refine some bad code

source/tensor/Main.cpp

@@ -45,7 +45,7 @@ int main( int argc, const char ** argv )
     //_CrtSetBreakAlloc(123);
 
     /* a tiny test */
-    if(true)
+    if(false)
         SmallTest();
 
     //_CrtDumpMemoryLeaks();
@@ -53,8 +53,8 @@ int main( int argc, const char ** argv )
 
     if(argc > 1 && !strcmp(argv[1], "-test"))
         Test();
-    //else if(argc > 1 && !strcmp(argv[1], "-fnnlm"))
-    //    FNNLMMain(argc - 1, argv + 1);
+    else if(argc > 1 && !strcmp(argv[1], "-fnnlm"))
+        FNNLMMain(argc - 1, argv + 1);
     else{
         fprintf(stderr, "Thanks for using NiuTrans.Tensor! This is a library that eases the\n");
         fprintf(stderr, "use of tensors. All you need is to ... \n\n");

source/tensor/core/arithmetic/MatrixMul.cpp

@@ -210,7 +210,7 @@ Obviously C = A * B performs normal matrix multiplication if A = y * z and B = x
 XTensor MatrixMul(const XTensor &a, MATRIX_TRANS_TYPE transposedA, const XTensor &b, MATRIX_TRANS_TYPE transposedB, 
                  DTYPE alpha, DTYPE beta, XPRunner * parallelRunner)
 {
-    CheckNTErrors((&a && &b), "Empty input tensors!");
+    CheckNTErrors((&a != &NULLTensor && &b != &NULLTensor), "Empty input tensors!");
     CheckNTErrors((a.dataType == b.dataType), "Input tensors should have the same data type!");
     CheckNTErrors((a.order >= 2 && b.order >= 2), "Input tensors must have a order >= 2!");
 
@@ -246,7 +246,7 @@ XTensor MatrixMul(const XTensor &a, MATRIX_TRANS_TYPE transposedA, const XTensor
     XLink::AddParamToHead(&c, beta);
 
     /* destroy variables */
-    delete dimSize;
+    delete[] dimSize;
 
     return c;
 }

source/tensor/core/arithmetic/MatrixMulBatched.cpp

@@ -175,9 +175,9 @@ where trans() returns the transposed matrix if the flag is fired.
 XTensor MatrixMulBatched(const XTensor &a, MATRIX_TRANS_TYPE transposedA, const XTensor &b, MATRIX_TRANS_TYPE transposedB,
                         DTYPE alpha, DTYPE beta, XPRunner * parallelRunner)
 {
-    CheckNTErrors((&a && &b), "Empty input tensors!");
+    CheckNTErrors(&a != &NULLTensor && &b != &NULLTensor, "Empty input tensors!");
     CheckNTErrors(a.dataType == b.dataType, "Input tensors should have the same data type!");
-    CheckNTErrors((a.order >= 2 && b.order >= 2), "Input tensors must have a order >= 2!");
+    CheckNTErrors(a.order >= 2 && b.order >= 2, "Input tensors must have a order >= 2!");
     CheckNTErrors(a.order == b.order, "Input tensor and output tensor must have same order!");
 
     int an = transposedA == X_TRANS ? a.dimSizeRDI[0] : a.dimSizeRDI[1];
@@ -210,7 +210,7 @@ XTensor MatrixMulBatched(const XTensor &a, MATRIX_TRANS_TYPE transposedA, const
     XLink::AddParamToHead(&c, beta);
 
     /* destroy variables */
-    delete dimSize;
+    delete[] dimSize;
 
     return c;
 }

source/tensor/core/getandset/Select.cpp

@@ -123,7 +123,7 @@ XTensor SelectRange(const XTensor &a, int dim, int low, int high)
     XLink::AddParamToHead(&c, high);
 
     /* destroy variables */
-    delete dimSize;
+    delete[] dimSize;
 
     return c;
 }

source/tensor/core/movement/CopyIndexed.cpp

@@ -131,7 +131,7 @@ XTensor CopyIndexed(const XTensor &s, int dim, int * srcIndex, int indexSize, in
     _CopyIndexed(&s, &t, dim, srcIndex, indexSize, tgtIndex, copyNum);
 
