> For the complete documentation index, see [llms.txt](https://facegsm.gitbook.io/facegsm-documentation/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://facegsm.gitbook.io/facegsm-documentation/facegsm/installation/windows-os.md).

# Windows OS

For users with a GPU (Graphics Processing Unit):

{% hint style="info" %}
The user need to use WSL2 for TensorFlow GPU, as TensorFlow 2.10.0 is the last version that runs natively on Windows using GPU. The user can follow the instructions [here](https://www.tensorflow.org/install/pip#windows-wsl2). 
{% endhint %}

*Note: The above step can be skipped if the user doesn't want to use a GPU or doesn't have a GPU on the machine.*

After succesfully installing WSL2, user can choose between **manual installation** or using a **Conda environment** for installing FaceGSM:

#### 1. Manual Install

User need to use [**Python 3.10**](https://www.python.org/downloads/) as the main python version to avoid any error during installation. Following steps can be use to install FaceGSM dependencies on the **local system**:

<pre class="language-bash"><code class="lang-bash"># Clone the FaceGSM repository
$ git clone https://github.com/facegsmproject/FaceGSM

# Install the required dependencies
<strong>$ pip install -r requirements.txt
</strong></code></pre>

#### 2. Conda Environment

Alternatively, user can install FaceGSM dependencies and [**Python 3.10**](https://www.python.org/downloads/) in a [**Conda**](https://docs.conda.io/en/latest/miniconda.html) **environment** using the following commands:

```bash
# Create the environment for FaceGSM using the provided facegsm.yml file
$ conda env create --name facegsm --file facegsm.yml

# Activate the FaceGSM environment
$ conda activate facegsm
```