search

YicXu / DiRSA

Diffusion-based Radio Signal Augmentation (DiRSA) algorithm
3 stars 0 forks source link

No code found for the prompt word section #1

Open Miraitwo opened 2 months ago

Miraitwo commented 2 months ago

Hello author, while reading your code section, I couldn't find the prompt words for modulation categories written in the paper. I would like to ask you how this part is implemented. Looking forward to your reply. Thank you very much.

YicXu commented 2 months ago

Actually, each modulation is assigned a unique identifier that ranges from 0 to 10. These identifiers are then transformed into a one-hot encoding format, where each identifier is represented by an 11-element binary vector. In this vector, only the position corresponding to the identifier is marked as “1”, with all other positions set to “0”. This one-hot encoded vector is subsequently used as a prompt word in the input to our model. In DiRSA_utils.py evaluate function, you can modify that vector to guide the augmentation result. I add an example for it. In our algorithm prompt words are not truly "words", hope you can understand. :)

Miraitwo commented 2 months ago

Thank you very much for your reply to my question and answering my doubts