grad still failed

theano/tensor/signal/downsample.py

@@ -223,7 +223,7 @@ class DownsampleFactorMax(Op):
         # pad the image
         fill = x.min()-1
         y = numpy.zeros((x.shape[0], x.shape[1], img_rows, img_cols)) + fill
-        y[:, :, pad_h:-pad_h, pad_w:-pad_w] = x
+        y[:, :, pad_h:(y.shape[2]-pad_h), pad_w:(y.shape[3]-pad_w)] = x
         # max pooling
         for n in xrange(x.shape[0]):
             for k in xrange(x.shape[1]):
@@ -369,12 +369,12 @@ class DownsampleFactorMaxGrad(Op):
         img_cols = x.shape[-1] + 2 * self.padding[1]
         pad_h = self.padding[0]
         pad_w = self.padding[1]
-
+        
         
         # pad the image
         fill = x.min()-1
         y = numpy.zeros((x.shape[0], x.shape[1], img_rows, img_cols)) + fill
-        y[:, :, pad_h:-pad_h, pad_w:-pad_w] = x
+        y[:, :, pad_h:(y.shape[2]-pad_h), pad_w:(y.shape[3]-pad_w)] = x
         gx = numpy.zeros_like(y)
         for n in xrange(x.shape[0]):
             for k in xrange(x.shape[1]):
@@ -389,7 +389,7 @@ class DownsampleFactorMaxGrad(Op):
                                 if (maxout[n, k, r, c] == y[n, k, row_ind, col_ind]):
                                     gx[n, k, row_ind, col_ind] += gz[n, k, r, c]
         # unpad the image
-        gx = gx[:, :, pad_h:-pad_h, pad_w:-pad_w]
+        gx = gx[:, :, pad_h:(y.shape[2]-pad_h), pad_w:(y.shape[3]-pad_w)]
         gx_stg[0] = gx
 
     def infer_shape(self, node, in_shapes):

theano/tensor/signal/tests/test_downsample.py

@@ -240,10 +240,10 @@ class TestDownsampleFactorMax(utt.InferShapeTester):
     def test_DownsampleFactorMaxPaddingStride(self):
         ignore_border = True # padding does not support ignore_border=False
         rng = numpy.random.RandomState(utt.fetch_seed())
-        maxpoolsizes = [(3, 3), (4,4), (3,4)]
-        stridesizes = [(2, 2), (2,2), (1,1)]
-        paddingsizes = [(2, 2), (1,2), (2,1)]
-        imgsizes = [(5, 5), (5,5), (5,6)]
+        maxpoolsizes = [(3, 3), (4,4), (3,4), (4,3)]
+        stridesizes = [(2, 2), (2,2), (1,1), (1,2)]
+        paddingsizes = [(2, 2), (1,2), (2,1), (0,0)]
+        imgsizes = [(5, 5), (5,5), (5,6), (6,5)]
         m = 4 # minibatch
         c = 10 # channel size
         images = tensor.dtensor4()