Hugging Face's logo

qualcomm
/
Yolo-X

Object Detection
PyTorch
LiteRT
real_time
android
Model card Files
xet
Community

Yolo-X: Optimized for Mobile Deployment

Real-time object detection optimized for mobile and edge

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

This model is an implementation of Yolo-X found here.

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

Model Details

  • Model Type: Model_use_case.object_detection
  • Model Stats:
    • Model checkpoint: YoloX Small
    • Input resolution: 640x640
    • Number of parameters: 8.98M
    • Model size (float): 34.3 MB
    • Model size (w8a16): 9.53 MB
    • Model size (w8a8): 8.96 MB
Model Precision Device Chipset Target Runtime Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit Target Model
Yolo-X float QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) TFLITE 30.572 ms 0 - 39 MB NPU Yolo-X.tflite
Yolo-X float QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) QNN_DLC 28.888 ms 2 - 73 MB NPU Yolo-X.dlc
Yolo-X float QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) TFLITE 13.628 ms 0 - 56 MB NPU Yolo-X.tflite
Yolo-X float QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) QNN_DLC 17.394 ms 4 - 49 MB NPU Yolo-X.dlc
Yolo-X float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) TFLITE 7.759 ms 0 - 9 MB NPU Yolo-X.tflite
Yolo-X float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) QNN_DLC 6.769 ms 5 - 44 MB NPU Yolo-X.dlc
Yolo-X float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) ONNX 14.786 ms 0 - 62 MB NPU Yolo-X.onnx.zip
Yolo-X float QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) TFLITE 10.829 ms 0 - 39 MB NPU Yolo-X.tflite
Yolo-X float QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) QNN_DLC 9.898 ms 1 - 71 MB NPU Yolo-X.dlc
Yolo-X float SA7255P ADP Qualcomm® SA7255P TFLITE 30.572 ms 0 - 39 MB NPU Yolo-X.tflite
Yolo-X float SA7255P ADP Qualcomm® SA7255P QNN_DLC 28.888 ms 2 - 73 MB NPU Yolo-X.dlc
Yolo-X float SA8255 (Proxy) Qualcomm® SA8255P (Proxy) TFLITE 7.765 ms 0 - 9 MB NPU Yolo-X.tflite
Yolo-X float SA8255 (Proxy) Qualcomm® SA8255P (Proxy) QNN_DLC 6.921 ms 5 - 46 MB NPU Yolo-X.dlc
Yolo-X float SA8295P ADP Qualcomm® SA8295P TFLITE 15.363 ms 0 - 49 MB NPU Yolo-X.tflite
Yolo-X float SA8295P ADP Qualcomm® SA8295P QNN_DLC 13.292 ms 4 - 48 MB NPU Yolo-X.dlc
Yolo-X float SA8650 (Proxy) Qualcomm® SA8650P (Proxy) TFLITE 7.597 ms 0 - 11 MB NPU Yolo-X.tflite
Yolo-X float SA8650 (Proxy) Qualcomm® SA8650P (Proxy) QNN_DLC 6.837 ms 5 - 41 MB NPU Yolo-X.dlc
Yolo-X float SA8775P ADP Qualcomm® SA8775P TFLITE 10.829 ms 0 - 39 MB NPU Yolo-X.tflite
Yolo-X float SA8775P ADP Qualcomm® SA8775P QNN_DLC 9.898 ms 1 - 71 MB NPU Yolo-X.dlc
Yolo-X float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile TFLITE 5.634 ms 0 - 48 MB NPU Yolo-X.tflite
Yolo-X float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN_DLC 5.152 ms 5 - 105 MB NPU Yolo-X.dlc
Yolo-X float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile ONNX 9.913 ms 5 - 123 MB NPU Yolo-X.onnx.zip
Yolo-X float Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile TFLITE 4.682 ms 0 - 44 MB NPU Yolo-X.tflite
