--- a/pylearn/shared/layers/__init__.py	Tue Nov 17 15:20:40 2009 -0500
+++ b/pylearn/shared/layers/__init__.py	Tue Jan 05 10:48:59 2010 -0500
@@ -1,14 +1,14 @@
 # logreg.py
-from .logreg import LogisticRegression
+from pylearn.shared.layers.logreg import LogisticRegression
 
 # sigmoidal_layer.py
-from .sigmoidal_layer import SigmoidalLayer
+from pylearn.shared.layers.sigmoidal_layer import SigmoidalLayer
 
 # exponential_mean.py
-from .exponential_mean import ExponentialMean
+from pylearn.shared.layers.exponential_mean import ExponentialMean
 
 # sgd.py
-from .sgd import StochasticGradientDescent, HalflifeStopper
+from pylearn.shared.layers.sgd import StochasticGradientDescent, HalflifeStopper
 
 # kording
 from kording2004 import Kording2004

--- a/pylearn/shared/layers/kording2004.py	Tue Nov 17 15:20:40 2009 -0500
+++ b/pylearn/shared/layers/kording2004.py	Tue Jan 05 10:48:59 2010 -0500
@@ -2,7 +2,7 @@
 import theano.tensor
 from hpu.theano_outgoing import mean, var, cov
 
-from .exponential_mean import ExponentialMean # exponential_mean.py
+from pylearn.shared.layers.exponential_mean import ExponentialMean # exponential_mean.py
 
 import logging
 _logger = logging.getLogger('kording2004')

--- a/pylearn/shared/layers/kouh2008.py	Tue Nov 17 15:20:40 2009 -0500
+++ b/pylearn/shared/layers/kouh2008.py	Tue Jan 05 10:48:59 2010 -0500
@@ -21,7 +21,7 @@
 from theano.tensor.nnet import softplus
 from theano.sandbox.softsign import softsign
 from theano.compile.sandbox import shared
-from .util import add_logging, update_locals
+from pylearn.shared.layers.util import add_logging, update_locals
 
 try:
     from PIL import Image
@@ -243,9 +243,12 @@
         if rows is None and cols is None:
             rows = int(numpy.sqrt(n_out))
         if cols is None:
-            cols = n_out // rows + (1 if n_out % rows else 0)
+            cols = n_out // rows
+            if n_out % rows: cols +=1
         if rows is None:
-            rows = n_out // cols + (1 if n_out % cols else 0)
+            rows = n_out // cols
+            if n_out % cols:
+                rows+=1
 
         filter_shape = self.filter_shape
         height = rows * (row_gap + filter_shape[0]) - row_gap

--- a/pylearn/shared/layers/lecun1998.py	Tue Nov 17 15:20:40 2009 -0500
+++ b/pylearn/shared/layers/lecun1998.py	Tue Jan 05 10:48:59 2010 -0500
@@ -11,8 +11,8 @@
 from theano.sandbox.conv import ConvOp
 from theano.sandbox.downsample import DownsampleFactorMax
 
-from .util import update_locals
-from .squash import squash
+from pylearn.shared.layers.util import update_locals
+from pylearn.shared.layers.squash import squash
 
 class LeNetConvPool(object):
     """

--- a/pylearn/shared/layers/logreg.py	Tue Nov 17 15:20:40 2009 -0500
+++ b/pylearn/shared/layers/logreg.py	Tue Jan 05 10:48:59 2010 -0500
@@ -4,7 +4,7 @@
 import theano
 from theano.compile.sandbox import shared
 from theano.tensor import nnet
-from .util import update_locals, add_logging
+from pylearn.shared.layers.util import update_locals, add_logging
 
 class LogisticRegression(object):
     def __init__(self, input, w, b, params=[]):

--- a/pylearn/shared/layers/rust2005.py	Tue Nov 17 15:20:40 2009 -0500
+++ b/pylearn/shared/layers/rust2005.py	Tue Jan 05 10:48:59 2010 -0500
@@ -30,7 +30,7 @@
 from theano.tensor.nnet import softplus
 from theano.sandbox.conv import ConvOp
 
-from .util import update_locals, add_logging
+from pylearn.shared.layers.util import update_locals, add_logging
 
 def rust2005_act_from_filters(linpart, E_quad, S_quad, eps):
     """Return rust2005 activation from linear filter responses, as well as E and S terms

--- a/pylearn/shared/layers/sigmoidal_layer.py	Tue Nov 17 15:20:40 2009 -0500
+++ b/pylearn/shared/layers/sigmoidal_layer.py	Tue Jan 05 10:48:59 2010 -0500
@@ -7,8 +7,8 @@
 import theano
 from theano import tensor
 from theano.compile.sandbox import shared, pfunc
-from .util import update_locals, add_logging
-from .squash import squash
+from pylearn.shared.layers.util import update_locals, add_logging
+from pylearn.shared.layers.squash import squash
 
 
 class SigmoidalLayer(object):