Hugging Face's logo

qualcomm
/
Segformer-Base

Image Segmentation
PyTorch
real_time
android
Model card Files
xet
 Community

Segformer-Base: Optimized for Qualcomm Devices

Segformer Base is a machine learning model that predicts masks and classes of objects in an image.

This is based on the implementation of Segformer-Base 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 w8a16 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 w8a16 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 Segformer-Base 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 Segformer-Base on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.semantic_segmentation

Model Stats:

  • Model checkpoint: nvidia/segformer-b0-finetuned-ade-512-512
  • Input resolution: 512x512
  • Number of output classes: 150
  • Number of parameters: 3.75M
  • Model size (float): 14.4 MB
  • Model size (w8a16): 4.57 MB
  • Model size (w8a8): 3.90 MB

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
Segformer-Base ONNX float Snapdragon® 8 Elite Gen 5 Mobile 73.622 ms 24 - 217 MB NPU
Segformer-Base ONNX float Snapdragon® 8 Elite Mobile 74.173 ms 23 - 218 MB NPU
Segformer-Base ONNX float Snapdragon® X2 Elite 72.582 ms 34 - 34 MB NPU
Segformer-Base ONNX float Snapdragon® X Elite 112.533 ms 33 - 33 MB NPU
Segformer-Base ONNX float Snapdragon® X Elite 112.533 ms 33 - 33 MB NPU
Segformer-Base ONNX float Snapdragon® 8 Gen 3 Mobile 82.074 ms 26 - 252 MB NPU
Segformer-Base ONNX float Qualcomm® QCS8550 (Proxy) 108.112 ms 8 - 15 MB NPU
Segformer-Base ONNX float Snapdragon® 8 Elite For Galaxy Mobile 74.173 ms 23 - 218 MB NPU
Segformer-Base ONNX float Qualcomm® QCS9075 112.457 ms 23 - 26 MB NPU
Segformer-Base ONNX w8a16 Snapdragon® 8 Elite Gen 5 Mobile 6.804 ms 14 - 219 MB NPU
Segformer-Base ONNX w8a16 Snapdragon® 8 Elite Mobile 8.618 ms 12 - 216 MB NPU
Segformer-Base ONNX w8a16 Snapdragon® X2 Elite 6.869 ms 13 - 13 MB NPU
Segformer-Base ONNX w8a16 Snapdragon® X Elite 15.411 ms 18 - 18 MB NPU
Segformer-Base ONNX w8a16 Snapdragon® X Elite 15.411 ms 18 - 18 MB NPU
Segformer-Base ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 10.459 ms 13 - 253 MB NPU
Segformer-Base ONNX w8a16 Qualcomm® QCS6490 731.41 ms 381 - 386 MB CPU
Segformer-Base ONNX w8a16 Qualcomm® QCS8550 (Proxy) 14.896 ms 9 - 17 MB NPU
Segformer-Base ONNX w8a16 Qualcomm® QCM6690 350.872 ms 323 - 334 MB CPU
Segformer-Base ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 318.13 ms 373 - 384 MB CPU
Segformer-Base ONNX w8a16 Qualcomm® QCS9075 20.743 ms 12 - 15 MB NPU
Segformer-Base ONNX w8a16 Snapdragon® 8 Elite For Galaxy Mobile 8.618 ms 12 - 216 MB NPU
Segformer-Base ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 318.13 ms 373 - 384 MB CPU
Segformer-Base ONNX w8a8 Snapdragon® 8 Elite Gen 5 Mobile 4.581 ms 7 - 205 MB NPU
Segformer-Base ONNX w8a8 Snapdragon® 8 Elite Mobile 5.564 ms 7 - 203 MB NPU
Segformer-Base ONNX w8a8 Snapdragon® X2 Elite 4.595 ms 4 - 4 MB NPU
Segformer-Base ONNX w8a8 Snapdragon® X Elite 11.679 ms 9 - 9 MB NPU
Segformer-Base ONNX w8a8 Snapdragon® X Elite 11.679 ms 9 - 9 MB NPU
Segformer-Base ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 7.615 ms 7 - 228 MB NPU
Segformer-Base ONNX w8a8 Qualcomm® QCS6490 272.916 ms 194 - 202 MB CPU
Segformer-Base ONNX w8a8 Qualcomm® QCS8550 (Proxy) 10.964 ms 5 - 12 MB NPU
