[theano-users] Re: Save and load MLP model

Hi Desy, I faced this issue before. One way to do this is to save and pickle all the weights. A good reference would be to download and study the codes from the following: https://sites.google.com/a/chalearn.org/automl/general-mnist---cnn-example On Tuesday, January 10, 2017 at 1:22:22 PM

[theano-users] gibbs sampling using theano scan for Replicated Softmax Model (RSM)

Hi, I've been trying to modify deeplearning.net's tutorial on RBM to create a RSM layer but i am struggling with theano's scan function to simulate multinomial random variables. I find theano's scan function difficult to master. Was hoping that someone can help identify where I went wrong

Re: [theano-users] generator Op

I'm currently trying to make user friendly interface for pymc3. I want to implement automatic likelihood scaling, that is now done by user. I believe that this Op will help a lot with implementing large scale inference algorithms. -- Best regards, Max > 9 янв. 2017 г., в 18:16, Frédéric

Re: [theano-users] New to theano, trying to update loss function to penalizes negative weights.

There is no question in that email. So it is hard to tell anything. Fred On Thu, Jan 5, 2017 at 2:35 PM, Gregory N wrote: > I have previously used categorical_cross_entropy >

Re: [theano-users] What is this warning saying about DEBUG: nvcc STDOUT mod.cu?

This is a warning from nvcc that it output by default. I don't understand why updating Theano help with that. This happen when we compile gpu code in the old back-end. As we are transitioning to the new back-end, I don't think we will do a work around that in the old back-end. The reason why you

Re: [theano-users] generator Op

Hi, Currenlty we don't have such an op. I'm not sure how to implement the case of the end of the computation. We could have it return an empty tensor, but this don't seem super clean. So such an op should be used with an ifelse op that would skip all the computation... Nothing super fast to

Re: [theano-users] What is this warning saying about DEBUG: nvcc STDOUT mod.cu?

Sorry for these reply. pip install --upgrade --no-deps git+git://github.com/Theano/Theano.git Bleeding-edge solve the problem! 在 2017年1月9日星期一 UTC+8下午8:57:22，Roach Sinai写道： > > Hi, Pascal. Why I run the same python script, also *Creating library. *Every > time I run the same script! > > DEBUG:

[theano-users] Re: CUDNN Liberies right but not working.

I will check this guides out on another PC. Am Sonntag, 8. Januar 2017 21:49:28 UTC+1 schrieb Alexander Pacha: > > Check out https://github.com/philferriere/dlwin, especially > https://github.com/philferriere/dlwin#cudnn-v51-august-10-2016-for-cuda-80-conditional > -- --- You received this

[theano-users] Re: CUDNN Liberies right but not working.

Im using CUDA v 8.0. I checked the properties of the folder and the programm should be able to see whats in there. Am Freitag, 6. Januar 2017 19:21:14 UTC+1 schrieb Ramana Subramanyam: > > Hi, > Which version of cuda are you using ? It happened to me(on my server) > after installing Cuda 7.5

[theano-users] Re: CUDNN Liberies right but not working.

Im using CUDA v 8.0. I checked the properties of the folder and the programm should be able to see whats in there. Am Freitag, 6. Januar 2017 19:21:14 UTC+1 schrieb Ramana Subramanyam: > > Hi, > Which version of cuda are you using ? It happened to me(on my server) > after installing Cuda

Re: [theano-users] What is this warning saying about DEBUG: nvcc STDOUT mod.cu?

Hi, Pascal. Why I run the same python script, also *Creating library. *Every time I run the same script! DEBUG: nvcc STDOUT nvcc warning : The 'compute_20', 'sm_20', and 'sm_21' architectures are deprecated, and may be removed in a future release (Use -Wno-deprecated-gpu-targets to suppress