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 2.45, ONNX Runtime 1.27.1 Download
ONNX w8a16 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 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:

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

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
Segformer-Base ONNX float Snapdragon® X2 Elite 13.564 ms 35 - 35 MB NPU
Segformer-Base ONNX float Snapdragon® X Elite 24.504 ms 35 - 35 MB NPU
Segformer-Base ONNX float Snapdragon® 8 Gen 3 Mobile 17.36 ms 24 - 242 MB NPU
Segformer-Base ONNX float Snapdragon® 8 Gen 1 Mobile 24.689 ms 23 - 245 MB NPU
Segformer-Base ONNX float Qualcomm® Dragonwing™ IQ-8275 24.315 ms 22 - 25 MB NPU
Segformer-Base ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 23.78 ms 19 - 25 MB NPU
Segformer-Base ONNX float Qualcomm® QCS8450 24.689 ms 23 - 245 MB NPU
Segformer-Base ONNX float Qualcomm® Dragonwing™ IQ-9075 25.686 ms 24 - 27 MB NPU
Segformer-Base ONNX float Qualcomm® Dragonwing™ IQ-X7181 24.504 ms 35 - 35 MB NPU
Segformer-Base ONNX float Qualcomm® Dragonwing™ Q-8750 14.378 ms 21 - 209 MB NPU
Segformer-Base ONNX float Snapdragon® 8 Elite Mobile 14.378 ms 21 - 209 MB NPU
Segformer-Base ONNX float Snapdragon® 8 Elite Gen 5 Mobile 13.266 ms 21 - 213 MB NPU
Segformer-Base ONNX w8a16 Snapdragon® X2 Elite 5.62 ms 18 - 18 MB NPU
Segformer-Base ONNX w8a16 Snapdragon® X Elite 13.561 ms 17 - 17 MB NPU
Segformer-Base ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 9.426 ms 12 - 242 MB NPU
Segformer-Base ONNX w8a16 Snapdragon® 8 Gen 1 Mobile 17.839 ms 11 - 242 MB NPU
Segformer-Base ONNX w8a16 Qualcomm® Dragonwing™ QCS6490 53.805 ms 14 - 16 MB NPU
Segformer-Base ONNX w8a16 Qualcomm® Dragonwing™ IQ-8275 12.704 ms 11 - 14 MB NPU
Segformer-Base ONNX w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 13.355 ms 3 - 9 MB NPU
Segformer-Base ONNX w8a16 Qualcomm® QCS8450 17.839 ms 11 - 242 MB NPU
Segformer-Base ONNX w8a16 Qualcomm® Dragonwing™ IQ-9075 13.866 ms 13 - 16 MB NPU
Segformer-Base ONNX w8a16 Qualcomm® Dragonwing™ IQ-X7181 13.561 ms 17 - 17 MB NPU
Segformer-Base ONNX w8a16 Qualcomm® Dragonwing™ Q-6690 93.546 ms 14 - 243 MB NPU
Segformer-Base ONNX w8a16 Qualcomm® Dragonwing™ Q-7790 16.922 ms 12 - 233 MB NPU
Segformer-Base ONNX w8a16 Qualcomm® Dragonwing™ Q-8750 7.243 ms 14 - 216 MB NPU
Segformer-Base ONNX w8a16 Snapdragon® 8 Elite Mobile 7.243 ms 14 - 216 MB NPU
Segformer-Base ONNX w8a16 Snapdragon® 8 Elite Gen 5 Mobile 5.668 ms 12 - 217 MB NPU
Segformer-Base ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 16.922 ms 12 - 233 MB NPU
Segformer-Base ONNX w8a8 Snapdragon® X2 Elite 1.947 ms 9 - 9 MB NPU
Segformer-Base ONNX w8a8 Snapdragon® X Elite 5.036 ms 5 - 5 MB NPU
Segformer-Base ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 3.224 ms 0 - 212 MB NPU
Segformer-Base ONNX w8a8 Snapdragon® 8 Gen 1 Mobile 6.971 ms 6 - 223 MB NPU
