Bug fixed and clean codes.

1. Backward bugs fixed.
2. Fix the minor errors.

source/network/XBackwardFunc.cpp

@@ -34,7 +34,14 @@ void XFuncGrad::MakeGrad(XTensor * node, bool isEfficient)
     XLink &income = node->income;
     XLink &income = node->income;
     int operID = income.typeID;
     int operID = income.typeID;
 
 
-    CheckNTErrors(node->grad != NULL, "No gradient found!");
+    if(!isEfficient){
+        CheckNTErrors(node->grad != NULL, "No gradient found!");
+    }
+    else{
+        CheckNTErrors(!node->isGrad || node->grad != NULL, "No gradient found!");
+    }
+
+    //CheckNTErrors(node->grad != NULL, "No gradient found!");
     CheckNTErrors(income.tailNum == 1, "Too many input tensors for the function!");
     CheckNTErrors(income.tailNum == 1, "Too many input tensors for the function!");
 
 
     XTensor * input = income.tails[0];
     XTensor * input = income.tails[0];

source/network/XBackwardShape.cpp

@@ -32,33 +32,38 @@
 namespace nts{
 namespace nts{
 
 
 /* compute dE/dx of a node */
 /* compute dE/dx of a node */
-void XShapeGrad::MakeGrad(XTensor * node, bool isEfficent)
+void XShapeGrad::MakeGrad(XTensor * node, bool isEfficient)
 {
 {
-    CheckNTErrors(node->grad != NULL, "No gradient found!");
+    if(!isEfficient){
+        CheckNTErrors(node->grad != NULL, "No gradient found!");
+    }
+    else{
+        CheckNTErrors(!node->isGrad || node->grad != NULL, "No gradient found!");
+    }
 
 
     XLink &income = node->income;
     XLink &income = node->income;
     int operID = income.typeID;
     int operID = income.typeID;
 
 
     if(operID == MOVEMENT_COPYINDEXED)
     if(operID == MOVEMENT_COPYINDEXED)
-        GradCopyIndexed(node, isEfficent);
+        GradCopyIndexed(node, isEfficient);
     else if(operID == MOVEMENT_GATHER)
     else if(operID == MOVEMENT_GATHER)
-        GradGather(node, isEfficent);
+        GradGather(node, isEfficient);
     else if (operID == MOVEMENT_DROPOUTWITHINDEX)
     else if (operID == MOVEMENT_DROPOUTWITHINDEX)
-        GradDropoutWithIndex(node, isEfficent);
+        GradDropoutWithIndex(node, isEfficient);
     else if(operID == SHAPE_MERGE)
     else if(operID == SHAPE_MERGE)
-        GradMerge(node, isEfficent);
+        GradMerge(node, isEfficient);
     else if(operID == SHAPE_MERGE_LIST)
     else if(operID == SHAPE_MERGE_LIST)
-        GradMergeList(node, isEfficent);
+        GradMergeList(node, isEfficient);
     else if(operID == SHAPE_RESHAPE)
     else if(operID == SHAPE_RESHAPE)
-        GradReshape(node, isEfficent);
+        GradReshape(node, isEfficient);
     else if(operID == SHAPE_SPLIT)
     else if(operID == SHAPE_SPLIT)
-        GradSplit(node, isEfficent);
+        GradSplit(node, isEfficient);
     else if(operID == SHAPE_SPLIT_LIST)
     else if(operID == SHAPE_SPLIT_LIST)
-        GradSplitList(node, isEfficent);
+        GradSplitList(node, isEfficient);
     else if (operID == SHAPE_TRANSPOSE)
     else if (operID == SHAPE_TRANSPOSE)
-        GradTranspose(node, isEfficent);
+        GradTranspose(node, isEfficient);
     else if(operID == SHAPE_UNSQUEEZE)
     else if(operID == SHAPE_UNSQUEEZE)
-        GradUnsqueeze(node, isEfficent);
+        GradUnsqueeze(node, isEfficient);
     else{
     else{
         ShowNTErrors("TODO!");
         ShowNTErrors("TODO!");
     }
     }

source/network/XBackwardShape.h

@@ -34,7 +34,7 @@ class XShapeGrad
 public:
 public:
     /* compute dE/dx of a node */
     /* compute dE/dx of a node */
     static
     static
-    void MakeGrad(XTensor * node, bool isEfficent);
+    void MakeGrad(XTensor * node, bool isEfficient);
 
 
     /* indicates whether the node is for a shaping operation */
     /* indicates whether the node is for a shaping operation */
     static
     static

source/tensor/function/LogSoftmax.cpp

@@ -293,7 +293,7 @@ void _LogSoftmaxBackward(XTensor * gold, XTensor * y, XTensor * x,
                          LOSS_FUNCTION_NAME lossName)
                          LOSS_FUNCTION_NAME lossName)
 {
 {
     CheckNTErrors((!dedx->isSparse), "The gradient matrix must be dense!");
     CheckNTErrors((!dedx->isSparse), "The gradient matrix must be dense!");
-    CheckNTErrors((gold != NULL), "The gold standard cannot be empty!");
+    CheckNTErrors((gold != NULL || lossName == NOLOSS), "The gold standard cannot be empty!");
 
 
     if(leadDim < 0)
     if(leadDim < 0)
         leadDim = y->order - 1;
         leadDim = y->order - 1;