GpuConvGrad3D has been modified in order to respect the flake8 style.

theano/sandbox/cuda/GpuConvGrad3D.py

@@ -39,7 +39,7 @@ class GpuConvGrad3D(GpuOp):
         d_ = T.as_tensor_variable(d)
         WShape_ = T.as_tensor_variable(WShape)
         dCdH_ = as_cuda_ndarray_variable(dCdH)
-        broad = (False,)*5
+        broad = (False,) * 5
         return theano.Apply(self, inputs=[V_, d_, WShape_, dCdH_],
                             outputs=[CudaNdarrayType(dtype=V_.dtype,
                                                      broadcastable=broad)()])
@@ -51,15 +51,10 @@ class GpuConvGrad3D(GpuOp):
         # partial C / partial W[j,z,k,l,m] = sum_i sum_p sum_q sum_r (partial C /partial H[i,j,p,q,r] ) *  V[i,z,dr*p+k,dc*q+l,dt*r+m]
 
         batchSize = dCdH.shape[0]
-        outputFilters = dCdH.shape[1]
         outputHeight = dCdH.shape[2]
         outputWidth = dCdH.shape[3]
         outputDur = dCdH.shape[4]
         assert V.shape[0] == batchSize
-        inputFilters = V.shape[1]
-        inputHeight = V.shape[2]
-        inputWidth = V.shape[3]
-        inputDur = V.shape[4]
         dr, dc, dt = d
 
         dCdW = numpy.zeros(WShape, dtype=V.dtype)
@@ -76,7 +71,11 @@ class GpuConvGrad3D(GpuOp):
                                 for p in xrange(0, outputHeight):
                                     for q in xrange(0, outputWidth):
                                         for r in xrange(0, outputDur):
-                                            dCdW[j, z, k, l, m] += dCdH[i, j, p, q, r] * V[i, z, dr*p+k, dc*q+l, dt*r+m]
+                                            dCdW[j, z, k, l, m] += dCdH[
+                                                i, j, p, q, r] * \
+                                                V[i, z, dr * p + k,
+                                                  dc * q + l,
+                                                  dt * r + m]
 
         output_storage[0][0] = dCdW