Same changes for GPU. cuDNN disabled. More tests

theano/gpuarray/blas.py

@@ -480,11 +480,11 @@ class BaseGpuCorrMM(CGpuKernelBase):
                     'tuple of length 2'.format(border_mode))
             border = ()
             for mode in border_mode:
-                if isinstance(mode, integer_types) and mode >= 0:
-                    border += ((mode, mode),)
-                elif isinstance(mode, tuple) and len(mode) == 2 and \
+                if isinstance(mode, tuple) and len(mode) == 2 and \
                         min(mode) >= 0:
                     border += ((int(mode[0]), int(mode[1])),)
+                elif mode >= 0:
+                    border += ((int(mode), int(mode)),)
                 else:
                     raise ValueError(
                         'invalid border mode {}. The tuple can only contain '
@@ -630,13 +630,13 @@ class BaseGpuCorrMM(CGpuKernelBase):
         if height:
             height = '(*(npy_int*)(PyArray_DATA(%s)))' % height
         else:
-            if ((direction != 0) and (dH != 1)) or ((direction == 1) and (padH_l == -1)):
+            if ((direction != 0) and (dH != 1)) or ((direction == 1) and (padH_l == -1 or padH_r == -1)):
                 raise ValueError("height must be given for backprop with vertical sampling or pad='half'")
             height = '-1'
         if width:
             width = '(*(npy_int*)(PyArray_DATA(%s)))' % width
         else:
-            if ((direction != 0) and (dW != 1)) or ((direction == 1) and (padW_l == -1)):
+            if ((direction != 0) and (dW != 1)) or ((direction == 1) and (padW_l == -1 or padW_r == -1)):
                 raise ValueError("width must be given for backprop with horizontal sampling or pad='half'")
             width = '-1'
 

theano/gpuarray/dnn.py

@@ -3038,6 +3038,9 @@ def local_abstractconv_cudnn_graph(op, context_name, inputs, outputs):
     if op.unshared:
         return None
 
+    if isinstance(op.border_mode, tuple) and any(isinstance(p, tuple) for p in op.border_mode):
+        return None
+
     inp1 = inputs[0]
     inp2 = inputs[1]
 
@@ -3134,6 +3137,8 @@ def local_abstractconv_cudnn(node):
         return
     if node.op.unshared:
         return None
+    if isinstance(node.op.border_mode, tuple) and any(isinstance(p, tuple) for p in node.op.border_mode):
+        return None
     if isinstance(node.op, AbstractConv2d):
         return local_abstractconv_cudnn_graph(node.op, ctx, node.inputs, node.outputs)
     elif isinstance(node.op, AbstractConv3d):
@@ -3150,6 +3155,8 @@ def local_abstractconv_cudnn_alt(node):
         return None
     if node.op.unshared:
         return None
+    if isinstance(node.op.border_mode, tuple) and any(isinstance(p, tuple) for p in node.op.border_mode):
+        return None
     inp1 = node.inputs[0]
     inp2 = node.inputs[1]
 
@@ -3358,6 +3365,8 @@ def local_abstractconv_gw_cudnn(node):
         return
     if node.op.unshared:
         return None
+    if isinstance(node.op.border_mode, tuple) and any(isinstance(p, tuple) for p in node.op.border_mode):
+        return None
     if isinstance(node.op, AbstractConv2d_gradWeights):
         return local_abstractconv_cudnn_graph(node.op, ctx, node.inputs, node.outputs)
     elif isinstance(node.op, AbstractConv3d_gradWeights):
@@ -3371,6 +3380,8 @@ def local_abstractconv_gi_cudnn(node):
         return
     if node.op.unshared:
         return None
+    if isinstance(node.op.border_mode, tuple) and any(isinstance(p, tuple) for p in node.op.border_mode):
+        return None
     if isinstance(node.op, AbstractConv2d_gradInputs):
         return local_abstractconv_cudnn_graph(node.op, ctx, node.inputs, node.outputs)
     elif isinstance(node.op, AbstractConv3d_gradInputs):

theano/gpuarray/tests/test_gemmcorr.py

@@ -12,7 +12,7 @@ from ..type import gpuarray_shared_constructor
 from ..blas import GpuCorrMM, GpuCorrMM_gradWeights, GpuCorrMM_gradInputs
 from .config import mode_with_gpu, mode_without_gpu, ref_cast
 from theano.tensor.nnet.tests.test_abstract_conv import Grouped_conv_noOptim, TestUnsharedConv
-from theano.tensor.nnet.tests.test_abstract_conv import TestAsymmetricPadding
+from theano.tensor.nnet.tests.test_abstract_conv import TestAsymmetricPadding, TestCausalConv
 
 
 class TestCorrMM(unittest.TestCase):
@@ -280,3 +280,7 @@ class TestAsymmetricGpu(TestAsymmetricPadding):
     conv2d_op = GpuCorrMM
     conv2d_gradw_op = GpuCorrMM_gradWeights
     conv2d_gradi_op = GpuCorrMM_gradInputs
+
+
+class TestCausalGpuCorr(TestCausalConv):
+    mode = mode_with_gpu.excluding('cudnn')

theano/tensor/nnet/tests/test_corr.py

@@ -11,7 +11,7 @@ import theano.tensor as T
 from theano.tests import unittest_tools as utt
 from theano.tensor.nnet import corr, conv
 from theano.tensor.nnet.tests.test_abstract_conv import Grouped_conv_noOptim, TestUnsharedConv
-from theano.tensor.nnet.tests.test_abstract_conv import TestAsymmetricPadding
+from theano.tensor.nnet.tests.test_abstract_conv import TestAsymmetricPadding, TestCausalConv
 
 
 class TestCorr2D(utt.InferShapeTester):
@@ -473,6 +473,13 @@ class TestAsymmetricCorr(TestAsymmetricPadding):
     conv2d_gradi_op = corr.CorrMM_gradInputs
 
 
+class TestCausalCorr(TestCausalConv):
+    if theano.config.mode == "FAST_COMPILE":
+        mode = theano.compile.get_mode("FAST_RUN").excluding('gpuarray')
+    else:
+        mode = None
+
+
 if __name__ == '__main__':
 
     t = TestCorr2D('setUp')