Usage of time_steps in MNIST and Character
Closed this issue · 0 comments
Hi,
This is not an issue. But I'm having hard time in the usage of time_steps
and element_size
. In case of MNIST image, each input size is 28 X 28. So the author is saying element_size
is 28 columns (considering iteration is going over the rows) and time_steps
is 28 rows?
If that's the case, why in text classification we are not using element_size
dimension in placeholder? Will it not throw an error?
Lastly, in labels
for MNIST, we are not considering the batch_size
. But for test classification, we are doing it. Why that so?
It will be a great help if you help me answer these questions? I'm struggling for a long time to get the answer. In all blogs and other references, the codes are exactly same as the book. But no one is reasoning why this difference is.
Thank you!