     /* destroy variables */
-    delete dimSize;
+    delete[] dimSize;
     
     /* tensor connection */
     XLink::MakeLink(&s, NULL, &t, MOVEMENT_COPYINDEXED);

source/tensor/core/reduce/ReduceMax.cpp

@@ -121,7 +121,7 @@ XTensor ReduceMax(const XTensor &input, int dim)
     _ReduceMax(&input, &output, dim);
 
     /* destroy variables */
-    delete dimSize;
+    delete[] dimSize;
 
     /* tensor connection */
     XLink::MakeLink(&input, NULL, &output, REDUCE_REDUCEMAX);

source/tensor/core/reduce/ReduceMean.cpp

@@ -82,7 +82,7 @@ XTensor ReduceMean(const XTensor &input, int dim)
     XLink::AddParamToHead(&output, dim);
 
     /* destroy variables */
-    delete dimSize;
+    delete[] dimSize;
 
     return output;
 }

source/tensor/core/reduce/ReduceSum.cpp

@@ -239,7 +239,7 @@ XTensor ReduceSum(const XTensor &input, int dim, const XTensor &shift, DTYPE pow
     XLink::AddParamToHead(&output, power);
 
     /* destroy variables */
-    delete dimSize;
+    delete[] dimSize;
 
     return output;
 }

source/tensor/core/reduce/ReduceSumSquared.cpp

@@ -78,7 +78,7 @@ XTensor ReduceSumSquared(const XTensor &input, int dim, const XTensor &shift)
     XLink::AddParamToHead(&output, dim);
 
     /* destroy variables */
-    delete dimSize;
+    delete[] dimSize;
 
     return output;
 }

source/tensor/core/reduce/ReduceVariance.cpp

@@ -76,7 +76,7 @@ XTensor ReduceVariance(const XTensor &input, int dim, const XTensor &mean)
     _ReduceVariance(&input, &output, dim, &mean);
 
     /* destroy variables */
-    delete dimSize;
+    delete[] dimSize;
 
     return output;
 }

source/tensor/core/shape/Merge.cpp

@@ -188,7 +188,7 @@ XTensor Merge(const XTensor &s, int whereToMerge, int leadingDim)
     _Merge(&s, &t, whereToMerge, leadingDim);
 
     /* destroy variables */
-    delete dimSize;
+    delete[] dimSize;
 
     return t;
 }
@@ -335,7 +335,7 @@ XTensor Merge(const XList &smalls, int whereToMerge)
     _Merge(&smalls, &big, whereToMerge);
 
     /* destroy variables */
-    delete dimSize;
+    delete[] dimSize;
 
     return big;
 }

source/tensor/core/shape/Split.cpp

@@ -162,7 +162,7 @@ XTensor Split(const XTensor &s, int whereToSplit, int splitNum)
     _Split(&s, &t, whereToSplit, splitNum);
 
     /* destroy variables */
-    delete dimSize;
+    delete[] dimSize;
 
     return t;
 }
@@ -308,7 +308,7 @@ XList SplitList(const XTensor &big, int whereToSplit, int splitNum)
     _Split(&big, &smalls, whereToSplit, splitNum);
     
     /* destroy variables */
-    delete dimSize;
+    delete[] dimSize;
 
     return smalls;
 }

source/tensor/core/shape/Unsqueeze.cpp

@@ -130,7 +130,7 @@ XTensor Unsqueeze(const XTensor &a, int dim, int dSize)
     _Unsqueeze(&a, &b, dim, dSize);
 
