pdnn

pdnn copied to clipboard

Is this an error?

1

ubgpu@ubgpu:~/github/pdnn/examples/mnist_rbm$ sudo ./run.sh --2015-05-16 15:48:05-- http://www.iro.umontreal.ca/~lisa/deep/data/mnist/mnist.pkl.gz Resolving www.iro.umontreal.ca (www.iro.umontreal.ca)... 132.204.24.179 Connecting to www.iro.umontreal.ca (www.iro.umontreal.ca)|132.204.24.179|:80... connected. HTTP request sent, awaiting response... 200 OK Length: 16168813 (15M) [application/x-gzip] Saving to: 鈥榤nist.pkl.gz.6鈥 100%[===============================================================================================================================================================>]...

andyyuan78

`nan` parameters

1

Hi! Training with PDNN sometimes ends with the `nan` parameters. Command is as follows: python run_DNN.py --train-data "train.pfile,partition=2000m,stream=true,random=true" --valid-data "valid.pfile,partition=200m,stream=true,random=true" --nnet-spec "1320:2048:2048:2048:2048:2048:1947" --lrate "D:0.8:0.5:0.1,0.1:6" --dropout-factor 0.2,0.2,0.2,0.2,0.2 --wdir model --kaldi-output-file model/model.dnn...

VeliBaba

Hi! I have obtained a kaldi formatted model. How can I use this model for decoding?

VeliBaba

Is there any way to enhance pdnn performance on GPU machine? the run time for the same algorithm on cpu is almost identical to the gpu one? any ideas?

1

I use a big partition value and i enable Stream, but nothing seems to make it work better.

nouramoubayed

Training data

2

Hi May I know how to get the training data for your PDNN?

zhanglongqi

kaldi data format

1

Hi, I am trying to build a DBN for language Id using PDNN. As is a huge amount of data, I decided to use kaldi data format to structure my...

anarucu

delta_W_rec dimensions

3

in rnn, shouldn't: self.delta_W_rec = theano.shared(value = numpy.zeros((n_in,n_out), dtype=theano.config.floatX), name='delta_W_rec') be: self.delta_W_rec = theano.shared(value = numpy.zeros((n_out,n_out), dtype=theano.config.floatX), name='delta_W_rec') ?

eyaler

does pdnn supports soft class association?

1

Hello, I want to know whether pdnn supports soft class labels? For example in the following 4 class classification problem: ``` Feature Vector Class Label ``` [0.2, 0.3, 0.5, 1.4,...

khademian

1- Now it accepts to initialize any layer of a network with the weights of any layer of another network (as long as they have the same description of course,...

tofigh-

If I want to apply PDNN to the task of regression, should I modify the source code?

Colin-Gu