diff datasets/MNIST.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
children 45b3eb429c15
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/datasets/MNIST.py	Wed Oct 22 15:56:53 2008 -0400
@@ -0,0 +1,31 @@
+"""
+Various routines to load/access MNIST data.
+"""
+from __future__ import absolute_import
+
+import numpy
+
+from ..amat import AMat
+
+default_path = '/u/bergstrj/pub/data/mnist.amat'
+"""the location of a file containing mnist data in .amat format"""
+
+
+def head(n=10, path=None):
+    """Load the first MNIST examples.
+
+    Returns two matrices: x, y.  x has N rows of 784 columns.  Each row of x represents the
+    28x28 grey-scale pixels in raster order.  y is a vector of N integers.  Each element y[i]
+    is the label of the i'th row of x.
+    
+    """
+    path = path if path is not None else default_path
+
+    dat = AMat(path=path, head=n)
+
+    return dat.input, numpy.asarray(dat.target, dtype='int64').reshape(dat.target.shape[0])
+
+def all(path=None):
+    return head(n=None, path=path)
+
+