Yolo-X float Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile QNN_DLC 3.944 ms 5 - 77 MB NPU Yolo-X.dlc
Yolo-X float Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile ONNX 8.238 ms 2 - 82 MB NPU Yolo-X.onnx.zip
Yolo-X float Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile TFLITE 3.575 ms 0 - 43 MB NPU Yolo-X.tflite
Yolo-X float Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile QNN_DLC 3.083 ms 5 - 84 MB NPU Yolo-X.dlc
Yolo-X float Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile ONNX 6.951 ms 5 - 92 MB NPU Yolo-X.onnx.zip
Yolo-X float Snapdragon X Elite CRD Snapdragon® X Elite QNN_DLC 7.556 ms 39 - 39 MB NPU Yolo-X.dlc
Yolo-X float Snapdragon X Elite CRD Snapdragon® X Elite ONNX 14.104 ms 14 - 14 MB NPU Yolo-X.onnx.zip
Yolo-X w8a16 QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) QNN_DLC 11.106 ms 2 - 46 MB NPU Yolo-X.dlc
Yolo-X w8a16 QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) QNN_DLC 6.612 ms 2 - 58 MB NPU Yolo-X.dlc
Yolo-X w8a16 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) QNN_DLC 5.202 ms 2 - 14 MB NPU Yolo-X.dlc
Yolo-X w8a16 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) ONNX 14.32 ms 0 - 54 MB NPU Yolo-X.onnx.zip
Yolo-X w8a16 QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) QNN_DLC 5.724 ms 1 - 46 MB NPU Yolo-X.dlc
Yolo-X w8a16 RB3 Gen 2 (Proxy) Qualcomm® QCS6490 (Proxy) QNN_DLC 23.176 ms 2 - 50 MB NPU Yolo-X.dlc
Yolo-X w8a16 RB3 Gen 2 (Proxy) Qualcomm® QCS6490 (Proxy) ONNX 393.119 ms 107 - 123 MB CPU Yolo-X.onnx.zip
Yolo-X w8a16 RB5 (Proxy) Qualcomm® QCS8250 (Proxy) ONNX 337.914 ms 106 - 110 MB CPU Yolo-X.onnx.zip
Yolo-X w8a16 SA7255P ADP Qualcomm® SA7255P QNN_DLC 11.106 ms 2 - 46 MB NPU Yolo-X.dlc
Yolo-X w8a16 SA8255 (Proxy) Qualcomm® SA8255P (Proxy) QNN_DLC 5.195 ms 2 - 13 MB NPU Yolo-X.dlc
Yolo-X w8a16 SA8295P ADP Qualcomm® SA8295P QNN_DLC 7.189 ms 2 - 53 MB NPU Yolo-X.dlc
Yolo-X w8a16 SA8650 (Proxy) Qualcomm® SA8650P (Proxy) QNN_DLC 5.186 ms 2 - 12 MB NPU Yolo-X.dlc
Yolo-X w8a16 SA8775P ADP Qualcomm® SA8775P QNN_DLC 5.724 ms 1 - 46 MB NPU Yolo-X.dlc
Yolo-X w8a16 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN_DLC 3.397 ms 2 - 60 MB NPU Yolo-X.dlc
Yolo-X w8a16 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile ONNX 10.037 ms 2 - 102 MB NPU Yolo-X.onnx.zip
Yolo-X w8a16 Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile QNN_DLC 2.392 ms 2 - 53 MB NPU Yolo-X.dlc
Yolo-X w8a16 Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile ONNX 9.097 ms 2 - 84 MB NPU Yolo-X.onnx.zip
Yolo-X w8a16 Snapdragon 7 Gen 4 QRD Snapdragon® 7 Gen 4 Mobile QNN_DLC 6.707 ms 2 - 50 MB NPU Yolo-X.dlc
Yolo-X w8a16 Snapdragon 7 Gen 4 QRD Snapdragon® 7 Gen 4 Mobile ONNX 388.661 ms 112 - 129 MB CPU Yolo-X.onnx.zip
Yolo-X w8a16 Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile QNN_DLC 1.911 ms 1 - 51 MB NPU Yolo-X.dlc
Yolo-X w8a16 Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile ONNX 11.267 ms 2 - 87 MB NPU Yolo-X.onnx.zip
Yolo-X w8a16 Snapdragon X Elite CRD Snapdragon® X Elite QNN_DLC 5.73 ms 12 - 12 MB NPU Yolo-X.dlc
Yolo-X w8a16 Snapdragon X Elite CRD Snapdragon® X Elite ONNX 14.448 ms 10 - 10 MB NPU Yolo-X.onnx.zip
Yolo-X w8a8 QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) TFLITE 6.248 ms 0 - 33 MB NPU Yolo-X.tflite
