Hugging Face's logo

qualcomm
/
DeepLabXception

Image Segmentation
PyTorch
bu_auto
android
Model card Files
xet
 Community

DeepLabXception: Optimized for Qualcomm Devices

DeepLabXception is a semantic segmentation model supporting multiple backbones like ResNet-101 and Xception, with flexible dataset compatibility including COCO, VOC, and Cityscapes.

This is based on the implementation of DeepLabXception 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 DeepLabXception 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 DeepLabXception on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.semantic_segmentation

Model Stats:

  • Input resolution: 480x520
  • Model checkpoint: COCO_WITH_VOC_LABELS_V1
  • Model size (float): 158 MB
  • Number of output classes: 21
  • Number of parameters: 41.26M

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
DeepLabXception ONNX float Snapdragon® X2 Elite 10.473 ms 3 - 3 MB NPU
DeepLabXception ONNX float Snapdragon® X Elite 23.103 ms 86 - 86 MB NPU
DeepLabXception ONNX float Snapdragon® 8 Gen 3 Mobile 17.102 ms 0 - 354 MB NPU
DeepLabXception ONNX float Snapdragon® 8 Gen 1 Mobile 51.146 ms 0 - 353 MB NPU
DeepLabXception ONNX float Qualcomm® Dragonwing™ IQ-8275 35.46 ms 3 - 9 MB NPU
DeepLabXception ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 22.836 ms 0 - 96 MB NPU
DeepLabXception ONNX float Qualcomm® QCS8450 51.146 ms 0 - 353 MB NPU
DeepLabXception ONNX float Qualcomm® Dragonwing™ IQ-9075 32.515 ms 3 - 8 MB NPU
DeepLabXception ONNX float Qualcomm® Dragonwing™ IQ-X7181 23.103 ms 86 - 86 MB NPU
DeepLabXception ONNX float Qualcomm® Dragonwing™ Q-8750 13.241 ms 1 - 251 MB NPU
DeepLabXception ONNX float Snapdragon® 8 Elite Mobile 13.241 ms 1 - 251 MB NPU
DeepLabXception ONNX float Snapdragon® 8 Elite Gen 5 Mobile 8.994 ms 2 - 256 MB NPU
DeepLabXception ONNX w8a8 Snapdragon® X2 Elite 3.434 ms 2 - 2 MB NPU
DeepLabXception ONNX w8a8 Snapdragon® X Elite 7.76 ms 44 - 44 MB NPU
DeepLabXception ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 5.243 ms 0 - 385 MB NPU
DeepLabXception ONNX w8a8 Snapdragon® 8 Gen 1 Mobile 12.26 ms 0 - 376 MB NPU
DeepLabXception ONNX w8a8 Qualcomm® Dragonwing™ QCS6490 45.99 ms 0 - 4 MB NPU
DeepLabXception ONNX w8a8 Qualcomm® Dragonwing™ IQ-8275 7.232 ms 0 - 5 MB NPU
DeepLabXception ONNX w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 7.464 ms 0 - 50 MB NPU
DeepLabXception ONNX w8a8 Qualcomm® QCS8450 12.26 ms 0 - 376 MB NPU
DeepLabXception ONNX w8a8 Qualcomm® Dragonwing™ IQ-9075 7.385 ms 0 - 4 MB NPU
DeepLabXception ONNX w8a8 Qualcomm® Dragonwing™ IQ-X7181 7.76 ms 44 - 44 MB NPU
DeepLabXception ONNX w8a8 Qualcomm® Dragonwing™ Q-6690 91.992 ms 0 - 307 MB NPU
DeepLabXception ONNX w8a8 Qualcomm® Dragonwing™ Q-7790 12.524 ms 1 - 279 MB NPU
DeepLabXception ONNX w8a8 Qualcomm® Dragonwing™ Q-8750 4.24 ms 0 - 287 MB NPU
DeepLabXception ONNX w8a8 Snapdragon® 8 Elite Mobile 4.24 ms 0 - 287 MB NPU
DeepLabXception ONNX w8a8 Snapdragon® 8 Elite Gen 5 Mobile 3.169 ms 0 - 297 MB NPU
DeepLabXception ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 12.524 ms 1 - 279 MB NPU
