Hugging Face's logo

qualcomm
/
YOLOv11-Segmentation

Image Segmentation
PyTorch
real_time
android
Model card Files
xet
 Community

YOLOv11-Segmentation: Optimized for Qualcomm Devices

Ultralytics YOLOv11 is a machine learning model that predicts bounding boxes, segmentation masks and classes of objects in an image.

This is based on the implementation of YOLOv11-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

Due to licensing restrictions, we cannot distribute pre-exported model assets for this model. 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

See our repository for YOLOv11-Segmentation on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.semantic_segmentation

Model Stats:

  • Input resolution: 640x640
  • Model checkpoint: YOLO11N-Seg
  • Model size (float): 11.1 MB
  • Model size (w8a16): 11.4 MB
  • Number of output classes: 80
  • Number of parameters: 2.89M

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
YOLOv11-Segmentation ONNX float Snapdragon® X2 Elite 3.791 ms 17 - 17 MB NPU
YOLOv11-Segmentation ONNX float Snapdragon® X Elite 7.582 ms 17 - 17 MB NPU
YOLOv11-Segmentation ONNX float Snapdragon® 8 Gen 3 Mobile 6.111 ms 17 - 241 MB NPU
YOLOv11-Segmentation ONNX float Snapdragon® 8 Gen 1 Mobile 13.436 ms 17 - 230 MB NPU
YOLOv11-Segmentation ONNX float Qualcomm® Dragonwing™ IQ-8275 9.424 ms 15 - 19 MB NPU
YOLOv11-Segmentation ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 8.036 ms 15 - 20 MB NPU
YOLOv11-Segmentation ONNX float Qualcomm® QCS8450 13.436 ms 17 - 230 MB NPU
YOLOv11-Segmentation ONNX float Qualcomm® Dragonwing™ IQ-9075 9.203 ms 16 - 19 MB NPU
YOLOv11-Segmentation ONNX float Qualcomm® Dragonwing™ IQ-X7181 7.582 ms 17 - 17 MB NPU
YOLOv11-Segmentation ONNX float Qualcomm® Dragonwing™ Q-8750 4.938 ms 12 - 213 MB NPU
YOLOv11-Segmentation ONNX float Snapdragon® 8 Elite Mobile 4.938 ms 12 - 213 MB NPU
YOLOv11-Segmentation ONNX float Snapdragon® 8 Elite Gen 5 Mobile 3.426 ms 0 - 222 MB NPU
YOLOv11-Segmentation ONNX w8a16 Snapdragon® X2 Elite 2.672 ms 9 - 9 MB NPU
YOLOv11-Segmentation ONNX w8a16 Snapdragon® X Elite 6.33 ms 7 - 7 MB NPU
YOLOv11-Segmentation ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 3.709 ms 0 - 227 MB NPU
YOLOv11-Segmentation ONNX w8a16 Snapdragon® 8 Gen 1 Mobile 10.735 ms 8 - 235 MB NPU
YOLOv11-Segmentation ONNX w8a16 Qualcomm® Dragonwing™ QCS6490 19.397 ms 8 - 10 MB NPU
YOLOv11-Segmentation ONNX w8a16 Qualcomm® Dragonwing™ IQ-8275 5.437 ms 8 - 11 MB NPU
YOLOv11-Segmentation ONNX w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 6.023 ms 8 - 126 MB NPU
YOLOv11-Segmentation ONNX w8a16 Qualcomm® QCS8450 10.735 ms 8 - 235 MB NPU
YOLOv11-Segmentation ONNX w8a16 Qualcomm® Dragonwing™ IQ-9075 6.518 ms 8 - 10 MB NPU
YOLOv11-Segmentation ONNX w8a16 Qualcomm® Dragonwing™ IQ-X7181 6.33 ms 7 - 7 MB NPU
YOLOv11-Segmentation ONNX w8a16 Qualcomm® Dragonwing™ Q-6690 30.185 ms 8 - 210 MB NPU
YOLOv11-Segmentation ONNX w8a16 Qualcomm® Dragonwing™ Q-7790 7.16 ms 8 - 210 MB NPU
YOLOv11-Segmentation ONNX w8a16 Qualcomm® Dragonwing™ Q-8750 2.8 ms 0 - 89 MB NPU
YOLOv11-Segmentation ONNX w8a16 Snapdragon® 8 Elite Mobile 2.8 ms 0 - 89 MB NPU
YOLOv11-Segmentation ONNX w8a16 Snapdragon® 8 Elite Gen 5 Mobile 2.502 ms 0 - 90 MB NPU
YOLOv11-Segmentation ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 7.16 ms 8 - 210 MB NPU
YOLOv11-Segmentation QNN_DLC float Snapdragon® X2 Elite 3.093 ms 5 - 5 MB NPU
YOLOv11-Segmentation QNN_DLC float Snapdragon® X Elite 5.485 ms 5 - 5 MB NPU
YOLOv11-Segmentation QNN_DLC float Snapdragon® 8 Gen 3 Mobile 3.623 ms 0 - 211 MB NPU
YOLOv11-Segmentation QNN_DLC float Snapdragon® 8 Gen 1 Mobile 10.262 ms 2 - 202 MB NPU
YOLOv11-Segmentation QNN_DLC float Qualcomm® Dragonwing™ IQ-8275 6.401 ms 5 - 16 MB NPU
