Hugging Face's logo

qualcomm
/
YOLOv11-Detection

Object Detection
PyTorch
real_time
android
Model card Files
xet
Community

YOLOv11-Detection: Optimized for Mobile Deployment

Real-time object detection optimized for mobile and edge by Ultralytics

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

This model is an implementation of YOLOv11-Detection found here.

This repository provides scripts to run YOLOv11-Detection on Qualcomm® devices. More details on model performance across various devices, can be found here.

WARNING: The model assets are not readily available for download due to licensing restrictions.

Model Details

  • Model Type: Model_use_case.object_detection
  • Model Stats:
    • Model checkpoint: YOLO11-N
    • Input resolution: 640x640
    • Number of parameters: 2.64M
    • Model size (float): 10.1 MB
    • Model size (w8a8): 2.83 MB
    • Model size (w8a16): 3.30 MB
Model Precision Device Chipset Target Runtime Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit Target Model
YOLOv11-Detection float QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) TFLITE 13.544 ms 0 - 65 MB NPU --
YOLOv11-Detection float QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) QNN_DLC 12.427 ms 1 - 95 MB NPU --
YOLOv11-Detection float QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) TFLITE 7.285 ms 0 - 40 MB NPU --
YOLOv11-Detection float QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) QNN_DLC 8.669 ms 4 - 43 MB NPU --
YOLOv11-Detection float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) TFLITE 4.286 ms 0 - 22 MB NPU --
YOLOv11-Detection float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) QNN_DLC 3.836 ms 0 - 92 MB NPU --
YOLOv11-Detection float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) ONNX 5.801 ms 0 - 39 MB NPU --
YOLOv11-Detection float QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) TFLITE 5.576 ms 0 - 65 MB NPU --
YOLOv11-Detection float QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) QNN_DLC 5.216 ms 2 - 120 MB NPU --
YOLOv11-Detection float SA7255P ADP Qualcomm® SA7255P TFLITE 13.544 ms 0 - 65 MB NPU --
YOLOv11-Detection float SA7255P ADP Qualcomm® SA7255P QNN_DLC 12.427 ms 1 - 95 MB NPU --
YOLOv11-Detection float SA8255 (Proxy) Qualcomm® SA8255P (Proxy) TFLITE 4.304 ms 0 - 22 MB NPU --
YOLOv11-Detection float SA8255 (Proxy) Qualcomm® SA8255P (Proxy) QNN_DLC 3.835 ms 0 - 94 MB NPU --
YOLOv11-Detection float SA8295P ADP Qualcomm® SA8295P TFLITE 8.427 ms 0 - 33 MB NPU --
YOLOv11-Detection float SA8295P ADP Qualcomm® SA8295P QNN_DLC 8.027 ms 0 - 34 MB NPU --
YOLOv11-Detection float SA8650 (Proxy) Qualcomm® SA8650P (Proxy) TFLITE 4.305 ms 0 - 22 MB NPU --
YOLOv11-Detection float SA8650 (Proxy) Qualcomm® SA8650P (Proxy) QNN_DLC 3.825 ms 5 - 94 MB NPU --
YOLOv11-Detection float SA8775P ADP Qualcomm® SA8775P TFLITE 5.576 ms 0 - 65 MB NPU --
YOLOv11-Detection float SA8775P ADP Qualcomm® SA8775P QNN_DLC 5.216 ms 2 - 120 MB NPU --
YOLOv11-Detection float Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile TFLITE 4.302 ms 0 - 23 MB NPU --
YOLOv11-Detection float Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile QNN_DLC 3.827 ms 0 - 88 MB NPU --
YOLOv11-Detection float Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile ONNX 5.963 ms 0 - 57 MB NPU --
YOLOv11-Detection float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile TFLITE 3.133 ms 0 - 77 MB NPU --
YOLOv11-Detection float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN_DLC 2.752 ms 0 - 222 MB NPU --
YOLOv11-Detection float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile ONNX 3.855 ms 0 - 157 MB NPU --
YOLOv11-Detection float Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile TFLITE 3.087 ms 0 - 70 MB NPU --
YOLOv11-Detection float Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile QNN_DLC 2.567 ms 5 - 119 MB NPU --
YOLOv11-Detection float Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile ONNX 3.514 ms 5 - 87 MB NPU --
YOLOv11-Detection float Snapdragon X Elite CRD Snapdragon® X Elite QNN_DLC 4.277 ms 156 - 156 MB NPU --
