YOLO11m-obb-INT8
Object Detection
INT8
post
YOLO11m-obb: Object Detection

YOLO11m-obb is a mid-sized oriented bounding box (OBB) detection model in the Ultralytics YOLO11 series, designed for high-precision and efficient detection of direction-sensitive objects in complex scenes.

Key Features:

  • High Accuracy: Achieves a mAP@50 of 80.9% on the DOTAv1 dataset, outperforming YOLO11n-obb and YOLO11s-obb.
  • Inference Speed: On CPU with ONNX format, inference speed is 562.8 ms; on T4 TensorRT10, it is 10.1 ms.
  • Model Scale: Contains approximately 20.9M parameters and 183.5B FLOPs, suitable for mid-to-high-performance computing platforms.
  • Use Cases: Ideal for applications in aerial image analysis, urban planning, agricultural monitoring, and energy infrastructure inspection, where precise detection of rotated objects is crucial.

Source model

  • Input shape: 1x3x1024x1024
  • Number of parameters: 19.98M
  • Model size: 80.05M
  • Output shape: 1x20x21504

Source model repository: yolo11m-obb

Performance Reference
Device
Backend
Precision
Inference Time
Accuracy Loss
File Size
Model Optimization

When the user has fine-tuned the source model, the model conversion process must be performed again.

Users can refer to either of the following two methods to complete the model conversion:

  • Using AIMO for model conversion: Click Model Conversion Reference in the Performance Reference section on the right to view the conversion steps.

  • Using Qualcomm QNN for model conversion: Please refer to the Qualcomm QNN Documentation.

Model Inference

The model performance benchmarks and example code provided by Model Farm are all implemented based on the APLUX AidLite SDK.

For models in .bin format, you can use either of the following two inference engines to run inference on Qualcomm chips:

Inference using APLUX AidLite: please refer to the APLUX AidLite Developer Documentation

Inference using Qualcomm QNN: Please refer to the Qualcomm QNN Documentation

Inference Example Code

The inference example code is implemented using the AidLite SDK.

Click Model & Code to download the model files and the inference code package. The file structure is as follows:

/model_farm_{model_name}_aidlite
    
    |__ models # folder where model files are stored

    |__ python # aidlite python model inference example

    |__ cpp # aidlite cpp model inference example

    |__ README.md
License
Source Model:AGPL-3.0
Deployable Model:AGPL-3.0
Performance Reference
Device
Backend
Precision
Inference Time
Accuracy Loss
File Size