     /* destroy variables */
-    delete dimSize;
+    delete[] dimSize;
 
     return b;
 }

source/tensor/function/Loss.cpp

@@ -178,7 +178,11 @@ DTYPE LossCompute(XTensor * gold, XTensor * output, LOSS_FUNCTION_NAME LFName,
         }
     }
     else {
+#ifdef USE_CUDA
         error = CudaLossCompute(gold, output, LFName, isLogOutput, leadDim, gBeg, gLen, oBeg);
+#else
+        ShowNTErrors("Please specify USE_CUDA and recompile the code!");
+#endif
     }
 
     return error;
@@ -476,7 +480,11 @@ void LossBackward(XTensor * dedy, XTensor * t, XTensor * y,
         }
     }
     else {
+#ifdef USE_CUDA
         CudaLossBackward(dedy, t, y, LFName, leadDim, tBeg, tLen, yBeg);
+#else
+        ShowNTErrors("Please specify USE_CUDA and recompile the code!");
+#endif
     }
 }
 

source/tensor/sample/fnnlm/FNNLM.cpp

@@ -490,9 +490,9 @@ float GetProb(XTensor &output, XTensor &gold, XTensor * wordProbs)
     /* probability of each word */
     XTensor wprobs;
     InitTensor1D(&wprobs, output.GetDim(0), output.dataType, output.devID, output.mem);
-    ReduceSum(&probs, &wprobs, 1);
+    _ReduceSum(&probs, &wprobs, 1);
     if(wordProbs != NULL)
-        CopyValues(&wprobs, wordProbs);
+        _CopyValues(&wprobs, wordProbs);
 
     /* reshape the tensor to fit it into the reduce procedure 
        TODO: XTensor supports scalars */
@@ -504,7 +504,7 @@ float GetProb(XTensor &output, XTensor &gold, XTensor * wordProbs)
     /* probability for the batch */
     XTensor result;
     InitTensor1D(&result, 1, X_FLOAT, output.devID, output.mem);
-    ReduceSum(&probs, &result, 1);
+    _ReduceSum(&probs, &result, 1);
     
     return result.Get1D(0);
 }
@@ -673,7 +673,7 @@ void Forward(XTensor inputs[], XTensor &output, FNNModel &model, FNNNet &net)
 
         /* generate word embedding of position i:
            embedding = input * w   */
-        MatrixMul(&input, X_NOTRANS, &w, X_NOTRANS, &embedding);
+        _MatrixMul(&input, X_NOTRANS, &w, X_NOTRANS, &embedding);
 
         eList.Add(&net.embeddings[i]);
     }
@@ -681,7 +681,7 @@ void Forward(XTensor inputs[], XTensor &output, FNNModel &model, FNNNet &net)
     /* concatenate word embeddings
        embeddingcat = cat(embedding_0...embedding_{n-1}) */
     InitModelTensor2D(net.embeddingCat, batchSize, (n - 1) * model.eSize, model);
-    Concatenate(&eList, &net.embeddingCat, 1);
+    _Concatenate(&eList, &net.embeddingCat, 1);
 
     /* go over each hidden layer */
     for(int i = 0; i < depth; i++){
@@ -696,12 +696,12 @@ void Forward(XTensor inputs[], XTensor &output, FNNModel &model, FNNNet &net)
 
         /* generate hidden states of layer i: 
            s = h_pre * w    */
-        MatrixMul(&h_pre, X_NOTRANS, &w, X_NOTRANS, &s);
+        _MatrixMul(&h_pre, X_NOTRANS, &w, X_NOTRANS, &s);
 
         /* make a 2d tensor for the bias term */
         XTensor b2D;
         InitTensor(&b2D, &s);
-        Unsqueeze(&b, &b2D, 0, batchSize);
+        _Unsqueeze(&b, &b2D, 0, batchSize);
 
         /* introduce bias term:
            s = s + b
@@ -711,7 +711,7 @@ void Forward(XTensor inputs[], XTensor &output, FNNModel &model, FNNNet &net)
 
         /* pass the state through the hard tanh function:
            h = tanh(s) */
-        HardTanH(&s, &h);
+        _HardTanH(&s, &h);
     }
 
     /* generate the output Pr(w_{n-1}|w_0...w_{n-2}):
@@ -729,16 +729,16 @@ void Forward(XTensor inputs[], XTensor &output, FNNModel &model, FNNNet &net)
         InitModelTensor2D(y, batchSize, model.vSize, model);
 
         /* s = h_last * w  */
-        MatrixMul(&h_last, X_NOTRANS, &w, X_NOTRANS, &s);
+        _MatrixMul(&h_last, X_NOTRANS, &w, X_NOTRANS, &s);
 
