Closed sutr90 closed 10 years ago
Thanks for the feedback! The example needed to be told explicitly which floating-point format to use. I think Theano also lets you avoid this error by setting the allow_input_downcast
keyword arg when calling functions, but I've avoided doing that in favor of making sure the data is in the format I expect.
Thanks for clearing this out. I was afraind, it would affect some other parts of library too.
Hi, I was testing my setup with your examples just to be sure everything works before I start doing any serious work.
When I run the example I get some log output and then following error:
I understand what's going on, I'm just not sure how to fix it.
I see two option here: either I have incorrect setup in my theano installation or there is some flaw in your code.
My setup taken from .theanorc
I think there is a conflict with your code and my settings, as my theano is trying to run on GPU, while yours isn't aware of it.
Thanks for help.