YOLOv11-Detection float Snapdragon X Elite CRD Snapdragon® X Elite ONNX 5.717 ms 5 - 5 MB NPU --
YOLOv11-Detection w8a16 QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) QNN_DLC 7.137 ms 2 - 31 MB NPU --
YOLOv11-Detection w8a16 QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) QNN_DLC 4.399 ms 2 - 45 MB NPU --
YOLOv11-Detection w8a16 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) QNN_DLC 3.788 ms 2 - 14 MB NPU --
YOLOv11-Detection w8a16 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) ONNX 61.358 ms 10 - 195 MB NPU --
YOLOv11-Detection w8a16 QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) QNN_DLC 4.399 ms 2 - 31 MB NPU --
YOLOv11-Detection w8a16 RB3 Gen 2 (Proxy) Qualcomm® QCS6490 (Proxy) QNN_DLC 13.278 ms 2 - 38 MB NPU --
YOLOv11-Detection w8a16 RB3 Gen 2 (Proxy) Qualcomm® QCS6490 (Proxy) ONNX 170.117 ms 88 - 104 MB CPU --
YOLOv11-Detection w8a16 RB5 (Proxy) Qualcomm® QCS8250 (Proxy) ONNX 140.755 ms 90 - 97 MB CPU --
YOLOv11-Detection w8a16 SA7255P ADP Qualcomm® SA7255P QNN_DLC 7.137 ms 2 - 31 MB NPU --
YOLOv11-Detection w8a16 SA8255 (Proxy) Qualcomm® SA8255P (Proxy) QNN_DLC 3.777 ms 4 - 16 MB NPU --
YOLOv11-Detection w8a16 SA8295P ADP Qualcomm® SA8295P QNN_DLC 5.007 ms 0 - 37 MB NPU --
YOLOv11-Detection w8a16 SA8650 (Proxy) Qualcomm® SA8650P (Proxy) QNN_DLC 3.784 ms 4 - 15 MB NPU --
YOLOv11-Detection w8a16 SA8775P ADP Qualcomm® SA8775P QNN_DLC 4.399 ms 2 - 31 MB NPU --
YOLOv11-Detection w8a16 Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile QNN_DLC 3.788 ms 2 - 15 MB NPU --
YOLOv11-Detection w8a16 Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile ONNX 63.013 ms 10 - 195 MB NPU --
YOLOv11-Detection w8a16 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN_DLC 2.526 ms 2 - 44 MB NPU --
YOLOv11-Detection w8a16 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile ONNX 49.278 ms 4 - 2109 MB NPU --
YOLOv11-Detection w8a16 Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile QNN_DLC 1.816 ms 2 - 43 MB NPU --
YOLOv11-Detection w8a16 Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile ONNX 51.107 ms 7 - 653 MB NPU --
YOLOv11-Detection w8a16 Snapdragon X Elite CRD Snapdragon® X Elite QNN_DLC 4.207 ms 7 - 7 MB NPU --
YOLOv11-Detection w8a16 Snapdragon X Elite CRD Snapdragon® X Elite ONNX 59.34 ms 31 - 31 MB NPU --
YOLOv11-Detection w8a8 QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) TFLITE 3.672 ms 0 - 26 MB NPU --
YOLOv11-Detection w8a8 QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) QNN_DLC 3.538 ms 1 - 27 MB NPU --
YOLOv11-Detection w8a8 QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) TFLITE 1.972 ms 0 - 38 MB NPU --
YOLOv11-Detection w8a8 QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) QNN_DLC 1.938 ms 1 - 38 MB NPU --
YOLOv11-Detection w8a8 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) TFLITE 1.823 ms 0 - 12 MB NPU --
YOLOv11-Detection w8a8 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) QNN_DLC 1.718 ms 1 - 13 MB NPU --
YOLOv11-Detection w8a8 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) ONNX 6.355 ms 0 - 27 MB NPU --
YOLOv11-Detection w8a8 QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) TFLITE 2.282 ms 0 - 26 MB NPU --
YOLOv11-Detection w8a8 QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) QNN_DLC 2.134 ms 1 - 27 MB NPU --
YOLOv11-Detection w8a8 RB3 Gen 2 (Proxy) Qualcomm® QCS6490 (Proxy) TFLITE 4.238 ms 0 - 33 MB NPU --
YOLOv11-Detection w8a8 RB3 Gen 2 (Proxy) Qualcomm® QCS6490 (Proxy) QNN_DLC 5.278 ms 1 - 36 MB NPU --
YOLOv11-Detection w8a8 RB3 Gen 2 (Proxy) Qualcomm® QCS6490 (Proxy) ONNX 44.328 ms 23 - 40 MB CPU --
YOLOv11-Detection w8a8 RB5 (Proxy) Qualcomm® QCS8250 (Proxy) TFLITE 57.878 ms 2 - 9 MB NPU --
YOLOv11-Detection w8a8 RB5 (Proxy) Qualcomm® QCS8250 (Proxy) ONNX 44.199 ms 24 - 29 MB CPU --
YOLOv11-Detection w8a8 SA7255P ADP Qualcomm® SA7255P TFLITE 3.672 ms 0 - 26 MB NPU --
YOLOv11-Detection w8a8 SA7255P ADP Qualcomm® SA7255P QNN_DLC 3.538 ms 1 - 27 MB NPU --
