Merge pull request #2691 from rolfvandam/max_pool_same_size

theano/tensor/signal/downsample.py

@@ -18,6 +18,23 @@ def max_pool2D(*args, **kwargs):
     print >> sys.stderr, "DEPRECATION: max_pool2D renamed to max_pool_2d"
     return max_pool_2d(*args, **kwargs)
 
+def max_pool_2d_same_size(input, patch_size):
+    """
+    Takes as input a 4-D tensor. It sets all non maximum values 
+    of non-overlapping patches of size (patch_size[0],patch_size[1]) to zero, 
+    keeping only the maximum values. The output has the same dimensions as 
+    the input.
+
+    :type input: 4-D theano tensor of input images.
+    :param input: input images. Max pooling will be done over the 2 last
+        dimensions.
+    :type patch_size: tuple of length 2
+    :param patch_size: size of the patch (patch height, patch width).
+        (2,2) will retain only one non-zero value per patch of 4 values.
+    """
+    output = DownsampleFactorMax(patch_size, True)(input)
+    outs = DownsampleFactorMaxGrad(patch_size, True)(input, output, output)
+    return outs
 
 def max_pool_2d(input, ds, ignore_border=False, st=None, padding=(0, 0)):
     """
@@ -43,7 +60,6 @@ def max_pool_2d(input, ds, ignore_border=False, st=None, padding=(0, 0)):
             of the images, pad_h is the size of the top and bottom margins,
             and pad_w is the size of the left and right margins.
     :type padding: tuple of two ints
-
     """
     if input.ndim < 2:
         raise NotImplementedError('max_pool_2d requires a dimension >= 2')

theano/tensor/signal/tests/test_downsample.py

@@ -4,7 +4,7 @@ import numpy
 import theano.tensor as tensor
 from theano.tests import unittest_tools as utt
 from theano.tensor.signal.downsample import (DownsampleFactorMax, max_pool_2d,
-                                             DownsampleFactorMaxGrad)
+                                             DownsampleFactorMaxGrad, max_pool_2d_same_size)
 from theano import function
 
 
@@ -464,6 +464,29 @@ class TestDownsampleFactorMax(utt.InferShapeTester):
                     return max_pool_2d(input, maxpoolshp, ignore_border)
                 utt.verify_grad(mp, [imval], rng=rng)
 
+    def test_max_pool_2d_2D_same_size(self):
+        rng = numpy.random.RandomState(utt.fetch_seed())
+        test_input_array = numpy.array([[[
+            [1.,2.,3.,4.], 
+            [5.,6.,7.,8.]
+        ]]])
+        test_answer_array = numpy.array([[[
+            [0.,0.,0.,0.],
+            [0.,6.,0.,8.]
+        ]]])
+        input = tensor.tensor4(name='input')
+        patch_size = (2,2)
+        op = max_pool_2d_same_size(input, patch_size)
+        op_output = function([input], op)(test_input_array)
+        assert numpy.all(op_output == test_answer_array), (
+            "op_output is %s, test_answer_array is %s" % (
+                op_output, numpy_output_val
+            )
+        )
+        def mp(input):
+            return max_pool_2d_same_size(input, patch_size)
+        utt.verify_grad(mp, [test_input_array], rng=rng)
+
     def test_max_pool_2d_3D(self):
         rng = numpy.random.RandomState(utt.fetch_seed())
         maxpoolshps = [(1, 2)]