antelopev2

Introduction

The repository contains the AntelopeV2 models for facial detection and recognition, developed by InsightFace. These models are designed for use with Immich, a self-hosted photo library platform. It is important to note that models for other tasks, like facial alignment, are not included.

Architecture

The AntelopeV2 models leverage ONNX for efficient execution across platforms, supporting tasks related to facial recognition. These models are part of the InsightFace suite, which is focused on providing robust facial recognition capabilities.

Training

Specific details on the training process for the AntelopeV2 models are not included in the provided documentation. For comprehensive insights, users are encouraged to explore the InsightFace repository, which may provide additional information on model training and optimization techniques.

Guide: Running Locally

To run the AntelopeV2 models locally:

1. Clone the Repository: Download the repository from the provided link.
2. Install Dependencies: Ensure ONNX and any related dependencies are installed.
3. Prepare Environment: Set up a Python environment suitable for running facial recognition models.
4. Execute Model: Load the models using ONNX-compatible tools and execute them on your local data.

For enhanced performance, consider utilizing cloud GPUs from providers such as AWS or Google Cloud Platform to handle computationally intensive tasks.

License

The AntelopeV2 models are distributed under the InsightFace license. More details can be found at the InsightFace license page.