YOLOv11-Detection w8a8 SA8255 (Proxy) Qualcomm® SA8255P (Proxy) TFLITE 1.829 ms 0 - 12 MB NPU --
YOLOv11-Detection w8a8 SA8255 (Proxy) Qualcomm® SA8255P (Proxy) QNN_DLC 1.722 ms 1 - 13 MB NPU --
YOLOv11-Detection w8a8 SA8295P ADP Qualcomm® SA8295P TFLITE 2.649 ms 0 - 31 MB NPU --
YOLOv11-Detection w8a8 SA8295P ADP Qualcomm® SA8295P QNN_DLC 2.504 ms 1 - 34 MB NPU --
YOLOv11-Detection w8a8 SA8650 (Proxy) Qualcomm® SA8650P (Proxy) TFLITE 1.839 ms 0 - 12 MB NPU --
YOLOv11-Detection w8a8 SA8650 (Proxy) Qualcomm® SA8650P (Proxy) QNN_DLC 1.718 ms 1 - 14 MB NPU --
YOLOv11-Detection w8a8 SA8775P ADP Qualcomm® SA8775P TFLITE 2.282 ms 0 - 26 MB NPU --
YOLOv11-Detection w8a8 SA8775P ADP Qualcomm® SA8775P QNN_DLC 2.134 ms 1 - 27 MB NPU --
YOLOv11-Detection w8a8 Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile TFLITE 1.824 ms 0 - 13 MB NPU --
YOLOv11-Detection w8a8 Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile QNN_DLC 1.714 ms 1 - 13 MB NPU --
YOLOv11-Detection w8a8 Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile ONNX 6.298 ms 0 - 26 MB NPU --
YOLOv11-Detection w8a8 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile TFLITE 1.204 ms 0 - 42 MB NPU --
YOLOv11-Detection w8a8 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN_DLC 1.179 ms 1 - 37 MB NPU --
YOLOv11-Detection w8a8 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile ONNX 4.57 ms 0 - 88 MB NPU --
YOLOv11-Detection w8a8 Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile TFLITE 1.11 ms 0 - 28 MB NPU --
YOLOv11-Detection w8a8 Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile QNN_DLC 1.041 ms 1 - 31 MB NPU --
YOLOv11-Detection w8a8 Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile ONNX 3.409 ms 1 - 60 MB NPU --
YOLOv11-Detection w8a8 Snapdragon X Elite CRD Snapdragon® X Elite QNN_DLC 1.96 ms 4 - 4 MB NPU --
YOLOv11-Detection w8a8 Snapdragon X Elite CRD Snapdragon® X Elite ONNX 6.774 ms 1 - 1 MB NPU --
YOLOv11-Detection w8a8_mixed_int16 QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) QNN_DLC 5.51 ms 1 - 28 MB NPU --
YOLOv11-Detection w8a8_mixed_int16 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) QNN_DLC 2.777 ms 2 - 13 MB NPU --
YOLOv11-Detection w8a8_mixed_int16 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) ONNX 60.911 ms 10 - 194 MB NPU --
YOLOv11-Detection w8a8_mixed_int16 QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) QNN_DLC 3.381 ms 1 - 30 MB NPU --
YOLOv11-Detection w8a8_mixed_int16 RB3 Gen 2 (Proxy) Qualcomm® QCS6490 (Proxy) ONNX 141.375 ms 75 - 92 MB CPU --
YOLOv11-Detection w8a8_mixed_int16 RB5 (Proxy) Qualcomm® QCS8250 (Proxy) ONNX 116.765 ms 70 - 77 MB CPU --
YOLOv11-Detection w8a8_mixed_int16 SA7255P ADP Qualcomm® SA7255P QNN_DLC 5.51 ms 1 - 28 MB NPU --
YOLOv11-Detection w8a8_mixed_int16 SA8255 (Proxy) Qualcomm® SA8255P (Proxy) QNN_DLC 2.811 ms 2 - 13 MB NPU --
YOLOv11-Detection w8a8_mixed_int16 SA8650 (Proxy) Qualcomm® SA8650P (Proxy) QNN_DLC 2.805 ms 2 - 12 MB NPU --
YOLOv11-Detection w8a8_mixed_int16 SA8775P ADP Qualcomm® SA8775P QNN_DLC 3.381 ms 1 - 30 MB NPU --
YOLOv11-Detection w8a8_mixed_int16 Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile QNN_DLC 2.806 ms 4 - 14 MB NPU --
YOLOv11-Detection w8a8_mixed_int16 Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile ONNX 61.57 ms 10 - 190 MB NPU --
YOLOv11-Detection w8a8_mixed_int16 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN_DLC 1.882 ms 2 - 37 MB NPU --
YOLOv11-Detection w8a8_mixed_int16 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile ONNX 47.321 ms 0 - 689 MB NPU --
YOLOv11-Detection w8a8_mixed_int16 Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile QNN_DLC 1.652 ms 2 - 38 MB NPU --
YOLOv11-Detection w8a8_mixed_int16 Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile ONNX 47.264 ms 8 - 656 MB NPU --
YOLOv11-Detection w8a8_mixed_int16 Snapdragon X Elite CRD Snapdragon® X Elite QNN_DLC 3.144 ms 5 - 5 MB NPU --
YOLOv11-Detection w8a8_mixed_int16 Snapdragon X Elite CRD Snapdragon® X Elite ONNX 61.883 ms 25 - 25 MB NPU --