DeepLabXception QNN_DLC float Snapdragon® X2 Elite 11.465 ms 3 - 3 MB NPU
DeepLabXception QNN_DLC float Snapdragon® X Elite 22.968 ms 3 - 3 MB NPU
DeepLabXception QNN_DLC float Snapdragon® 8 Gen 3 Mobile 16.138 ms 3 - 361 MB NPU
DeepLabXception QNN_DLC float Snapdragon® 8 Gen 1 Mobile 46.177 ms 0 - 353 MB NPU
DeepLabXception QNN_DLC float Qualcomm® Dragonwing™ IQ-8275 33.973 ms 3 - 8 MB NPU
DeepLabXception QNN_DLC float Qualcomm® Dragonwing™ IQ-8275 112.919 ms 2 - 245 MB NPU
DeepLabXception QNN_DLC float Qualcomm® Dragonwing™ QCS8550 (Proxy) 21.942 ms 3 - 8 MB NPU
DeepLabXception QNN_DLC float Qualcomm® SA8775P 30.597 ms 1 - 245 MB NPU
DeepLabXception QNN_DLC float Qualcomm® SA8650P 30.597 ms 1 - 245 MB NPU
DeepLabXception QNN_DLC float Qualcomm® SA8255P 30.597 ms 1 - 245 MB NPU
DeepLabXception QNN_DLC float Qualcomm® QCS8450 46.177 ms 0 - 353 MB NPU
DeepLabXception QNN_DLC float Qualcomm® Dragonwing™ IQ-9075 31.171 ms 3 - 8 MB NPU
DeepLabXception QNN_DLC float Qualcomm® Dragonwing™ IQ-X7181 22.968 ms 3 - 3 MB NPU
DeepLabXception QNN_DLC float Qualcomm® Dragonwing™ Q-8750 12.202 ms 0 - 249 MB NPU
DeepLabXception QNN_DLC float Qualcomm® SA7255P 112.919 ms 2 - 245 MB NPU
DeepLabXception QNN_DLC float Qualcomm® SA8295P 39.138 ms 0 - 239 MB NPU
DeepLabXception QNN_DLC float Snapdragon® 8 Elite Mobile 12.202 ms 0 - 249 MB NPU
DeepLabXception QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 9.654 ms 3 - 259 MB NPU
DeepLabXception QNN_DLC w8a8 Snapdragon® X2 Elite 3.902 ms 1 - 1 MB NPU
DeepLabXception QNN_DLC w8a8 Snapdragon® X Elite 8.55 ms 1 - 1 MB NPU
DeepLabXception QNN_DLC w8a8 Snapdragon® 8 Gen 3 Mobile 5.564 ms 0 - 372 MB NPU
DeepLabXception QNN_DLC w8a8 Snapdragon® 8 Gen 1 Mobile 13.582 ms 1 - 368 MB NPU
DeepLabXception QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS6490 46.36 ms 2 - 5 MB NPU
DeepLabXception QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-8275 7.652 ms 1 - 4 MB NPU
DeepLabXception QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-8275 20.367 ms 1 - 283 MB NPU
DeepLabXception QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 7.878 ms 1 - 3 MB NPU
DeepLabXception QNN_DLC w8a8 Qualcomm® SA8775P 8.075 ms 1 - 286 MB NPU
DeepLabXception QNN_DLC w8a8 Qualcomm® SA8650P 8.075 ms 1 - 286 MB NPU
DeepLabXception QNN_DLC w8a8 Qualcomm® SA8255P 8.075 ms 1 - 286 MB NPU
DeepLabXception QNN_DLC w8a8 Qualcomm® QCS8450 13.582 ms 1 - 368 MB NPU
DeepLabXception QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-9075 7.776 ms 3 - 5 MB NPU
DeepLabXception QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-X7181 8.55 ms 1 - 1 MB NPU
DeepLabXception QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-6690 93.89 ms 1 - 303 MB NPU
DeepLabXception QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-7790 12.948 ms 1 - 278 MB NPU
DeepLabXception QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-8750 4.37 ms 1 - 289 MB NPU
DeepLabXception QNN_DLC w8a8 Qualcomm® SA7255P 20.367 ms 1 - 283 MB NPU
DeepLabXception QNN_DLC w8a8 Qualcomm® SA8295P 12.744 ms 0 - 279 MB NPU
DeepLabXception QNN_DLC w8a8 Snapdragon® 8 Elite Mobile 4.37 ms 1 - 289 MB NPU
