YOLOv13-S-INT8
Object Detection
INT8
post
YOLOv13-S: Object Detection

YOLOv13-S is the small lightweight variant of the 13th-generation YOLO series, designed to balance model size and detection accuracy. While maintaining the hallmark fast inference of the YOLO family, it features an optimized backbone and feature fusion structure, enhanced with lightweight attention modules and dynamic convolution operators—delivering strong detection performance even on low-power devices.

Compared to the ultra-light YOLOv13-N, YOLOv13-S offers deeper feature extraction and wider channels, making it more effective in multi-object detection and moderately complex environments. With its compact size and millisecond-level latency, it is well-suited for deployment on mobile devices, drones, smart cameras, and IoT edge platforms.

Source model

  • Input shape: 1x3x640x640
  • Number of parameters: 8.65M
  • Model size: 34.74M
  • Output shape: 1x84x8400

Source model repository: yolov13

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