Normal (Gaussian Curve) formula breaks with Tensorflow 1.01
Closed this issue · 3 comments
YanYas commented
Hi, I was trying out the tutorials on windows and I found that the gaussian formula wasn't working. Something to do with the dtypes not converting correctly. None the less, there is a solution in the form of the Normal Distribution contribution in the update. I dunno if you want to re-record that bit though. I'll see if I can figure out how it works later and mention it in the Kadenze forum.
pkmital commented
Hi and thanks! Good to note the https://www.tensorflow.org/api_docs/python/tf/contrib/distributions/Normal distribution. Is there any specific error on windows? I will try to take a look at it then! Thanks
YanYas commented
I'm not in front of my machine at the moment but I don't think the issue
strictly a Windows one. I saw a similar error elsewhere on Stack Overflow
and it referred to a change in the api.
I think it might be worth also having a look at tf.nn.moments and
tf.nn.batchnormalization, although I found it important to see the practice
broken down into explicit parts so I could understand what the functions
were doing. They could be employed in later tutorials where students
already understand what they do to speed up the process of setting up a
graph.
Anyways, I'll take a look at the error and post it to you.
…On Saturday, 8 April 2017, Parag K Mital ***@***.***> wrote:
Hi and thanks! Good to note the https://www.tensorflow.org/
api_docs/python/tf/contrib/distributions/Normal distribution. Is there
any specific error on windows? I will try to take a look at it then! Thanks
—
You are receiving this because you authored the thread.
Reply to this email directly, view it on GitHub
<#66 (comment)>, or mute
the thread
<https://github.com/notifications/unsubscribe-auth/AJDp3AujDe5zlPX7uqrftbdPh_xEHD_tks5rt-fpgaJpZM4M0Wo6>
.
pkmital commented
Closing to inactivity. Please feel free to repoen!