YOLOv11-Segmentation QNN_DLC float Qualcomm® Dragonwing™ QCS8550 (Proxy) 4.916 ms 5 - 6 MB NPU
YOLOv11-Segmentation QNN_DLC float Qualcomm® SA8775P 6.73 ms 0 - 184 MB NPU
YOLOv11-Segmentation QNN_DLC float Qualcomm® SA8650P 6.73 ms 0 - 184 MB NPU
YOLOv11-Segmentation QNN_DLC float Qualcomm® SA8255P 6.73 ms 0 - 184 MB NPU
YOLOv11-Segmentation QNN_DLC float Qualcomm® QCS8450 10.262 ms 2 - 202 MB NPU
YOLOv11-Segmentation QNN_DLC float Qualcomm® Dragonwing™ IQ-9075 6.451 ms 5 - 15 MB NPU
YOLOv11-Segmentation QNN_DLC float Qualcomm® Dragonwing™ IQ-X7181 5.485 ms 5 - 5 MB NPU
YOLOv11-Segmentation QNN_DLC float Qualcomm® Dragonwing™ Q-8750 2.93 ms 0 - 189 MB NPU
YOLOv11-Segmentation QNN_DLC float Qualcomm® SA7255P 16.268 ms 0 - 183 MB NPU
YOLOv11-Segmentation QNN_DLC float Qualcomm® SA8295P 10.326 ms 0 - 173 MB NPU
YOLOv11-Segmentation QNN_DLC float Snapdragon® 8 Elite Mobile 2.93 ms 0 - 189 MB NPU
YOLOv11-Segmentation QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 2.169 ms 5 - 200 MB NPU
YOLOv11-Segmentation QNN_DLC w8a16 Snapdragon® X2 Elite 2.335 ms 2 - 2 MB NPU
YOLOv11-Segmentation QNN_DLC w8a16 Snapdragon® X Elite 5.286 ms 2 - 2 MB NPU
YOLOv11-Segmentation QNN_DLC w8a16 Snapdragon® 8 Gen 3 Mobile 3.164 ms 2 - 206 MB NPU
YOLOv11-Segmentation QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-8275 4.564 ms 2 - 9 MB NPU
YOLOv11-Segmentation QNN_DLC w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 4.671 ms 2 - 111 MB NPU
YOLOv11-Segmentation QNN_DLC w8a16 Qualcomm® SA8775P 5.385 ms 1 - 181 MB NPU
YOLOv11-Segmentation QNN_DLC w8a16 Qualcomm® SA8650P 5.385 ms 1 - 181 MB NPU
YOLOv11-Segmentation QNN_DLC w8a16 Qualcomm® SA8255P 5.385 ms 1 - 181 MB NPU
YOLOv11-Segmentation QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-9075 5.153 ms 1 - 7 MB NPU
YOLOv11-Segmentation QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-X7181 5.286 ms 2 - 2 MB NPU
YOLOv11-Segmentation QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-6690 24.236 ms 3 - 184 MB NPU
YOLOv11-Segmentation QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-7790 5.069 ms 1 - 184 MB NPU
YOLOv11-Segmentation QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-8750 2.238 ms 2 - 186 MB NPU
YOLOv11-Segmentation QNN_DLC w8a16 Qualcomm® SA7255P 8.822 ms 1 - 180 MB NPU
YOLOv11-Segmentation QNN_DLC w8a16 Snapdragon® 8 Elite Mobile 2.238 ms 2 - 186 MB NPU
YOLOv11-Segmentation QNN_DLC w8a16 Snapdragon® 8 Elite Gen 5 Mobile 1.94 ms 2 - 190 MB NPU
YOLOv11-Segmentation QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 5.069 ms 1 - 184 MB NPU
YOLOv11-Segmentation TFLITE float Snapdragon® 8 Gen 3 Mobile 3.229 ms 0 - 106 MB NPU
YOLOv11-Segmentation TFLITE float Snapdragon® 8 Gen 1 Mobile 9.356 ms 4 - 91 MB NPU
YOLOv11-Segmentation TFLITE float Qualcomm® Dragonwing™ IQ-8275 5.933 ms 4 - 23 MB NPU
YOLOv11-Segmentation TFLITE float Qualcomm® Dragonwing™ QCS8550 (Proxy) 4.451 ms 4 - 6 MB NPU
YOLOv11-Segmentation TFLITE float Qualcomm® SA8775P 6.18 ms 4 - 85 MB NPU
YOLOv11-Segmentation TFLITE float Qualcomm® SA8650P 6.18 ms 4 - 85 MB NPU
YOLOv11-Segmentation TFLITE float Qualcomm® SA8255P 6.18 ms 4 - 85 MB NPU
YOLOv11-Segmentation TFLITE float Qualcomm® QCS8450 9.356 ms 4 - 91 MB NPU
YOLOv11-Segmentation TFLITE float Qualcomm® Dragonwing™ IQ-9075 5.939 ms 4 - 22 MB NPU
YOLOv11-Segmentation TFLITE float Qualcomm® Dragonwing™ Q-8750 2.442 ms 0 - 95 MB NPU
YOLOv11-Segmentation TFLITE float Qualcomm® SA7255P 15.552 ms 4 - 83 MB NPU
YOLOv11-Segmentation TFLITE float Qualcomm® SA8295P 9.557 ms 4 - 61 MB NPU
YOLOv11-Segmentation TFLITE float Snapdragon® 8 Elite Mobile 2.442 ms 0 - 95 MB NPU
YOLOv11-Segmentation TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 2.037 ms 0 - 95 MB NPU

License

  • The license for the original implementation of YOLOv11-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