Segment-Anything-Model-2 (SAM 2) is Meta AI’s next-generation foundation model for promptable visual segmentation, operating on both images and videos in real time. It uses a unified Transformer-based architecture with a streaming memory mechanism, enabling accurate object tracking with minimal user interaction.

Key Features:

• Image and Video Support: Handles both modalities with diverse prompts, including clicks and bounding boxes.
• High Speed and Accuracy: Delivers ~6× faster image segmentation and supports ~44 FPS on video.
• Large Video Dataset: Trained on the SA-V dataset, comprising 51K videos and 643K annotated masks, with labeling speed ~8.4× faster.
• Occlusion-aware = Memory Module: Capable of consistent segmentation through object occlusions.
• Open-source Launch: Fully open under Apache 2.0 license, with integration in frameworks like Ultralytics.

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