Installation

Install the package via pip:

pip install "qai-hub-models[yolov11-det]"

Configure Qualcomm® AI Hub to run this model on a cloud-hosted device

Sign-in to Qualcomm® AI Hub with your Qualcomm® ID. Once signed in navigate to Account -> Settings -> API Token.

With this API token, you can configure your client to run models on the cloud hosted devices.

qai-hub configure --api_token API_TOKEN

Navigate to docs for more information.

Demo off target

The package contains a simple end-to-end demo that downloads pre-trained weights and runs this model on a sample input.

python -m qai_hub_models.models.yolov11_det.demo

The above demo runs a reference implementation of pre-processing, model inference, and post processing.

NOTE: If you want running in a Jupyter Notebook or Google Colab like environment, please add the following to your cell (instead of the above).

%run -m qai_hub_models.models.yolov11_det.demo

Run model on a cloud-hosted device

In addition to the demo, you can also run the model on a cloud-hosted Qualcomm® device. This script does the following:

  • Performance check on-device on a cloud-hosted device
  • Downloads compiled assets that can be deployed on-device for Android.
  • Accuracy check between PyTorch and on-device outputs.
python -m qai_hub_models.models.yolov11_det.export

How does this work?

This export script leverages Qualcomm® AI Hub to optimize, validate, and deploy this model on-device. Lets go through each step below in detail:

Step 1: Compile model for on-device deployment

To compile a PyTorch model for on-device deployment, we first trace the model in memory using the jit.trace and then call the submit_compile_job API.

import torch

import qai_hub as hub
from qai_hub_models.models.yolov11_det import Model

# Load the model
torch_model = Model.from_pretrained()

# Device
device = hub.Device("Samsung Galaxy S24")

# Trace model
input_shape = torch_model.get_input_spec()
sample_inputs = torch_model.sample_inputs()

pt_model = torch.jit.trace(torch_model, [torch.tensor(data[0]) for _, data in sample_inputs.items()])

# Compile model on a specific device
compile_job = hub.submit_compile_job(
    model=pt_model,
    device=device,
    input_specs=torch_model.get_input_spec(),
)

# Get target model to run on-device
target_model = compile_job.get_target_model()

Step 2: Performance profiling on cloud-hosted device

After compiling models from step 1. Models can be profiled model on-device using the target_model. Note that this scripts runs the model on a device automatically provisioned in the cloud. Once the job is submitted, you can navigate to a provided job URL to view a variety of on-device performance metrics.

profile_job = hub.submit_profile_job(
    model=target_model,
    device=device,
)

Step 3: Verify on-device accuracy

To verify the accuracy of the model on-device, you can run on-device inference on sample input data on the same cloud hosted device.

input_data = torch_model.sample_inputs()
inference_job = hub.submit_inference_job(
    model=target_model,
    device=device,
    inputs=input_data,
)
    on_device_output = inference_job.download_output_data()

With the output of the model, you can compute like PSNR, relative errors or spot check the output with expected output.

Note: This on-device profiling and inference requires access to Qualcomm® AI Hub. Sign up for access.

Run demo on a cloud-hosted device

You can also run the demo on-device.

python -m qai_hub_models.models.yolov11_det.demo --eval-mode on-device

NOTE: If you want running in a Jupyter Notebook or Google Colab like environment, please add the following to your cell (instead of the above).

%run -m qai_hub_models.models.yolov11_det.demo -- --eval-mode on-device

Deploying compiled model to Android

The models can be deployed using multiple runtimes:

  • TensorFlow Lite (.tflite export): This tutorial provides a guide to deploy the .tflite model in an Android application.

  • QNN (.so export ): This sample app provides instructions on how to use the .so shared library in an Android application.

View on Qualcomm® AI Hub

Get more details on YOLOv11-Detection's performance across various devices here. Explore all available models on Qualcomm® AI Hub

License

  • The license for the original implementation of YOLOv11-Detection can be found here.
  • The license for the compiled assets for on-device deployment can be found here

References

Community

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
Object Detection
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support