diff --git a/examples/mnist_cnn.py b/examples/mnist_cnn.py
index 92ea0bc6f..d7a4d9b30 100644
--- a/examples/mnist_cnn.py
+++ b/examples/mnist_cnn.py
@@ -51,7 +51,7 @@ Y_test = np_utils.to_categorical(y_test, nb_classes)
 model = Sequential()
 
 model.add(Convolution2D(nb_filters, nb_conv, nb_conv,
-                        border_mode='same',
+                        border_mode='valid',
                         input_shape=(1, img_rows, img_cols)))
 model.add(Activation('relu'))
 model.add(Convolution2D(nb_filters, nb_conv, nb_conv))
diff --git a/keras/backend/tensorflow_backend.py b/keras/backend/tensorflow_backend.py
index 12271e669..74ff8a3d5 100644
--- a/keras/backend/tensorflow_backend.py
+++ b/keras/backend/tensorflow_backend.py
@@ -502,7 +502,8 @@ def dropout(x, level, seed=None):
 # CONVOLUTIONS
 
 
-def conv2d(x, kernel, strides=(1, 1), border_mode='valid', dim_ordering='th'):
+def conv2d(x, kernel, strides=(1, 1), border_mode='valid', dim_ordering='th',
+           image_shape=None, filter_shape=None):
     '''
     Run on cuDNN if available.
     border_mode: string, "same" or "valid".
diff --git a/keras/backend/theano_backend.py b/keras/backend/theano_backend.py
index 3d34262bb..e8418e7ce 100644
--- a/keras/backend/theano_backend.py
+++ b/keras/backend/theano_backend.py
@@ -515,7 +515,8 @@ def dropout(x, level, seed=None):
 # CONVOLUTIONS
 
 
-def conv2d(x, kernel, strides=(1, 1), border_mode='valid', dim_ordering='th'):
+def conv2d(x, kernel, strides=(1, 1), border_mode='valid', dim_ordering='th',
+           image_shape=None, filter_shape=None):
     '''
     Run on cuDNN if available.
     border_mode: string, "same" or "valid".
@@ -532,6 +533,12 @@ def conv2d(x, kernel, strides=(1, 1), border_mode='valid', dim_ordering='th'):
         # TF kernel shape: (rows, cols, input_depth, depth)
         x = x.dimshuffle((0, 3, 1, 2))
         kernel = kernel.dimshuffle((3, 2, 0, 1))
+        if image_shape:
+            image_shape = (image_shape[0], image_shape[3],
+                           image_shape[1], image_shape[2])
+        if filter_shape:
+            filter_shape = (filter_shape[3], filter_shape[2],
+                            filter_shape[0], filter_shape[1])
 
     if _on_gpu() and dnn.dnn_available():
         if border_mode == 'same':
@@ -558,7 +565,9 @@ def conv2d(x, kernel, strides=(1, 1), border_mode='valid', dim_ordering='th'):
 
         conv_out = T.nnet.conv.conv2d(x, kernel,
                                       border_mode=th_border_mode,
-                                      subsample=strides)
+                                      subsample=strides,
+                                      image_shape=image_shape,
+                                      filter_shape=filter_shape)
         if border_mode == 'same':
             shift_x = (kernel.shape[2] - 1) // 2
             shift_y = (kernel.shape[3] - 1) // 2
diff --git a/keras/layers/convolutional.py b/keras/layers/convolutional.py
index e1d49093c..53a28a5bc 100644
--- a/keras/layers/convolutional.py
+++ b/keras/layers/convolutional.py
@@ -93,7 +93,8 @@ class Convolution1D(Layer):
         X = K.expand_dims(X, -1)  # add a dimension of the right
         X = K.permute_dimensions(X, (0, 2, 1, 3))
         conv_out = K.conv2d(X, self.W, strides=self.subsample,
-                            border_mode=self.border_mode, dim_ordering='th')
+                            border_mode=self.border_mode,
+                            dim_ordering='th')
 
         output = conv_out + K.reshape(self.b, (1, self.nb_filter, 1, 1))
         output = self.activation(output)
@@ -212,7 +213,9 @@ class Convolution2D(Layer):
         X = self.get_input(train)
         conv_out = K.conv2d(X, self.W, strides=self.subsample,
                             border_mode=self.border_mode,
-                            dim_ordering=self.dim_ordering)
+                            dim_ordering=self.dim_ordering,
+                            image_shape=self.input_shape,
+                            filter_shape=self.W_shape)
 
         output = conv_out + K.reshape(self.b, (1, self.nb_filter, 1, 1))
         output = self.activation(output)