Problem with understanding part of the decoder logic

[JRMeyer]

>>> damiankwasny95
[May 28, 2019, 1:29am]

Hello. I have a trouble understanding a certain line in the decoder
forward method. This one:
https://github.com/mozilla/TTS/blob/924d6ad4e55e7763e61933bf3542dae1e892c369/layers/tacotron.py#L405-L417

memory_input, attention_rnn_hidden, decoder_rnn_hiddens, slash
current_context_vec, attention, attention_cum = self._init_states(inputs)
while True:
if t > 0:
if memory is None:
new_memory = outputs[-1]
else:
new_memory = memory[t - 1]
# Queuing if memory size defined else use previous prediction only.
if self.memory_size > 0:
memory_input = torch.cat([memory_input[:, self.r curl-run-all.sh discourse.mozilla.org html-to-markdown.sh ordered-posts ordered-posts~ TTS.cdx tts.commands tts-emails.txt TTS.pages tts-telegram.txt TTS.warc.gz self.memory_dim:].clone(), new_memory], dim=-1)
else:
memory_input = new_memory

So my question is, what does this concatenation do? We have a
new_memory with size (B, r*memory_channels) and in step t=1 when
we can enter this part of the condition, the current memory_input we
are trying to concatenate with is of shape
(B, memory_size*memory_channels). So in case memory_size is as a
default set to memory_size = r this line literally concatenates with
an empty tensor. The only situation it actually concatenates with
something is only when memory_size is higher then r, am I right?
shouldn't the condition be changed to if self.memory_size > r or
something like that in this case?
[Maybe I am missing something, but I am] stuck on this line for like more
then half an hours already and I cannot see a different solution. I
would be glad for clarification.

[This is an archived TTS discussion thread from discourse.mozilla.org/t/problem-with-understanding-part-of-the-decoder-logic]

[JRMeyer]

>>> erogol
[May 28, 2019, 8:55am]

if memory_size slash > 0, then TTS uses a constant queue regardless of r.
So if the queue is active, it basically queues the incoming frames.
Otherwise, it uses the previous prediction as memory_input.

[Archived Post]

[JRMeyer]

>>> damiankwasny95
[June 3, 2019, 4:52am]

Thanks for the reply! I am still not sure if I understand this part
correctly, but it seems that the code changed anyway, so I will try to
dig into once again and comeback here in case I still don't grasp it.
Have a nice day!

[Archived Post]