Skip to content

Using a pregenerated MATLAB RG and using SIONNA channel models for processing and validation and a replacement for MATLAB #39

Answered by faycalaa
Infiltra asked this question in Q&A
Discussion options

You must be logged in to vote

If my understanding is correct, assuming a single transmitter with a single transmit antenna, what is imported from the datafile is a complex-valued tensor of shape [batch_size, num_ofdm_symbols, fft_size]. If this is the case, and if you want to use the channel models assuming an OFDM waveform, then you would need to cast this tensor into a TensorFlow tensor, and then make it fit the expected input shape of the OFDMChannel (or ApplyOFDMChannel) classes. The data input x is expected to be complex-valued and of shape [batch size, num_tx, num_tx_ant, num_ofdm_symbols, fft_size]. Therefore, you would need to add the num_tx and num_tx_ant dimensions to allow broadcasting, using, e.g., the exp…

Replies: 1 comment

Comment options

You must be logged in to vote
0 replies
Answer selected by jhoydis
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Category
Q&A
Labels
None yet
2 participants