[theano-users] Re: Weights are not updated on each iteration

I had normalized the input so that all the values were between 0 and 1. There is no luck with using either ReLU activation unit or tanh nor by multiplying the initial weights with factor of 0.01. There seems to be some other problem with my implementation which I'm unable to figure out. On

[theano-users] Re: Unable to write gradient step for rnn in theano

The error is telling you the issue, your original shared variables are float32 but the updates you produce are float64. I'm guessing you don't have floatX set as float32 in your theano config, so when you multiply the gradient by the learning rate it gets upcast to float64, you can either set

[theano-users] When I run "import theano" I get "Not able to select available GPU from 2 cards (out of memory)."

On this machine I have another process using theano with memory on the GPU. Normally I can launch many processes and import theano but now I get this error. $ python Python 2.7.12 |Anaconda 2.3.0 (64-bit)| (default, Jul 2

Re: Private message regarding: [theano-users] how to use theano scan with RandomStreams

I did not test this, because I don't have data or code for one_step, but it would be something like: def loop_over_examples(x): # hidden and outputs of the entire sequence [h_vals, o_vals], inner_updates = theano.scan(fn=one_step, sequences = dict(input = x, taps=[0]),

Re: [theano-users] Testing 'borrow=True' with cnmm=0 and cnmm=0.3 to assess performance times

Hi, My guess is that: - without cnmem, allocation and deallocation of intermediate results force synchronization of the GPU more often, so the overall time is slower - with cnmem and borrow=False, there is no synchronization at all, and what is measured is just the time to launch the GPU

Re: [theano-users] Weights are not updated on each iteration

The sigmoid activation function tends to saturate and block gradient propagation, so the gradient wrt W1 is probably really close to zero in your case. Potential solutions include using another activation function (ReLU for instance, or tanh), initializing W1 with smaller weights, making sure

Re: [theano-users] Can't get bilinear_upsampling work

Hi Fred, thanks for the info, will try that. On Tuesday, 11 October 2016 20:51:49 UTC+8, nouiz wrote: > > Update to Theano dev version. There was update to it since the last > release that could help you. > > Fred > > Le 11 oct. 2016 01:31, "狄凯" a écrit : > >> Hi guys, I'm