YOLO12-s is the 12th-generation small-scale lightweight model in the YOLO (You Only Look Once) family, specifically optimized for efficient, real-time object detection on resource-constrained devices. While retaining the speed and accuracy strengths of its predecessors, YOLO12-s introduces advanced architectural improvements such as efficient attention mechanisms, enhanced feature fusion, and lightweight convolution modules, boosting inference performance at the edge.

Designed for embedded vision systems, mobile devices, drones, and IoT scenarios, YOLO12-s delivers strong object detection capabilities in a compact model size. It excels in tasks requiring multi-object and small object detection, while remaining suitable for real-time applications.

The model supports various post-processing optimizations and is compatible with major inference frameworks including ONNX, TensorRT, and OpenVINO, making it easy to integrate and deploy across platforms. YOLO12-s is an ideal, cost-effective vision model for industrial, security, retail, and smart manufacturing use cases.

Source model

• Input shape: 1x3x640x640
• Number of parameters: 8.83M
• Model size: 35.61M
• Output shape: 1x84x8400

Source model repository: yolo12s

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.

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