Posterior sampling with conditional flow matching

Create a virtual environment and install required packages:

python -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt

Run this command from the root directory to train a flow, where <example> is either circles or stars:

nohup python -u flowmatching/train.py -cn config_<example>.yaml &> output.out &

During or after training, check metrics:

tensorboard --logdir=logs_<example> &