PyTorch implementation of A Unified Multi-Task Semantic Communication System for Multimodal Data

This repository is built upon BEiT and MAE, thanks very much!

We would gradually upload the full-version of the implementation.

TODO

• implement the designed benchmark: task-oriented semantic communication works (T-DeepSC) for the considered tasks, including image(cls/recons), text(cls/recons) under analog transmission.
• implement the designed benchmark: TDeepSC for VQA and MSA under analog transmission.
• implement the digital transmission: vector quantization (VQ) and uniform scalar quantization (SQ).
• implement the 16QAM and QPSK modulations.
• dataset preparation
• the basic version of the unified semantic communication (U-DeepSC).
• the code for dynamic overhead.
• visualization of the results.

Run

1. The instructions are given in execute.sh, use "bash execute.sh" to execute the script.
2. All instructions are given in running_command.sh.