softmax output -> logsoftmax output

source/sample/transformer/T2TOutput.cpp

@@ -93,8 +93,8 @@ void T2TOutput::Make(XTensor &input, XTensor &output)
 {
     XTensor &x = input;
 
-    //output = LogSoftmax(MMul(x, w), -1);
-    output = Softmax(MMul(x, w), -1);
+    output = LogSoftmax(MMul(x, w), -1);
+    //output = Softmax(MMul(x, w), -1);
 }
 
 }

source/sample/transformer/T2TTrainer.cpp

@@ -218,8 +218,8 @@ void T2TTrainer::Train(const char * fn, const char * validFN, const char * model
                 LabelSmooth(&gold, &goldSmoothed, labelSmoothingP);
 
             /* make paddings for the output */
-            //if (output.GetDim(0) > 1)
-            //    PadOutput(&output, &gold, &paddingDec);
+            if (output.GetDim(0) > 1)
+                PadOutput(&output, &gold, &paddingDec);
 
             /* get probabilities */
             float prob = GetProb(&output, &gold, NULL);
@@ -232,7 +232,7 @@ void T2TTrainer::Train(const char * fn, const char * validFN, const char * model
             if (doUpdate) {
                 
                 /* recale the output for normalized loss */
-                //RescaleOutput(&output, &g, &paddingDec);
+                RescaleOutput(&output, &g, &paddingDec);
                 
                 /* back-propagation */
                 net.Backward(output, g, paddingDec, CROSSENTROPY);
@@ -977,12 +977,12 @@ float T2TTrainer::GetProb(XTensor * output, XTensor * gold, XTensor * wordProbs)
     XTensor probs;
     InitTensor(&probs, output);
     
-    XTensor logOutput;
+    /*XTensor logOutput;
     InitTensor(&logOutput, output);
-    _Log(output, &logOutput);
+    _Log(output, &logOutput);*/
 
     /* probs[i,j] = output[i,j] * gold[i,j] */
-    _Multiply(&logOutput, gold, &probs);
+    _Multiply(output, gold, &probs);
     
     /* probability of each word */
     XTensor wprobs;