Mercurial > pylearn
comparison amat.py @ 470:bd937e845bbb
new stuff: algorithms/logistic_regression, datasets/MNIST
author | James Bergstra <bergstrj@iro.umontreal.ca> |
---|---|
date | Wed, 22 Oct 2008 15:56:53 -0400 |
parents | 6e69fb91f3c0 |
children |
comparison
equal
deleted
inserted
replaced
469:4335309f4924 | 470:bd937e845bbb |
---|---|
1 """load PLearn AMat files""" | 1 """load PLearn AMat files""" |
2 | 2 |
3 import sys, numpy, array | 3 import sys, numpy, array |
4 | |
5 path_MNIST = '/u/bergstrj/pub/data/mnist.amat' | |
6 | |
7 | 4 |
8 class AMat: | 5 class AMat: |
9 """DataSource to access a plearn amat file as a periodic unrandomized stream. | 6 """DataSource to access a plearn amat file as a periodic unrandomized stream. |
10 | 7 |
11 Attributes: | 8 Attributes: |
12 | 9 |
13 input -- minibatch of input | 10 input -- all columns of input |
14 target -- minibatch of target | 11 target -- all columns of target |
15 weight -- minibatch of weight | 12 weight -- all columns of weight |
16 extra -- minitbatch of extra | 13 extra -- all columns of extra |
17 | 14 |
18 all -- the entire data contents of the amat file | 15 all -- the entire data contents of the amat file |
19 n_examples -- the number of training examples in the file | 16 n_examples -- the number of training examples in the file |
20 | 17 |
21 AMat stands for Ascii Matri[x,ces] | 18 AMat stands for Ascii Matri[x,ces] |