Hugging Face's logo

qualcomm
/
Unet-Segmentation

Image Segmentation
PyTorch
backbone
bu_auto
real_time
android
Model card Files
xet
 Community

Unet-Segmentation: Optimized for Qualcomm Devices

UNet is a machine learning model that produces a segmentation mask for an image. The most basic use case will label each pixel in the image as being in the foreground or the background. More advanced usage will assign a class label to each pixel. This version of the model was trained on the data from Kaggle's Carvana Image Masking Challenge (see https://www.kaggle.com/c/carvana-image-masking-challenge) and is used for vehicle segmentation.

This is based on the implementation of Unet-Segmentation 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 Unet-Segmentation 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 Unet-Segmentation on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.semantic_segmentation

Model Stats:

  • Input resolution: 640x1280
  • Model checkpoint: unet_carvana_scale1.0_epoch2
  • Model size (float): 118 MB
  • Model size (w8a8): 29.8 MB
  • Number of output classes: 2 (foreground / background)
  • Number of parameters: 31.0M

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
Unet-Segmentation ONNX float Snapdragon® X2 Elite 74.864 ms 17 - 17 MB NPU
Unet-Segmentation ONNX float Snapdragon® X Elite 142.616 ms 54 - 54 MB NPU
Unet-Segmentation ONNX float Snapdragon® 8 Gen 3 Mobile 113.914 ms 2 - 523 MB NPU
Unet-Segmentation ONNX float Snapdragon® 8 Gen 1 Mobile 329.318 ms 1 - 549 MB NPU
Unet-Segmentation ONNX float Qualcomm® Dragonwing™ IQ-8275 286.177 ms 9 - 22 MB NPU
Unet-Segmentation ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 154.1 ms 0 - 56 MB NPU
Unet-Segmentation ONNX float Qualcomm® QCS8450 329.318 ms 1 - 549 MB NPU
Unet-Segmentation ONNX float Qualcomm® Dragonwing™ IQ-9075 250.143 ms 9 - 22 MB NPU
Unet-Segmentation ONNX float Qualcomm® Dragonwing™ IQ-X7181 142.616 ms 54 - 54 MB NPU
Unet-Segmentation ONNX float Qualcomm® Dragonwing™ Q-8750 91.494 ms 14 - 334 MB NPU
Unet-Segmentation ONNX float Snapdragon® 8 Elite Mobile 91.494 ms 14 - 334 MB NPU
Unet-Segmentation ONNX float Snapdragon® 8 Elite Gen 5 Mobile 67.754 ms 16 - 345 MB NPU
Unet-Segmentation ONNX w8a8 Snapdragon® X2 Elite 18.817 ms 4 - 4 MB NPU
Unet-Segmentation ONNX w8a8 Snapdragon® X Elite 37.721 ms 29 - 29 MB NPU
Unet-Segmentation ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 30.3 ms 6 - 339 MB NPU
Unet-Segmentation ONNX w8a8 Snapdragon® 8 Gen 1 Mobile 66.487 ms 6 - 341 MB NPU
Unet-Segmentation ONNX w8a8 Qualcomm® Dragonwing™ QCS6490 299.506 ms 3 - 8 MB NPU
Unet-Segmentation ONNX w8a8 Qualcomm® Dragonwing™ IQ-8275 40.791 ms 4 - 7 MB NPU
Unet-Segmentation ONNX w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 38.194 ms 0 - 32 MB NPU
Unet-Segmentation ONNX w8a8 Qualcomm® QCS8450 66.487 ms 6 - 341 MB NPU
Unet-Segmentation ONNX w8a8 Qualcomm® Dragonwing™ IQ-9075 35.942 ms 4 - 7 MB NPU
Unet-Segmentation ONNX w8a8 Qualcomm® Dragonwing™ IQ-X7181 37.721 ms 29 - 29 MB NPU
Unet-Segmentation ONNX w8a8 Qualcomm® Dragonwing™ Q-6690 1180.481 ms 0 - 539 MB NPU
Unet-Segmentation ONNX w8a8 Qualcomm® Dragonwing™ Q-7790 81.721 ms 6 - 279 MB NPU
Unet-Segmentation ONNX w8a8 Qualcomm® Dragonwing™ Q-8750 24.452 ms 3 - 189 MB NPU
