BinaryNet
BinaryNet copied to clipboard
error when running Run-time/mnist.py
This is what I got, (the training part works fine):
Using gpu device 0: GeForce GTX 960 (CNMeM is enabled with initial size: 90.0% of memory, cuDNN 5105)
Traceback (most recent call last):
File "binary_ops.py", line 225, in
Thanks
Exactly the same to me..
Downgrading Theano to version 0.8.2 solved the problem to me
Thanks, I solved it by not using "baseline" in the first layer, but using "theano".. (which I do not believe is really a solution)
I'm having the same error. How did you downgrade? Did you have to uninstall and reinstall theano manually?
I have just compiled Theano from source code choosing that version
2016-12-24 3:33 GMT+01:00 Luis Bill [email protected]:
How did you downgrade? Did you have to uninstall and reinstall theano manually?
— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub https://github.com/MatthieuCourbariaux/BinaryNet/issues/13#issuecomment-269065027, or mute the thread https://github.com/notifications/unsubscribe-auth/AAxsafxngaq5vVRR0yAiuHYBoqpedKIVks5rLIR-gaJpZM4Kmr6G .
Install Theano with version 0.8.0, this problem can be solved. sudo pip install -r https://raw.githubusercontent.com/Lasagne/Lasagne/master/requirements.txt
I use Theano with version 0.9.0 and I have sloved the problem by add an argument " impl='c' " in function make_thunk of class Gemm and class XnorGemm.