Package pylearn :: Package dataset_ops :: Module cifar10
[hide private]

Module cifar10

source code

CIFAR-10 dataset of labeled small colour images.

For details see either:

Classes [hide private]
GreyScale
Functions [hide private]
 
_unpickle(filename, dtype) source code
 
forget() source code
 
train_data(dtype) source code
 
train_labels() source code
 
valid_data(dtype) source code
 
valid_labels() source code
 
test_data(dtype) source code
 
test_labels() source code
 
cifar10(s_idx, split, dtype='float64', rasterized=False, color='grey')
:param s_idx: the indexes
source code
 
glviewer(split='train') source code
 
datarow_to_greyscale_28by28(row, max_scale=1.0) source code
 
batch_iter(b_idx, max_scale=1.0) source code
 
train_iter(scale=1.0) source code
 
valid_iter(scale=1.0) source code
 
test_iter(scale=1.0) source code
Variables [hide private]
  nclasses = 10

Imports: cPickle, os, sys, numpy, data_root, theano, TensorFnDataset, memo, train_data_labels, test_data_labels


Function Details [hide private]

cifar10(s_idx, split, dtype='float64', rasterized=False, color='grey')

source code 

:param s_idx: the indexes

:param split:

:param dtype:

:param rasterized: return examples as vectors (True) or 28x28 matrices (False)

:param color: control how to deal with the color in the images'

  • grey greyscale (with luminance weighting)
  • rgb add a trailing dimension of length 3 with rgb colour channels