Segformer-Base ONNX w8a8 Qualcomm® Dragonwing™ QCS6490 19.719 ms 8 - 11 MB NPU
Segformer-Base ONNX w8a8 Qualcomm® Dragonwing™ IQ-8275 4.619 ms 5 - 9 MB NPU
Segformer-Base ONNX w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 4.746 ms 5 - 13 MB NPU
Segformer-Base ONNX w8a8 Qualcomm® QCS8450 6.971 ms 6 - 223 MB NPU
Segformer-Base ONNX w8a8 Qualcomm® Dragonwing™ IQ-9075 6.62 ms 8 - 10 MB NPU
Segformer-Base ONNX w8a8 Qualcomm® Dragonwing™ IQ-X7181 5.036 ms 5 - 5 MB NPU
Segformer-Base ONNX w8a8 Qualcomm® Dragonwing™ Q-6690 30.336 ms 8 - 236 MB NPU
Segformer-Base ONNX w8a8 Qualcomm® Dragonwing™ Q-7790 5.417 ms 8 - 204 MB NPU
Segformer-Base ONNX w8a8 Qualcomm® Dragonwing™ Q-8750 2.394 ms 0 - 188 MB NPU
Segformer-Base ONNX w8a8 Snapdragon® 8 Elite Mobile 2.394 ms 0 - 188 MB NPU
Segformer-Base ONNX w8a8 Snapdragon® 8 Elite Gen 5 Mobile 1.912 ms 0 - 193 MB NPU
Segformer-Base ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 5.417 ms 8 - 204 MB NPU
Segformer-Base QNN_DLC float Snapdragon® X2 Elite 12.519 ms 3 - 3 MB NPU
Segformer-Base QNN_DLC float Snapdragon® X Elite 23.566 ms 3 - 3 MB NPU
Segformer-Base QNN_DLC float Snapdragon® 8 Gen 3 Mobile 16.396 ms 3 - 226 MB NPU
Segformer-Base QNN_DLC float Snapdragon® 8 Gen 1 Mobile 29.58 ms 3 - 227 MB NPU
Segformer-Base QNN_DLC float Qualcomm® Dragonwing™ IQ-8275 23.181 ms 3 - 18 MB NPU
Segformer-Base QNN_DLC float Qualcomm® Dragonwing™ IQ-8275 48.885 ms 1 - 190 MB NPU
Segformer-Base QNN_DLC float Qualcomm® Dragonwing™ QCS8550 (Proxy) 22.628 ms 3 - 5 MB NPU
Segformer-Base QNN_DLC float Qualcomm® SA8775P 24.416 ms 1 - 193 MB NPU
Segformer-Base QNN_DLC float Qualcomm® SA8650P 24.416 ms 1 - 193 MB NPU
Segformer-Base QNN_DLC float Qualcomm® SA8255P 24.416 ms 1 - 193 MB NPU
Segformer-Base QNN_DLC float Qualcomm® QCS8450 29.58 ms 3 - 227 MB NPU
Segformer-Base QNN_DLC float Qualcomm® Dragonwing™ IQ-9075 25.791 ms 3 - 17 MB NPU
Segformer-Base QNN_DLC float Qualcomm® Dragonwing™ IQ-X7181 23.566 ms 3 - 3 MB NPU
Segformer-Base QNN_DLC float Qualcomm® Dragonwing™ Q-8750 13.161 ms 0 - 196 MB NPU
Segformer-Base QNN_DLC float Qualcomm® SA7255P 48.885 ms 1 - 190 MB NPU
Segformer-Base QNN_DLC float Qualcomm® SA8295P 27.859 ms 0 - 191 MB NPU
Segformer-Base QNN_DLC float Snapdragon® 8 Elite Mobile 13.161 ms 0 - 196 MB NPU
Segformer-Base QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 13.628 ms 3 - 196 MB NPU
Segformer-Base QNN_DLC w8a16 Snapdragon® X2 Elite 8.953 ms 2 - 2 MB NPU
Segformer-Base QNN_DLC w8a16 Snapdragon® X Elite 19.498 ms 2 - 2 MB NPU
Segformer-Base QNN_DLC w8a16 Snapdragon® 8 Gen 3 Mobile 15.247 ms 2 - 240 MB NPU
Segformer-Base QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-8275 19.495 ms 2 - 10 MB NPU
Segformer-Base QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-8275 32.443 ms 2 - 204 MB NPU