DeepLabXception QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 Mobile 3.282 ms 1 - 281 MB NPU
DeepLabXception QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 12.948 ms 1 - 278 MB NPU
DeepLabXception TFLITE float Snapdragon® 8 Gen 3 Mobile 16.18 ms 0 - 453 MB NPU
DeepLabXception TFLITE float Snapdragon® 8 Gen 1 Mobile 45.933 ms 0 - 452 MB NPU
DeepLabXception TFLITE float Qualcomm® Dragonwing™ IQ-8275 34.242 ms 0 - 94 MB NPU
DeepLabXception TFLITE float Qualcomm® Dragonwing™ IQ-8275 113.17 ms 1 - 343 MB NPU
DeepLabXception TFLITE float Qualcomm® Dragonwing™ QCS8550 (Proxy) 21.334 ms 0 - 3 MB NPU
DeepLabXception TFLITE float Qualcomm® SA8775P 30.641 ms 0 - 343 MB NPU
DeepLabXception TFLITE float Qualcomm® SA8650P 30.641 ms 0 - 343 MB NPU
DeepLabXception TFLITE float Qualcomm® SA8255P 30.641 ms 0 - 343 MB NPU
DeepLabXception TFLITE float Qualcomm® QCS8450 45.933 ms 0 - 452 MB NPU
DeepLabXception TFLITE float Qualcomm® Dragonwing™ IQ-9075 30.794 ms 0 - 93 MB NPU
DeepLabXception TFLITE float Qualcomm® Dragonwing™ Q-8750 12.47 ms 0 - 354 MB NPU
DeepLabXception TFLITE float Qualcomm® SA7255P 113.17 ms 1 - 343 MB NPU
DeepLabXception TFLITE float Qualcomm® SA8295P 38.705 ms 0 - 337 MB NPU
DeepLabXception TFLITE float Snapdragon® 8 Elite Mobile 12.47 ms 0 - 354 MB NPU
DeepLabXception TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 9.307 ms 0 - 360 MB NPU
DeepLabXception TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 4.981 ms 0 - 366 MB NPU
DeepLabXception TFLITE w8a8 Snapdragon® 8 Gen 1 Mobile 12.626 ms 0 - 357 MB NPU
DeepLabXception TFLITE w8a8 Qualcomm® Dragonwing™ QCS6490 45.096 ms 0 - 58 MB NPU
DeepLabXception TFLITE w8a8 Qualcomm® Dragonwing™ IQ-8275 6.888 ms 0 - 48 MB NPU
DeepLabXception TFLITE w8a8 Qualcomm® Dragonwing™ IQ-8275 19.007 ms 0 - 284 MB NPU
DeepLabXception TFLITE w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 6.961 ms 0 - 271 MB NPU
DeepLabXception TFLITE w8a8 Qualcomm® SA8775P 7.276 ms 0 - 285 MB NPU
DeepLabXception TFLITE w8a8 Qualcomm® SA8650P 7.276 ms 0 - 285 MB NPU
DeepLabXception TFLITE w8a8 Qualcomm® SA8255P 7.276 ms 0 - 285 MB NPU
DeepLabXception TFLITE w8a8 Qualcomm® QCS8450 12.626 ms 0 - 357 MB NPU
DeepLabXception TFLITE w8a8 Qualcomm® Dragonwing™ IQ-9075 6.982 ms 0 - 47 MB NPU
DeepLabXception TFLITE w8a8 Qualcomm® Dragonwing™ Q-6690 90.991 ms 0 - 291 MB NPU
DeepLabXception TFLITE w8a8 Qualcomm® Dragonwing™ Q-7790 11.231 ms 0 - 266 MB NPU
DeepLabXception TFLITE w8a8 Qualcomm® Dragonwing™ Q-8750 3.917 ms 0 - 271 MB NPU
DeepLabXception TFLITE w8a8 Qualcomm® SA7255P 19.007 ms 0 - 284 MB NPU
DeepLabXception TFLITE w8a8 Qualcomm® SA8295P 11.618 ms 0 - 276 MB NPU
DeepLabXception TFLITE w8a8 Snapdragon® 8 Elite Mobile 3.917 ms 0 - 271 MB NPU
DeepLabXception TFLITE w8a8 Snapdragon® 8 Elite Gen 5 Mobile 2.913 ms 0 - 285 MB NPU
DeepLabXception TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 11.231 ms 0 - 266 MB NPU

License

  • The license for the original implementation of DeepLabXception 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/DeepLabXception