         XTensor b2D;
         InitTensor(&b2D, &s);
-        Unsqueeze(&b, &b2D, 0, batchSize);
+        _Unsqueeze(&b, &b2D, 0, batchSize);
 
         _Sum(&s, &b2D, &s);
 
         /* y = softmax(s) */
-        LogSoftmax(&s, &y, 1);
+        _LogSoftmax(&s, &y, 1);
     }
     
     
@@ -782,18 +782,18 @@ void Backward(XTensor inputs[], XTensor &output, XTensor &gold, LOSS_FUNCTION_NA
         x is the top most hidden layer)
        so we know 
        dE/dw = x^T * dE/ds */
-    MatrixMul(&x, X_TRANS, &deds, X_NOTRANS, &dedw);
+    _MatrixMul(&x, X_TRANS, &deds, X_NOTRANS, &dedw);
 
     /* gradient of the bias: dE/db = dE/ds * 1 = dE/ds
     specifically dE/db_{j} = \sum_{i} dE/ds_{i,j} */
-    ReduceSum(&deds, &dedb, 0);
+    _ReduceSum(&deds, &dedb, 0);
 
     /* then, we compute 
        dE/dx_{j} = \sum_j' (dE/ds_{j'} * ds_{j'}/dx_j) 
                  = \sum_j' (dE/ds_{j'} * w_{j, j'})
        i.e., 
        dE/dx = dE/ds * w^T */
-    MatrixMul(&deds, X_NOTRANS, &w, X_TRANS, &dedx);
+    _MatrixMul(&deds, X_NOTRANS, &w, X_TRANS, &dedx);
 
     XTensor &gradPassed = dedx;
     XTensor dedsHidden;
@@ -821,17 +821,17 @@ void Backward(XTensor inputs[], XTensor &output, XTensor &gold, LOSS_FUNCTION_NA
         HardTanHBackward(NULL, &h, &s, &dedh, &deds, NOLOSS);
 
         /* gradient of the weight: dE/dw = x^T * dE/ds   */
-        MatrixMul(&x, X_TRANS, &deds, X_NOTRANS, &dedw);
+        _MatrixMul(&x, X_TRANS, &deds, X_NOTRANS, &dedw);
 
         /* gradient of the bias: dE/db = dE/ds * 1 = dE/ds
            specifically dE/db_{j} = \sum_{i} dE/ds_{i,j} */
-        ReduceSum(&deds, &dedb, 0);
+        _ReduceSum(&deds, &dedb, 0);
 
         /* gradient of the input: dE/dx = dE/ds * w^T    */
-        MatrixMul(&deds, X_NOTRANS, &w, X_TRANS, &dedx);
+        _MatrixMul(&deds, X_NOTRANS, &w, X_TRANS, &dedx);
 
         if (i > 0)
-            CopyValues(&dedx, &gradPassed);
+            _CopyValues(&dedx, &gradPassed);
     }
 
     XList eList(n - 1);
@@ -846,7 +846,7 @@ void Backward(XTensor inputs[], XTensor &output, XTensor &gold, LOSS_FUNCTION_NA
     XTensor &dedyCat = depth > 0 ? dedxBottom : dedx;
 
     /* split the concatenation of gradients of the embeddings */
-    Split(&dedyCat, &eList, 1, n - 1);
+    _Split(&dedyCat, &eList, 1, n - 1);
 
     /* go over for each word */
     for (int i = 0; i < n - 1; i++) {
@@ -857,7 +857,7 @@ void Backward(XTensor inputs[], XTensor &output, XTensor &gold, LOSS_FUNCTION_NA
         /* gradient of the embedding weight: dE/dw += x^T * dE/dy 
            NOTE that we accumulate dE/dw here because the matrix w
            is shared by several layers (or words) */
-        MatrixMul(&x, X_TRANS, dedy, X_NOTRANS, &dedw, 1.0F, 1.0F);
+        _MatrixMul(&x, X_TRANS, dedy, X_NOTRANS, &dedw, 1.0F, 1.0F);
 
         delete dedy;
     }