Segformer-Base ONNX w8a8 Qualcomm® QCS9075 11.775 ms 6 - 9 MB NPU
Segformer-Base ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 157.69 ms 192 - 204 MB CPU
Segformer-Base ONNX w8a8 Qualcomm® QCM6690 173.943 ms 195 - 207 MB CPU
Segformer-Base ONNX w8a8 Snapdragon® 8 Elite For Galaxy Mobile 5.564 ms 7 - 203 MB NPU
Segformer-Base ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 157.69 ms 192 - 204 MB CPU
Segformer-Base QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 13.66 ms 3 - 193 MB NPU
Segformer-Base QNN_DLC float Snapdragon® 8 Elite Mobile 13.222 ms 0 - 195 MB NPU
Segformer-Base QNN_DLC float Snapdragon® X2 Elite 12.518 ms 3 - 3 MB NPU
Segformer-Base QNN_DLC float Snapdragon® X Elite 23.476 ms 3 - 3 MB NPU
Segformer-Base QNN_DLC float Snapdragon® X Elite 23.476 ms 3 - 3 MB NPU
Segformer-Base QNN_DLC float Snapdragon® 8 Gen 3 Mobile 16.38 ms 0 - 225 MB NPU
Segformer-Base QNN_DLC float Qualcomm® QCS8550 (Proxy) 22.693 ms 0 - 5 MB NPU
Segformer-Base QNN_DLC float Qualcomm® SA8775P 24.41 ms 0 - 192 MB NPU
Segformer-Base QNN_DLC float Qualcomm® SA8775P 24.41 ms 0 - 192 MB NPU
Segformer-Base QNN_DLC float Qualcomm® SA8775P 24.41 ms 0 - 192 MB NPU
Segformer-Base QNN_DLC float Qualcomm® QCS8450 (Proxy) 29.635 ms 2 - 227 MB NPU
Segformer-Base QNN_DLC float Qualcomm® SA7255P 48.884 ms 1 - 190 MB NPU
Segformer-Base QNN_DLC float Snapdragon® 8 Elite For Galaxy Mobile 13.222 ms 0 - 195 MB NPU
Segformer-Base QNN_DLC float Qualcomm® SA8295P 27.91 ms 0 - 191 MB NPU
Segformer-Base QNN_DLC float Qualcomm® QCS9075 28.059 ms 3 - 17 MB NPU
Segformer-Base QNN_DLC w8a16 Snapdragon® 8 Elite Gen 5 Mobile 12.699 ms 2 - 241 MB NPU
Segformer-Base QNN_DLC w8a16 Snapdragon® 8 Elite Mobile 14.533 ms 1 - 232 MB NPU
Segformer-Base QNN_DLC w8a16 Snapdragon® X2 Elite 11.355 ms 2 - 2 MB NPU
Segformer-Base QNN_DLC w8a16 Snapdragon® X Elite 23.052 ms 2 - 2 MB NPU
Segformer-Base QNN_DLC w8a16 Snapdragon® X Elite 23.052 ms 2 - 2 MB NPU
Segformer-Base QNN_DLC w8a16 Snapdragon® 8 Gen 3 Mobile 19.0 ms 2 - 273 MB NPU
Segformer-Base QNN_DLC w8a16 Qualcomm® QCS8550 (Proxy) 24.951 ms 2 - 3 MB NPU
Segformer-Base QNN_DLC w8a16 Qualcomm® SA8775P 24.503 ms 2 - 232 MB NPU
Segformer-Base QNN_DLC w8a16 Qualcomm® SA8775P 24.503 ms 2 - 232 MB NPU
Segformer-Base QNN_DLC w8a16 Qualcomm® SA8775P 24.503 ms 2 - 232 MB NPU
Segformer-Base QNN_DLC w8a16 Qualcomm® QCM6690 134.491 ms 2 - 292 MB NPU
Segformer-Base QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 47.508 ms 2 - 261 MB NPU
Segformer-Base QNN_DLC w8a16 Qualcomm® QCS9075 45.252 ms 4 - 11 MB NPU
Segformer-Base QNN_DLC w8a16 Qualcomm® SA7255P 37.609 ms 2 - 230 MB NPU
Segformer-Base QNN_DLC w8a16 Snapdragon® 8 Elite For Galaxy Mobile 14.533 ms 1 - 232 MB NPU
Segformer-Base QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 47.508 ms 2 - 261 MB NPU
Segformer-Base QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 Mobile 2.232 ms 1 - 182 MB NPU
Segformer-Base QNN_DLC w8a8 Snapdragon® 8 Elite Mobile 2.835 ms 0 - 179 MB NPU
Segformer-Base QNN_DLC w8a8 Snapdragon® X2 Elite 2.576 ms 1 - 1 MB NPU
Segformer-Base QNN_DLC w8a8 Snapdragon® X Elite 6.345 ms 1 - 1 MB NPU
Segformer-Base QNN_DLC w8a8 Snapdragon® X Elite 6.345 ms 1 - 1 MB NPU
Segformer-Base QNN_DLC w8a8 Snapdragon® 8 Gen 3 Mobile 3.966 ms 0 - 199 MB NPU
