Closed gccollect closed 4 years ago
Hi, this may be due to the "window" chunk mode, which was written to split the input time length in week-long intervals. I have not tested its behavior when the time length is not a multiple of 168 (on week in hours).
You could try switching to chunk_mode = "classic"
, see if the problem persists. If it doesn't, you may have to rewrite the Window MHA to be more flexible.
Hi, this may be due to the "window" chunk mode, which was written to split the input time length in week-long intervals. I have not tested its behavior when the time length is not a multiple of 168 (on week in hours).
You could try switching to
chunk_mode = "classic"
, see if the problem persists. If it doesn't, you may have to rewrite the Window MHA to be more flexible.
There is no chunk_mode="classic"
. It's only: One of 'chunk', 'window' or None.
Sorry, I meant chunk_mode=None
, I got mixed up in my explanation.
Hi, thanks for making this implementation available. I am following the tutorial but I am encountering a size mismatch error when I call
net(inputs)
on my timeseries data. My input is 1 x K x d_input but the output of the self-attention layer appears to be truncated to K-5 and thus cannot be added to the residual.I am using the same parameters as the training.ipynb