Source code for paper "Deep Diffusion Models for Robust Channel Estimation".
Generic flow:
- Use 'matlab/main.m' to generate training, validation and test channels.
- Use 'train.py' to train a deep diffusion model for channel estimation with the default parameters used in the paper.
- Use 'hyperparam_tuning.py' to find 'beta' and 'N', exactly like in the paper.
- Use 'inference.py' to perform inference.
Full credits for the ncsnv2 repository go to: https://github.com/utcsilab/diffusion-channels/tree/main/ncsnv2