FFNet-78S-LowRes TFLITE w8a8 Qualcomm® QCS8275 (Proxy) 7.452 ms 0 - 51 MB NPU
FFNet-78S-LowRes TFLITE w8a8 Qualcomm® QCS8550 (Proxy) 2.863 ms 0 - 2 MB NPU
FFNet-78S-LowRes TFLITE w8a8 Qualcomm® SA8775P 3.319 ms 0 - 54 MB NPU
FFNet-78S-LowRes TFLITE w8a8 Qualcomm® SA8775P 3.319 ms 0 - 54 MB NPU
FFNet-78S-LowRes TFLITE w8a8 Qualcomm® SA8775P 3.319 ms 0 - 54 MB NPU
FFNet-78S-LowRes TFLITE w8a8 Qualcomm® QCS9075 3.375 ms 0 - 29 MB NPU
FFNet-78S-LowRes TFLITE w8a8 Qualcomm® QCM6690 30.986 ms 0 - 189 MB NPU
FFNet-78S-LowRes TFLITE w8a8 Qualcomm® QCS8450 (Proxy) 3.629 ms 0 - 99 MB NPU
FFNet-78S-LowRes TFLITE w8a8 Qualcomm® SA7255P 7.452 ms 0 - 51 MB NPU
FFNet-78S-LowRes TFLITE w8a8 Qualcomm® SA8295P 4.578 ms 0 - 49 MB NPU
FFNet-78S-LowRes TFLITE w8a8 Snapdragon® 8 Elite For Galaxy Mobile 1.555 ms 0 - 51 MB NPU
FFNet-78S-LowRes TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 4.437 ms 0 - 180 MB NPU
FFNet-78S-LowRes TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 4.437 ms 0 - 180 MB NPU

License

  • The license for the original implementation of FFNet-78S-LowRes 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-LowRes