Start with creating a virtual environment:
py -3.13 -m venv .venv
.\.venv\Scripts\activate
py -m pip install --upgrade pip
py -m pip install -r requirements-base.txt


Install the base dependencies:
py -3.13 -m pip install -r requirements-base.txt

Then install the Torch build that matches your machine.

For CPU-only use:
py -3.13 -m pip install torch==2.10.0 torchvision==0.25.0

For NVIDIA CUDA 12.8:
py -3.13 -m pip install torch==2.10.0+cu128 torchvision==0.25.0+cu128 --index-url https://download.pytorch.org/whl/cu128

For DirectML / AMD support, install torch-directml as an optional extra:
py -3.13 -m pip install torch-directml