Documentation on signal parameters for signal generation and create user friendly section to change parameters.

TorchDSP / torchsig

TorchSig is an open-source signal processing machine learning toolkit based on the PyTorch data handling pipeline.

MIT License

155 stars 37 forks source link

Documentation on signal parameters for signal generation and create user friendly section to change parameters. #224

Closed ven716 closed 2 days ago

ven716 commented 11 months ago

Looking at when creating the datasets for the classifier and detector models, it seems very difficult for users to discern certain characteristics like center frequency, samples per symbol, and others. Is it possible to change these parameters? If so, can there be a feature that lets the user input their needed parameters.

MattCarrickPL commented 2 days ago

Dataset generation is randomized behind the scenes to cover a broad range of center frequencies, bandwidths, modulations, etc. and is not user controllable by design.