Stack Overflow
Stack Overflow

Questions tagged [pylearn]

Pylearn is a machine learning library for python. Much of the functionality is built on top of Theano, meaning that you can utilise its performance, such as GPU parallelisation.

http://deeplearning.net/software/pylearn2/

27 questions
5
votes
1 answer

Pre-training ANN with RBM in pylearn2

I'm trying to train a multi-layered ANN with pylearn2, using pre-training with RBM. I've slightly modified the script called run_deep_trainer that is contained in pylearn2\pylearn2\scripts\tutorials\deep_trainer. I want a 4-layered net, where the…
giogix
  • 769
  • 1
  • 12
  • 32
4
votes
3 answers

installing pylearn2 - ImportError: No module named six.moves

I'm trying to install pylearn2. I'm using a fresh virtual environment where I've only install the development versions of theano and pygpu. I have tested them and both are working fine. However, when I try to install pylearn2 I get this error: $…
soroosh.strife
  • 1,181
  • 4
  • 19
  • 45
4
votes
2 answers

Can the validation error of a dataset be higher than the test error during the whole process of training a neural network?

I'm training a convolutional neural network using pylearn2 library and during all the ephocs, my validation error is consistently higher than the testing error. Is it possible? If so, in what kind of situations?
SameeraR
  • 415
  • 1
  • 6
  • 19
3
votes
1 answer

How can I train my pylearn2 neural network on multiple target variables?

I have a functioning pylearn2 neural network which loads data from a csv and predicts a continuous target variable. How can I change it to predict multiple distinct target variables? I am using Kaggle's African soil dataset. And have constructed…
powellwe
  • 31
  • 3
3
votes
1 answer

pylearn2 CSVDataset TypeError

I'm having an issue loading a custom dataset into pylearn2. I'm trying to get a simple MLP to train using a tiny XOR dataset. I have a dataset named xor.csv in the same directory as my yaml file, which is not in the same directory as pylearn2's…
Mike C
  • 1,959
  • 2
  • 17
  • 17
2
votes
2 answers

implementing LSTM with theano scan, way slower then using loops

I am using Theano/Pylearn2 to implement LSTM model inside my own network. However, I've found that Theano scan is much, much slower than using plain loops. I used the Theano profiler <% time>
Jing
  • 895
  • 6
  • 14
  • 38
2
votes
2 answers

create a single layer neural network with pylearn2

Pylearn2 is usually suggest as python resource for neural networks. I would like to create a Single hidden layer neural network and train it with the backpropagation algorithm. This should be something of basic but I do not understand how to do it…
Donbeo
  • 17,067
  • 37
  • 114
  • 188
2
votes
2 answers

import theano results in ImportError

I'm trying to use theano but I get an error when I import it. I've installed cuda_6.5.14_linux_64.run, and passed all the recommended test in Chapter 6 of this NVIDIA PDF. Ultimately I want to be able to install pylearn2, but I get the exact same…
ADJ
  • 4,892
  • 10
  • 50
  • 83
1
vote
0 answers

How to fine tune hyper-parameters of momentum optimizer?

There are several optimizers in training of neural network. But the Momentum and SGD seem always better than adaptive methods. Now I am writing a program in tensorflow to reproduce the results of others. They use momentum to train in pylearn2. But…
Kai He
  • 48
  • 8
1
vote
1 answer

pkl file for customized image data in pylearn2

I'm totally novice in pylearn2 & right now I'm working in Brats database in which we work on 3D MRI of brain for tumor segmentation by using Pylearn2 same as explained in pylearn2 tutorial for CIFAR10 Database . My problem is that all the volumetric…
Lot_to_learn
  • 590
  • 2
  • 9
  • 21
1
vote
0 answers

Pylearn2: MLP model with my own data

I'm trying to build an MLP model using pylearn2. But the manual isn't that explicit on how to import extern data (all tutorials use the MNSIT datas). So, my data are CSV files: 0 0.129 -0.234 0.394 ... 0 0.293 -0.394 0.234 ... 1 0.192 -0.842 0.123…
romz34
  • 45
  • 1
  • 7
1
vote
1 answer

predictions using pylearn2 models

I have trained the following CNN model using pylearn2. h1 Input space: Conv2DSpace(shape=(25, 150), num_channels=1, axes=('b', 0, 1, 'c'), dtype=float64) Total input dimension: 3750 h2 Input space: Conv2DSpace(shape=(11, 73),…
user3124696
  • 11
  • 2
1
vote
0 answers

Adding L2 regularization to SGD trainer in MLP from pylearn2/Theano

I am new to Pylearn -so this question might be pretty basic. I want to add L2 regularization to the SGD trainer for MLP, but I am not sure how to do so. Here's my code (that fails): from pylearn2.datasets import DenseDesignMatrix from…
abhgh
  • 308
  • 1
  • 9
1
vote
0 answers

Visualize weights of deep neural network in scikit-neuralnetwork

I played with the scikit-neuralnetwork, which is backed by the pylearn2 library. The pylearn2 has functions to visualize learned weights of the convolutional kernels. Can I somehow access the learned model inside the scikit wrapper and visualize the…
Vojtech Letal
  • 2,168
  • 3
  • 13
  • 17
1
vote
0 answers

Ubuntu 14.04 - Pylearn2 installation : nvcc compiler not found on $PATH

I'm trying to install pylearn2 on my Ubuntu 14.04.However,installation fails when I type "python setup.py develop" command and gets nvcc&x86_64-linux-gnu-gcc fatal error. joeson@joeson-Lenovo-G40-70m:~/KuaiPan/MachineLearning/Deep…
John_joeson
  • 11
  • 1
1
2