Segformer-Base QNN_DLC w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 20.199 ms 2 - 3 MB NPU
Segformer-Base QNN_DLC w8a16 Qualcomm® SA8775P 20.236 ms 2 - 206 MB NPU
Segformer-Base QNN_DLC w8a16 Qualcomm® SA8650P 20.236 ms 2 - 206 MB NPU
Segformer-Base QNN_DLC w8a16 Qualcomm® SA8255P 20.236 ms 2 - 206 MB NPU
Segformer-Base QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-9075 20.802 ms 0 - 8 MB NPU
Segformer-Base QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-X7181 19.498 ms 2 - 2 MB NPU
Segformer-Base QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-6690 127.564 ms 2 - 255 MB NPU
Segformer-Base QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-7790 33.481 ms 2 - 231 MB NPU
Segformer-Base QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-8750 11.199 ms 1 - 207 MB NPU
Segformer-Base QNN_DLC w8a16 Qualcomm® SA7255P 32.443 ms 2 - 204 MB NPU
Segformer-Base QNN_DLC w8a16 Snapdragon® 8 Elite Mobile 11.199 ms 1 - 207 MB NPU
Segformer-Base QNN_DLC w8a16 Snapdragon® 8 Elite Gen 5 Mobile 9.783 ms 1 - 213 MB NPU
Segformer-Base QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 33.481 ms 2 - 231 MB NPU
Segformer-Base QNN_DLC w8a8 Snapdragon® X2 Elite 2.554 ms 1 - 1 MB NPU
Segformer-Base QNN_DLC w8a8 Snapdragon® X Elite 6.389 ms 1 - 1 MB NPU
Segformer-Base QNN_DLC w8a8 Snapdragon® 8 Gen 3 Mobile 3.94 ms 0 - 199 MB NPU
Segformer-Base QNN_DLC w8a8 Snapdragon® 8 Gen 1 Mobile 8.649 ms 0 - 198 MB NPU
Segformer-Base QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS6490 21.475 ms 1 - 6 MB NPU
Segformer-Base QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-8275 5.503 ms 1 - 6 MB NPU
Segformer-Base QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-8275 10.879 ms 1 - 174 MB NPU
Segformer-Base QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 5.753 ms 1 - 5 MB NPU
Segformer-Base QNN_DLC w8a8 Qualcomm® SA8775P 6.4 ms 1 - 174 MB NPU
Segformer-Base QNN_DLC w8a8 Qualcomm® SA8650P 6.4 ms 1 - 174 MB NPU
Segformer-Base QNN_DLC w8a8 Qualcomm® SA8255P 6.4 ms 1 - 174 MB NPU
Segformer-Base QNN_DLC w8a8 Qualcomm® QCS8450 8.649 ms 0 - 198 MB NPU
Segformer-Base QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-9075 6.169 ms 2 - 7 MB NPU
Segformer-Base QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-X7181 6.389 ms 1 - 1 MB NPU
Segformer-Base QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-6690 34.059 ms 1 - 187 MB NPU
Segformer-Base QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-7790 6.834 ms 1 - 179 MB NPU
Segformer-Base QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-8750 2.844 ms 0 - 176 MB NPU
Segformer-Base QNN_DLC w8a8 Qualcomm® SA7255P 10.879 ms 1 - 174 MB NPU
Segformer-Base QNN_DLC w8a8 Qualcomm® SA8295P 7.797 ms 0 - 172 MB NPU
Segformer-Base QNN_DLC w8a8 Snapdragon® 8 Elite Mobile 2.844 ms 0 - 176 MB NPU
Segformer-Base QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 Mobile 2.247 ms 1 - 184 MB NPU
