I installed theano 0.9.0-dev and lasagne 0.2.0 dev. When I run my code
using CPU, it works. When I my code using GPU, it shows me error as below:
sing cuDNN version 5110 on context None
Preallocating 10295/11439 Mb (0.90) on cuda0
Mapped name None to device cuda0: Tesla K80 (:04:00.0)
Usi
The old server crash and trying to run my code on the new server. I
installed theano 0.9.0-dev and lasagne 0.2.0 dev. When I ran my previous
code, it shows me error as below:
69
70 {
71 // Op class DnnVersion
72
73 #if defined(CUDNN_VERSION)
74 V1 = PyTuple_Pack(2, PyInt_FromLong(CUDNN
I see. I'll try that. Thanks.
On Wednesday, July 12, 2017 at 11:57:57 AM UTC-8, Jesse Livezey wrote:
>
> Do you need to take derivatives through the activation? If not, then you
> could use switch, i.e.
>
> x = some theano variable
> threshold = .5
> x_binary = T.switch(x > theshold, 1., 0.)
>
>
In the binarized network github code (), Matthieu used stochastic
binarization. I'm wondering how to define just a simple binary activation
instead of stochastic in theano?
--
---
You received this message because you are subscribed to the Google Groups
"theano-users" group.
To unsubscribe f
Ok, it works now. Thanks!
On Sunday, July 9, 2017 at 2:32:30 PM UTC-8, Alexander Botev wrote:
>
> If you look at the error the shapes don't match. the conv_out is
> 1x32x16x16 while the bias is 1x1x1x32.
> I guess your bias you did wrong the dimshuffle.
>
> On Saturday, 8 July 2017 01:53:58 UTC+
In other words, how to add bias in Dan's code:
https://github.com/dannyneil/sensor_fusion_iscas_2016/blob/master/theano_layers.py
On Sunday, July 9, 2017 at 2:32:30 PM UTC-8, Alexander Botev wrote:
>
> If you look at the error the shapes don't match. the conv_out is
> 1x32x16x16 while the bias is
So what I did is: def __init__(, b=None)
self.b=b
def get_output(self):
.
.
.
conv_out is the output of dnn.dnn_conv. I tried to add the bias to the
w^T*x. But it reports me an error:
Running network...
Traceback (most recent call last):
File "", line 1, in
runfile('/space/xzhang/git_cnn_conversion/MyLasagneCode_CIFAR10/test_convnet_binary_bias.py',
wdir='/spa