Yolo-X w8a8 QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) QNN_DLC 5.392 ms 1 - 37 MB NPU Yolo-X.dlc
Yolo-X w8a8 QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) TFLITE 2.94 ms 0 - 47 MB NPU Yolo-X.tflite
Yolo-X w8a8 QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) QNN_DLC 2.82 ms 1 - 49 MB NPU Yolo-X.dlc
Yolo-X w8a8 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) TFLITE 2.631 ms 0 - 37 MB NPU Yolo-X.tflite
Yolo-X w8a8 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) QNN_DLC 2.302 ms 1 - 12 MB NPU Yolo-X.dlc
Yolo-X w8a8 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) ONNX 8.753 ms 0 - 28 MB NPU Yolo-X.onnx.zip
Yolo-X w8a8 QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) TFLITE 3.117 ms 0 - 33 MB NPU Yolo-X.tflite
Yolo-X w8a8 QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) QNN_DLC 10.931 ms 1 - 38 MB NPU Yolo-X.dlc
Yolo-X w8a8 RB3 Gen 2 (Proxy) Qualcomm® QCS6490 (Proxy) TFLITE 8.442 ms 0 - 42 MB NPU Yolo-X.tflite
Yolo-X w8a8 RB3 Gen 2 (Proxy) Qualcomm® QCS6490 (Proxy) QNN_DLC 10.063 ms 0 - 42 MB NPU Yolo-X.dlc
Yolo-X w8a8 RB3 Gen 2 (Proxy) Qualcomm® QCS6490 (Proxy) ONNX 90.818 ms 47 - 64 MB CPU Yolo-X.onnx.zip
Yolo-X w8a8 RB5 (Proxy) Qualcomm® QCS8250 (Proxy) ONNX 82.887 ms 45 - 56 MB CPU Yolo-X.onnx.zip
Yolo-X w8a8 SA7255P ADP Qualcomm® SA7255P TFLITE 6.248 ms 0 - 33 MB NPU Yolo-X.tflite
Yolo-X w8a8 SA7255P ADP Qualcomm® SA7255P QNN_DLC 5.392 ms 1 - 37 MB NPU Yolo-X.dlc
Yolo-X w8a8 SA8255 (Proxy) Qualcomm® SA8255P (Proxy) TFLITE 2.686 ms 0 - 35 MB NPU Yolo-X.tflite
Yolo-X w8a8 SA8255 (Proxy) Qualcomm® SA8255P (Proxy) QNN_DLC 2.3 ms 3 - 15 MB NPU Yolo-X.dlc
Yolo-X w8a8 SA8295P ADP Qualcomm® SA8295P TFLITE 4.025 ms 0 - 39 MB NPU Yolo-X.tflite
Yolo-X w8a8 SA8295P ADP Qualcomm® SA8295P QNN_DLC 3.581 ms 1 - 43 MB NPU Yolo-X.dlc
Yolo-X w8a8 SA8650 (Proxy) Qualcomm® SA8650P (Proxy) TFLITE 2.694 ms 0 - 37 MB NPU Yolo-X.tflite
Yolo-X w8a8 SA8650 (Proxy) Qualcomm® SA8650P (Proxy) QNN_DLC 2.303 ms 0 - 10 MB NPU Yolo-X.dlc
Yolo-X w8a8 SA8775P ADP Qualcomm® SA8775P TFLITE 3.117 ms 0 - 33 MB NPU Yolo-X.tflite
Yolo-X w8a8 SA8775P ADP Qualcomm® SA8775P QNN_DLC 10.931 ms 1 - 38 MB NPU Yolo-X.dlc
Yolo-X w8a8 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile TFLITE 1.805 ms 0 - 49 MB NPU Yolo-X.tflite
Yolo-X w8a8 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN_DLC 1.534 ms 1 - 53 MB NPU Yolo-X.dlc
Yolo-X w8a8 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile ONNX 6.432 ms 1 - 94 MB NPU Yolo-X.onnx.zip
Yolo-X w8a8 Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile TFLITE 1.449 ms 0 - 45 MB NPU Yolo-X.tflite
Yolo-X w8a8 Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile QNN_DLC 1.12 ms 1 - 45 MB NPU Yolo-X.dlc
Yolo-X w8a8 Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile ONNX 6.063 ms 1 - 74 MB NPU Yolo-X.onnx.zip
Yolo-X w8a8 Snapdragon 7 Gen 4 QRD Snapdragon® 7 Gen 4 Mobile TFLITE 3.461 ms 0 - 42 MB NPU Yolo-X.tflite
Yolo-X w8a8 Snapdragon 7 Gen 4 QRD Snapdragon® 7 Gen 4 Mobile QNN_DLC 2.798 ms 1 - 44 MB NPU Yolo-X.dlc
Yolo-X w8a8 Snapdragon 7 Gen 4 QRD Snapdragon® 7 Gen 4 Mobile ONNX 92.035 ms 48 - 66 MB CPU Yolo-X.onnx.zip