Segformer-Base QNN_DLC w8a8 Qualcomm® QCS6490 15.777 ms 0 - 5 MB NPU
Segformer-Base QNN_DLC w8a8 Qualcomm® QCS8550 (Proxy) 5.79 ms 1 - 2 MB NPU
Segformer-Base QNN_DLC w8a8 Qualcomm® SA8775P 6.411 ms 1 - 175 MB NPU
Segformer-Base QNN_DLC w8a8 Qualcomm® SA8775P 6.411 ms 1 - 175 MB NPU
Segformer-Base QNN_DLC w8a8 Qualcomm® SA8775P 6.411 ms 1 - 175 MB NPU
Segformer-Base QNN_DLC w8a8 Qualcomm® QCS9075 6.795 ms 1 - 5 MB NPU
Segformer-Base QNN_DLC w8a8 Qualcomm® QCS8450 (Proxy) 8.62 ms 0 - 203 MB NPU
Segformer-Base QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 6.891 ms 1 - 180 MB NPU
Segformer-Base QNN_DLC w8a8 Qualcomm® QCM6690 33.381 ms 1 - 190 MB NPU
Segformer-Base QNN_DLC w8a8 Snapdragon® 8 Elite For Galaxy Mobile 2.835 ms 0 - 179 MB NPU
Segformer-Base QNN_DLC w8a8 Qualcomm® SA7255P 10.849 ms 1 - 175 MB NPU
Segformer-Base QNN_DLC w8a8 Qualcomm® SA8295P 7.809 ms 0 - 173 MB NPU
Segformer-Base QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 6.891 ms 1 - 180 MB NPU
Segformer-Base TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 13.675 ms 8 - 201 MB NPU
Segformer-Base TFLITE float Snapdragon® 8 Elite Mobile 13.322 ms 8 - 210 MB NPU
Segformer-Base TFLITE float Snapdragon® 8 Gen 3 Mobile 16.371 ms 9 - 237 MB NPU
Segformer-Base TFLITE float Qualcomm® QCS8550 (Proxy) 22.504 ms 9 - 21 MB NPU
Segformer-Base TFLITE float Qualcomm® SA8775P 24.482 ms 9 - 202 MB NPU
Segformer-Base TFLITE float Qualcomm® SA8775P 24.482 ms 9 - 202 MB NPU
Segformer-Base TFLITE float Qualcomm® SA8775P 24.482 ms 9 - 202 MB NPU
Segformer-Base TFLITE float Qualcomm® QCS8450 (Proxy) 29.802 ms 9 - 234 MB NPU
Segformer-Base TFLITE float Qualcomm® SA7255P 48.921 ms 10 - 201 MB NPU
Segformer-Base TFLITE float Snapdragon® 8 Elite For Galaxy Mobile 13.322 ms 8 - 210 MB NPU
Segformer-Base TFLITE float Qualcomm® SA8295P 27.816 ms 9 - 202 MB NPU
Segformer-Base TFLITE float Qualcomm® QCS9075 27.605 ms 8 - 30 MB NPU
Segformer-Base TFLITE w8a8 Snapdragon® 8 Elite Gen 5 Mobile 4.533 ms 2 - 189 MB NPU
Segformer-Base TFLITE w8a8 Snapdragon® 8 Elite Mobile 5.706 ms 1 - 185 MB NPU
Segformer-Base TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 7.09 ms 2 - 209 MB NPU
Segformer-Base TFLITE w8a8 Qualcomm® QCS6490 106.621 ms 15 - 50 MB NPU
Segformer-Base TFLITE w8a8 Qualcomm® QCS8550 (Proxy) 10.138 ms 2 - 4 MB NPU
Segformer-Base TFLITE w8a8 Qualcomm® SA8775P 10.895 ms 2 - 182 MB NPU
Segformer-Base TFLITE w8a8 Qualcomm® SA8775P 10.895 ms 2 - 182 MB NPU
Segformer-Base TFLITE w8a8 Qualcomm® SA8775P 10.895 ms 2 - 182 MB NPU
Segformer-Base TFLITE w8a8 Qualcomm® QCS9075 10.634 ms 0 - 10 MB NPU
Segformer-Base TFLITE w8a8 Qualcomm® QCS8450 (Proxy) 12.083 ms 2 - 215 MB NPU
Segformer-Base TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 38.939 ms 15 - 60 MB NPU
Segformer-Base TFLITE w8a8 Qualcomm® QCM6690 96.12 ms 15 - 175 MB NPU
Segformer-Base TFLITE w8a8 Snapdragon® 8 Elite For Galaxy Mobile 5.706 ms 1 - 185 MB NPU
Segformer-Base TFLITE w8a8 Qualcomm® SA7255P 18.263 ms 2 - 180 MB NPU
Segformer-Base TFLITE w8a8 Qualcomm® SA8295P 12.854 ms 2 - 187 MB NPU
Segformer-Base TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 38.939 ms 15 - 60 MB NPU

License

  • The license for the original implementation of Segformer-Base 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/Segformer-Base