Previously, when the len(trX) is completely divisible by batch_size, the training skipped over the last batch because end=len(trX) would never occur. Corrected this and now the loop will go over the entire training set if batch_size can cleanly fit in.
Previously, when the
len(trX)
is completely divisible bybatch_size
, the training skipped over the last batch becauseend=len(trX)
would never occur. Corrected this and now the loop will go over the entire training set ifbatch_size
can cleanly fit in.