Yolo-X w8a8 Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile TFLITE 1.246 ms 0 - 39 MB NPU Yolo-X.tflite
Yolo-X w8a8 Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile QNN_DLC 0.881 ms 1 - 45 MB NPU Yolo-X.dlc
Yolo-X w8a8 Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile ONNX 8.34 ms 1 - 77 MB NPU Yolo-X.onnx.zip
Yolo-X w8a8 Snapdragon X Elite CRD Snapdragon® X Elite QNN_DLC 2.583 ms 25 - 25 MB NPU Yolo-X.dlc
Yolo-X w8a8 Snapdragon X Elite CRD Snapdragon® X Elite ONNX 9.425 ms 8 - 8 MB NPU Yolo-X.onnx.zip
Yolo-X w8a8_mixed_int16 QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) QNN_DLC 7.695 ms 1 - 39 MB NPU Yolo-X.dlc
Yolo-X w8a8_mixed_int16 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) QNN_DLC 3.509 ms 1 - 11 MB NPU Yolo-X.dlc
Yolo-X w8a8_mixed_int16 QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) QNN_DLC 3.932 ms 1 - 39 MB NPU Yolo-X.dlc
Yolo-X w8a8_mixed_int16 SA7255P ADP Qualcomm® SA7255P QNN_DLC 7.695 ms 1 - 39 MB NPU Yolo-X.dlc
Yolo-X w8a8_mixed_int16 SA8255 (Proxy) Qualcomm® SA8255P (Proxy) QNN_DLC 3.517 ms 1 - 11 MB NPU Yolo-X.dlc
Yolo-X w8a8_mixed_int16 SA8650 (Proxy) Qualcomm® SA8650P (Proxy) QNN_DLC 3.511 ms 2 - 14 MB NPU Yolo-X.dlc
Yolo-X w8a8_mixed_int16 SA8775P ADP Qualcomm® SA8775P QNN_DLC 3.932 ms 1 - 39 MB NPU Yolo-X.dlc
Yolo-X w8a8_mixed_int16 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN_DLC 2.335 ms 1 - 53 MB NPU Yolo-X.dlc
Yolo-X w8a8_mixed_int16 Samsung Galaxy S25 Snapdragon® 8 Elite For Galaxy Mobile QNN_DLC 1.683 ms 1 - 46 MB NPU Yolo-X.dlc
Yolo-X w8a8_mixed_int16 Snapdragon 7 Gen 4 QRD Snapdragon® 7 Gen 4 Mobile QNN_DLC 4.196 ms 1 - 46 MB NPU Yolo-X.dlc
Yolo-X w8a8_mixed_int16 Snapdragon 8 Elite Gen 5 QRD Snapdragon® 8 Elite Gen5 Mobile QNN_DLC 1.336 ms 1 - 48 MB NPU Yolo-X.dlc
Yolo-X w8a8_mixed_int16 Snapdragon X Elite CRD Snapdragon® X Elite QNN_DLC 3.916 ms 12 - 12 MB NPU Yolo-X.dlc

Installation

Install the package via pip:

# NOTE: 3.10 <= PYTHON_VERSION < 3.11 is supported.
pip install wheel==0.45.1 "torch>=2.1,<2.9.0" "setuptools>=77.0.3"
pip install "qai-hub-models[yolox]" git+https://github.com/Megvii-BaseDetection/YOLOX.git@6ddff48 --no-build-isolation --use-pep517

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

Sign-in to Qualcomm® AI Hub Workbench 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.yolox.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.yolox.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.yolox.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.yolox import Model

# Load the model
torch_model = Model.from_pretrained()

# Device
device = hub.Device("Samsung Galaxy S25")

# 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 Workbench. 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.yolox.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.yolox.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 Yolo-X's performance across various devices here. Explore all available models on Qualcomm® AI Hub

License

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

References

Community

Downloads last month
644
Inference Providers NEW
Object Detection
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support