Unet-Segmentation ONNX w8a8 Snapdragon® 8 Elite Mobile 24.452 ms 3 - 189 MB NPU
Unet-Segmentation ONNX w8a8 Snapdragon® 8 Elite Gen 5 Mobile 16.691 ms 3 - 191 MB NPU
Unet-Segmentation ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 81.721 ms 6 - 279 MB NPU
Unet-Segmentation QNN_DLC float Snapdragon® X2 Elite 71.892 ms 9 - 9 MB NPU
Unet-Segmentation QNN_DLC float Snapdragon® X Elite 132.372 ms 9 - 9 MB NPU
Unet-Segmentation QNN_DLC float Snapdragon® 8 Gen 3 Mobile 101.671 ms 9 - 523 MB NPU
Unet-Segmentation QNN_DLC float Snapdragon® 8 Gen 1 Mobile 293.677 ms 9 - 545 MB NPU
Unet-Segmentation QNN_DLC float Qualcomm® Dragonwing™ IQ-8275 273.715 ms 9 - 27 MB NPU
Unet-Segmentation QNN_DLC float Qualcomm® Dragonwing™ IQ-8275 954.506 ms 0 - 323 MB NPU
Unet-Segmentation QNN_DLC float Qualcomm® Dragonwing™ QCS8550 (Proxy) 139.982 ms 9 - 798 MB NPU
Unet-Segmentation QNN_DLC float Qualcomm® SA8775P 240.406 ms 0 - 324 MB NPU
Unet-Segmentation QNN_DLC float Qualcomm® SA8650P 240.406 ms 0 - 324 MB NPU
Unet-Segmentation QNN_DLC float Qualcomm® SA8255P 240.406 ms 0 - 324 MB NPU
Unet-Segmentation QNN_DLC float Qualcomm® QCS8450 293.677 ms 9 - 545 MB NPU
Unet-Segmentation QNN_DLC float Qualcomm® Dragonwing™ IQ-9075 238.779 ms 9 - 27 MB NPU
Unet-Segmentation QNN_DLC float Qualcomm® Dragonwing™ IQ-X7181 132.372 ms 9 - 9 MB NPU
Unet-Segmentation QNN_DLC float Qualcomm® Dragonwing™ Q-8750 82.938 ms 9 - 340 MB NPU
Unet-Segmentation QNN_DLC float Qualcomm® SA7255P 954.506 ms 0 - 323 MB NPU
Unet-Segmentation QNN_DLC float Qualcomm® SA8295P 274.445 ms 0 - 323 MB NPU
Unet-Segmentation QNN_DLC float Snapdragon® 8 Elite Mobile 82.938 ms 9 - 340 MB NPU
Unet-Segmentation QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 62.092 ms 9 - 356 MB NPU
Unet-Segmentation QNN_DLC w8a8 Snapdragon® X2 Elite 18.849 ms 2 - 2 MB NPU
Unet-Segmentation QNN_DLC w8a8 Snapdragon® X Elite 35.788 ms 2 - 2 MB NPU
Unet-Segmentation QNN_DLC w8a8 Snapdragon® 8 Gen 3 Mobile 26.232 ms 2 - 320 MB NPU
Unet-Segmentation QNN_DLC w8a8 Snapdragon® 8 Gen 1 Mobile 59.234 ms 2 - 318 MB NPU
Unet-Segmentation QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS6490 288.685 ms 2 - 8 MB NPU
Unet-Segmentation QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-8275 37.375 ms 2 - 9 MB NPU
Unet-Segmentation QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-8275 121.501 ms 1 - 180 MB NPU
Unet-Segmentation QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 34.674 ms 2 - 4 MB NPU
Unet-Segmentation QNN_DLC w8a8 Qualcomm® SA8775P 32.153 ms 0 - 180 MB NPU
Unet-Segmentation QNN_DLC w8a8 Qualcomm® SA8650P 32.153 ms 0 - 180 MB NPU
Unet-Segmentation QNN_DLC w8a8 Qualcomm® SA8255P 32.153 ms 0 - 180 MB NPU
Unet-Segmentation QNN_DLC w8a8 Qualcomm® QCS8450 59.234 ms 2 - 318 MB NPU
Unet-Segmentation QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-9075 32.918 ms 2 - 7 MB NPU
Unet-Segmentation QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-X7181 35.788 ms 2 - 2 MB NPU
Unet-Segmentation QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-6690 1220.752 ms 2 - 524 MB NPU
Unet-Segmentation QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-7790 79.02 ms 2 - 267 MB NPU
Unet-Segmentation QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-8750 21.814 ms 2 - 188 MB NPU
Unet-Segmentation QNN_DLC w8a8 Qualcomm® SA7255P 121.501 ms 1 - 180 MB NPU
