added copy_stack_trace calls, todo: unit tests

theano/tensor/nnet/conv3d2d.py

@@ -3,6 +3,7 @@ from theano.gradient import DisconnectedType
 from theano.gof import Op, Apply, TopoOptimizer
 from theano import tensor
 import theano.sandbox.cuda as cuda
+from theano.tensor.opt import copy_stack_trace
 
 
 def get_diagonal_subtensor_view(x, i0, i1):
@@ -328,7 +329,9 @@ def make_gpu_optimizer(op, to_gpu):
                 new_inp = list(node.inputs)
                 for idx in to_gpu:
                     new_inp[idx] = cuda.gpu_from_host(new_inp[idx])
-                return [cuda.host_from_gpu(op()(*new_inp))]
+                new_node = cuda.host_from_gpu(op()(*new_inp))
+                copy_stack_trace(node.outputs[0], new_node)
+                return [new_node]
         if node.op == cuda.gpu_from_host:
             # gpu_from_host(op) -> op(gpu_from_host)
             host_input = node.inputs[0]
@@ -338,7 +341,9 @@ def make_gpu_optimizer(op, to_gpu):
                 new_inp = list(op_node.inputs)
                 for idx in to_gpu:
                     new_inp[idx] = cuda.gpu_from_host(new_inp[idx])
-                return [op()(*new_inp)]
+                new_node = op()(*new_inp)
+                copy_stack_trace(node.outputs[0], new_node)
+                return [new_node]
         return False
     local_to_gpu.__name__ = "local_to_gpu_" + op.__name__
     cuda.opt.register_opt()(local_to_gpu)
@@ -355,6 +360,7 @@ def local_inplace_DiagonalSubtensor(node):
             not node.op.inplace):
         new_op = node.op.__class__(inplace=True)
         new_node = new_op(*node.inputs)
+        copy_stack_trace(node.outputs[0], new_node)
         return [new_node]
     return False
 theano.compile.optdb.register(

theano/tensor/nnet/nnet.py

@@ -752,7 +752,8 @@ def local_logsoftmax(node):
         inVars = node.inputs[0].owner.inputs[0]
         new_op = LogSoftmax()
         ret = new_op(inVars)
-        ret.tag.values_eq_approx = values_eq_approx_remove_inf
+        ret .tag.values_eq_approx = values_eq_approx_remove_inf
+        copy_stack_trace(node.outputs[0], ret)
         return [ret]
 
 
@@ -785,9 +786,9 @@ def local_logsoftmax_grad(node):
         grads = node.inputs[0].owner.inputs[0]
         if grads.broadcastable[1] and not sm.broadcastable[1]:
             grads = tensor.alloc(grads, grads.shape[0], sm.shape[1])
-
         ret = grads - tensor.sum(grads, axis=1, keepdims=True) * sm
         ret.tag.values_eq_approx = values_eq_approx_remove_nan
+        copy_stack_trace(node.outputs[0], ret)
         return [ret]
 
 
@@ -866,6 +867,7 @@ def local_softmax_with_bias(node):
                 if sm_bias.type == node.outputs[0].type:
                     # This condition is not always true. See the test
                     # nnet/tests/test_nnet.py:T_SoftmaxWithBias.test_broadcast
+                    copy_stack_trace(node.outputs[0], sm_bias)
                     return [sm_bias]
 
 

theano/tensor/nnet/opt.py

@@ -36,6 +36,7 @@ def local_inplace_sparse_block_gemv(node):
     """
     if isinstance(node.op, SparseBlockGemv) and not node.op.inplace:
         new_node = sparse_block_gemv_inplace(*node.inputs)
+        copy_stack_trace(node.outputs[0], new_node)
         return [new_node]
     return False
 compile.optdb.register('local_inplace_sparse_block_gemv',
@@ -52,6 +53,7 @@ def local_inplace_sparse_block_outer(node):
     """
     if isinstance(node.op, SparseBlockOuter) and not node.op.inplace:
         new_node = sparse_block_outer_inplace(*node.inputs)
+        copy_stack_trace(node.outputs[0], new_node)
         return [new_node]
     return False
 compile.optdb.register('local_inplace_sparse_block_outer',

theano/tensor/nnet/sigm.py

@@ -18,7 +18,7 @@ from theano.printing import pprint
 from theano.tensor import basic as tensor
 from theano.tensor import elemwise, opt, NotScalarConstantError
 from theano.tensor.type import values_eq_approx_remove_inf
-
+from theano.tensor.opt import copy_stack_trace
 
 ############
 #
@@ -262,6 +262,7 @@ def local_ultra_fast_sigmoid(node):
     if (isinstance(node.op, tensor.Elemwise) and
             node.op.scalar_op == scalar_sigmoid):
         out = ultra_fast_sigmoid(node.inputs[0])
+        copy_stack_trace(node.outputs[0], out)
 
         def values_eq_approx_remove_low_prec(a, b):
             # atol is found by trial/error.
@@ -301,6 +302,7 @@ def local_hard_sigmoid(node):
     if (isinstance(node.op, tensor.Elemwise) and
             node.op.scalar_op == scalar_sigmoid):
         out = hard_sigmoid(node.inputs[0])
+        copy_stack_trace(node.outputs[0], out)
 
         def values_eq_approx_remove_low_prec(a, b):
             # atol is found by trial/error.
@@ -925,7 +927,10 @@ def local_sigm_times_exp(node):
     # get rid of them.
     mul_tree = simplify_mul(mul_tree)
     # Recompute final output based on the updated tree.
-    return [compute_mul(mul_tree)]
+    out = compute_mul(mul_tree)
+    # keep the stack trace
+    copy_stack_trace(node.outputs[0], out)
+    return [out]
 
 
 @opt.register_stabilize
@@ -946,10 +951,13 @@ def local_inv_1_plus_exp(node):
             if len(nonconsts) == 1:
                 if nonconsts[0].owner and nonconsts[0].owner.op == tensor.exp:
                     if scalars and numpy.allclose(numpy.sum(scalars), 1):
-                        return opt._fill_chain(
+                        out = opt._fill_chain(
                             sigmoid(
                                 tensor.neg(nonconsts[0].owner.inputs[0])),
                             scalar_inputs)
+                        # keep stack trace
+                        copy_stack_trace(node.outputs[0], out)
+                        return out
 
 # Registration is below, and conditional.
 
@@ -970,7 +978,9 @@ def local_1msigmoid(node):
             except Exception:
                 return
             if numpy.allclose(numpy.sum(val_l), 1):
-                return [sigmoid(-sub_r.owner.inputs[0])]
+                out = sigmoid(-sub_r.owner.inputs[0])
+                copy_stack_trace(node.outputs[0], out)
+                return [out]
 
 register_local_1msigmoid = False
 # This is False because the Stabilize pattern above