jamesmf

Sure! The code's pretty old and not very clean, I apologize. The script that trains the model doesn't actually save it (that part is at the bottom and is commented...

I haven't tried to add masking yet, but there have been a number of questions asked about it in the keras issues section. As [this issue](https://github.com/fchollet/keras/issues/411) remains open, I'm not...

`maxToAdd` is the number of MNIST digits to add together in this example. If you're repurposing this code, it would represent the time or sequence dimension. So if you're processing...

That is extremely helpful and matches what I've experienced so far (the ~1MB bound param size).

The problem is intermittent and I have a hard time reproducing it. So far I've noticed it only when the input I'm trying to insert contains floats. It also seems...

Okay confirmed that the TD ODBC drivers are still 15.10. It seems to reliably work when I create a table and immediately insert into it, but when I insert into...

It appears to be an issue relating to the size of the input to .executemany(). When I insert line-by-line it succeeds, as it does when I insert 5000 rows at...

I'm having trouble recreating it with arbitrarily generated data. With data on which it's already failed, I can reliably recreate the issue (including on new tables with the same definition)....

emailed.

I ended up lumping it in with this error https://github.com/Teradata/PyTd/issues/76 and catching either of these Exceptions. My best solution was to wrap my inserts with a try: and in the...