Segformer-Base QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 6.834 ms 1 - 179 MB NPU
Segformer-Base TFLITE float Snapdragon® 8 Gen 3 Mobile 16.356 ms 8 - 238 MB NPU
Segformer-Base TFLITE float Snapdragon® 8 Gen 1 Mobile 29.407 ms 9 - 234 MB NPU
Segformer-Base TFLITE float Qualcomm® Dragonwing™ IQ-8275 22.98 ms 9 - 32 MB NPU
Segformer-Base TFLITE float Qualcomm® Dragonwing™ IQ-8275 48.956 ms 3 - 194 MB NPU
Segformer-Base TFLITE float Qualcomm® Dragonwing™ QCS8550 (Proxy) 22.636 ms 9 - 21 MB NPU
Segformer-Base TFLITE float Qualcomm® SA8775P 24.485 ms 10 - 202 MB NPU
Segformer-Base TFLITE float Qualcomm® SA8650P 24.485 ms 10 - 202 MB NPU
Segformer-Base TFLITE float Qualcomm® SA8255P 24.485 ms 10 - 202 MB NPU
Segformer-Base TFLITE float Qualcomm® QCS8450 29.407 ms 9 - 234 MB NPU
Segformer-Base TFLITE float Qualcomm® Dragonwing™ IQ-9075 29.12 ms 8 - 31 MB NPU
Segformer-Base TFLITE float Qualcomm® Dragonwing™ Q-8750 13.212 ms 9 - 205 MB NPU
Segformer-Base TFLITE float Qualcomm® SA7255P 48.956 ms 3 - 194 MB NPU
Segformer-Base TFLITE float Qualcomm® SA8295P 27.857 ms 14 - 199 MB NPU
Segformer-Base TFLITE float Snapdragon® 8 Elite Mobile 13.212 ms 9 - 205 MB NPU
Segformer-Base TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 13.727 ms 8 - 199 MB NPU
Segformer-Base TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 7.108 ms 2 - 211 MB NPU
Segformer-Base TFLITE w8a8 Snapdragon® 8 Gen 1 Mobile 12.053 ms 2 - 212 MB NPU
Segformer-Base TFLITE w8a8 Qualcomm® Dragonwing™ QCS6490 147.26 ms 13 - 49 MB NPU
Segformer-Base TFLITE w8a8 Qualcomm® Dragonwing™ IQ-8275 9.578 ms 2 - 13 MB NPU
Segformer-Base TFLITE w8a8 Qualcomm® Dragonwing™ IQ-8275 18.268 ms 2 - 178 MB NPU
Segformer-Base TFLITE w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 10.117 ms 2 - 4 MB NPU
Segformer-Base TFLITE w8a8 Qualcomm® SA8775P 10.909 ms 2 - 185 MB NPU
Segformer-Base TFLITE w8a8 Qualcomm® SA8650P 10.909 ms 2 - 185 MB NPU
Segformer-Base TFLITE w8a8 Qualcomm® SA8255P 10.909 ms 2 - 185 MB NPU
Segformer-Base TFLITE w8a8 Qualcomm® QCS8450 12.053 ms 2 - 212 MB NPU
Segformer-Base TFLITE w8a8 Qualcomm® Dragonwing™ IQ-9075 10.633 ms 2 - 12 MB NPU
Segformer-Base TFLITE w8a8 Qualcomm® Dragonwing™ Q-6690 101.986 ms 13 - 185 MB NPU
Segformer-Base TFLITE w8a8 Qualcomm® Dragonwing™ Q-7790 39.404 ms 13 - 72 MB NPU
Segformer-Base TFLITE w8a8 Qualcomm® Dragonwing™ Q-8750 5.712 ms 2 - 178 MB NPU
Segformer-Base TFLITE w8a8 Qualcomm® SA7255P 18.268 ms 2 - 178 MB NPU
Segformer-Base TFLITE w8a8 Qualcomm® SA8295P 12.851 ms 2 - 183 MB NPU
Segformer-Base TFLITE w8a8 Snapdragon® 8 Elite Mobile 5.712 ms 2 - 178 MB NPU
Segformer-Base TFLITE w8a8 Snapdragon® 8 Elite Gen 5 Mobile 4.558 ms 3 - 181 MB NPU
Segformer-Base TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 39.404 ms 13 - 72 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