Convop's getOutputShape modified to reflect docstring: inshp a pair.

theano/tensor/nnet/conv.py

@@ -213,7 +213,7 @@ class ConvOp(Op):
         if mode=='valid': s = -1
         else: s = 1
         inshp, kshp = numpy.array(inshp), numpy.array(kshp)
-        return  numpy.int64(numpy.ceil((inshp[1:] + s*kshp - s*1)/\
+        return  numpy.int64(numpy.ceil((inshp + s*kshp - s*1)/\
                 numpy.array([dx,dy], dtype='float')))
 
 
@@ -372,8 +372,8 @@ class ConvOp(Op):
                 self.unroll_kern=new
 
         if all_shape:
-            self.outshp = ConvOp.getOutputShape(self.imshp_logical, self.kshp_logical, (dx,dy), output_mode)
-            self.fulloutshp = ConvOp.getOutputShape(self.imshp_logical, self.kshp_logical, (1,1), output_mode)
+            self.outshp = ConvOp.getOutputShape(self.imshp_logical[1:], self.kshp_logical, (dx,dy), output_mode)
+            self.fulloutshp = ConvOp.getOutputShape(self.imshp_logical[1:], self.kshp_logical, (1,1), output_mode)
         else:
             self.outshp = None
             self.fulloutshp = None
@@ -509,7 +509,7 @@ class ConvOp(Op):
         if self.fulloutshp is not None:
             fulloutshp = tuple(self.fulloutshp)
         else:
-            fulloutshp = tuple(ConvOp.getOutputShape(imshp_logical, kshp_logical, (1,1), self.out_mode))
+            fulloutshp = tuple(ConvOp.getOutputShape(imshp_logical[1:], kshp_logical, (1,1), self.out_mode))
 
         if z[0] is None or z[0].shape!=(bsize,)+(nkern,)+fulloutshp:
             z[0] = numpy.zeros((bsize,)+(nkern,)+fulloutshp,

theano/tensor/nnet/tests/speed_test_conv.py

@@ -79,7 +79,7 @@ def exec_multilayer_conv_nnet(conv_mode, ss, bsize, imshp, kshps, nkerns,
                 padimg[:, :, kshp[0]-1:-kshp[0]+1, 
                              kshp[1]-1:-kshp[1]+1] = imgval
 
-            outshp = N.hstack((nkern, ConvOp.getOutputShape(imshp, kshp, ss, conv_mode)))
+            outshp = N.hstack((nkern, ConvOp.getOutputShape(imshp[1:], kshp, ss, conv_mode)))
 
             time1 = time.time()
             outval = N.zeros(N.r_[bsize,outshp])
@@ -104,7 +104,7 @@ def exec_multilayer_conv_nnet(conv_mode, ss, bsize, imshp, kshps, nkerns,
                 conv_op = ConvOp(imshp, kshp, nkern, bsize, ss[0],ss[1], conv_mode,
                                  unroll_batch=unroll_batch, unroll_kern=unroll_kern, unroll_patch=unroll_patch, verbose=verbose)(inputs4, kerns4)
             l1shp=N.hstack((nkern,
-                            ConvOp.getOutputShape(imshp, kshp, ss, conv_mode)))
+                            ConvOp.getOutputShape(imshp[1:], kshp, ss, conv_mode)))
             propup2 = function([inputs4, kerns4], conv_op)
             propup3 = function([inputs4, kerns4], conv_op, mode=Mode(linker="py"))