Deep JSCC implementation

Minimal PyTorch implementation of Deep Joint Source-Channel Coding (DeepJSCC) over an AWGN channel.
Trains separate models at fixed SNR_train ∈ {1,4,7,13,19} and evaluates PSNR across SNR_test sweep.
This implementation is based on the paper Deep Joint Source-Channel Coding for Wireless Image Transmission.

Name		Name	Last commit message	Last commit date
Latest commit History 35 Commits
LICENSE		LICENSE
README.md		README.md
architecture.jpg		architecture.jpg
awgn_psnr.png		awgn_psnr.png
channel.py		channel.py
eval.py		eval.py
metrics.py		metrics.py
models.py		models.py
requirements.txt		requirements.txt
train.py		train.py

Provide feedback