Unet-Segmentation QNN_DLC w8a8 Qualcomm® SA8295P 63.741 ms 2 - 182 MB NPU
Unet-Segmentation QNN_DLC w8a8 Snapdragon® 8 Elite Mobile 21.814 ms 2 - 188 MB NPU
Unet-Segmentation QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 Mobile 16.062 ms 2 - 200 MB NPU
Unet-Segmentation QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 79.02 ms 2 - 267 MB NPU
Unet-Segmentation TFLITE float Snapdragon® 8 Gen 3 Mobile 105.529 ms 5 - 578 MB NPU
Unet-Segmentation TFLITE float Snapdragon® 8 Gen 1 Mobile 291.085 ms 7 - 590 MB NPU
Unet-Segmentation TFLITE float Qualcomm® Dragonwing™ IQ-8275 274.112 ms 0 - 81 MB NPU
Unet-Segmentation TFLITE float Qualcomm® Dragonwing™ IQ-8275 953.338 ms 0 - 324 MB NPU
Unet-Segmentation TFLITE float Qualcomm® Dragonwing™ QCS8550 (Proxy) 144.959 ms 7 - 218 MB NPU
Unet-Segmentation TFLITE float Qualcomm® SA8775P 240.498 ms 11 - 335 MB NPU
Unet-Segmentation TFLITE float Qualcomm® SA8650P 240.498 ms 11 - 335 MB NPU
Unet-Segmentation TFLITE float Qualcomm® SA8255P 240.498 ms 11 - 335 MB NPU
Unet-Segmentation TFLITE float Qualcomm® QCS8450 291.085 ms 7 - 590 MB NPU
Unet-Segmentation TFLITE float Qualcomm® Dragonwing™ IQ-9075 239.338 ms 0 - 80 MB NPU
Unet-Segmentation TFLITE float Qualcomm® Dragonwing™ Q-8750 82.576 ms 5 - 337 MB NPU
Unet-Segmentation TFLITE float Qualcomm® SA7255P 953.338 ms 0 - 324 MB NPU
Unet-Segmentation TFLITE float Qualcomm® SA8295P 274.491 ms 7 - 329 MB NPU
Unet-Segmentation TFLITE float Snapdragon® 8 Elite Mobile 82.576 ms 5 - 337 MB NPU
Unet-Segmentation TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 62.625 ms 6 - 353 MB NPU
Unet-Segmentation TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 26.029 ms 1 - 318 MB NPU
Unet-Segmentation TFLITE w8a8 Snapdragon® 8 Gen 1 Mobile 60.008 ms 2 - 318 MB NPU
Unet-Segmentation TFLITE w8a8 Qualcomm® Dragonwing™ QCS6490 288.425 ms 1 - 41 MB NPU
Unet-Segmentation TFLITE w8a8 Qualcomm® Dragonwing™ IQ-8275 37.164 ms 2 - 39 MB NPU
Unet-Segmentation TFLITE w8a8 Qualcomm® Dragonwing™ IQ-8275 121.602 ms 2 - 181 MB NPU
Unet-Segmentation TFLITE w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 33.858 ms 2 - 4 MB NPU
Unet-Segmentation TFLITE w8a8 Qualcomm® SA8775P 32.214 ms 2 - 180 MB NPU
Unet-Segmentation TFLITE w8a8 Qualcomm® SA8650P 32.214 ms 2 - 180 MB NPU
Unet-Segmentation TFLITE w8a8 Qualcomm® SA8255P 32.214 ms 2 - 180 MB NPU
Unet-Segmentation TFLITE w8a8 Qualcomm® QCS8450 60.008 ms 2 - 318 MB NPU
Unet-Segmentation TFLITE w8a8 Qualcomm® Dragonwing™ IQ-9075 33.275 ms 1 - 38 MB NPU
Unet-Segmentation TFLITE w8a8 Qualcomm® Dragonwing™ Q-6690 1249.429 ms 0 - 522 MB NPU
Unet-Segmentation TFLITE w8a8 Qualcomm® Dragonwing™ Q-7790 78.318 ms 2 - 268 MB NPU
Unet-Segmentation TFLITE w8a8 Qualcomm® Dragonwing™ Q-8750 21.934 ms 1 - 187 MB NPU
Unet-Segmentation TFLITE w8a8 Qualcomm® SA7255P 121.602 ms 2 - 181 MB NPU
Unet-Segmentation TFLITE w8a8 Qualcomm® SA8295P 63.753 ms 2 - 180 MB NPU
Unet-Segmentation TFLITE w8a8 Snapdragon® 8 Elite Mobile 21.934 ms 1 - 187 MB NPU
Unet-Segmentation TFLITE w8a8 Snapdragon® 8 Elite Gen 5 Mobile 16.07 ms 1 - 196 MB NPU
Unet-Segmentation TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 78.318 ms 2 - 268 MB NPU

License

  • The license for the original implementation of Unet-Segmentation 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/Unet-Segmentation