bug fixes of transformer

source/sample/transformer/T2TAttention.cpp

@@ -57,9 +57,9 @@ void T2TAttention::InitModel(int argc, const char ** argv, int myDevID, XMem * m
     float minmax = 0;
 
     LoadParamInt(argc, argv, "nhead", &nhead, 8);
-    LoadParamInt(argc, argv, "d", &dk, DEFAULT_BEDDING_SIZE);
-    LoadParamInt(argc, argv, "d", &dv, DEFAULT_BEDDING_SIZE);
-    LoadParamInt(argc, argv, "d", &d, DEFAULT_BEDDING_SIZE);
+    LoadParamInt(argc, argv, "d", &dk, DEFAULT_EMBEDDING_SIZE);
+    LoadParamInt(argc, argv, "d", &dv, DEFAULT_EMBEDDING_SIZE);
+    LoadParamInt(argc, argv, "d", &d, DEFAULT_EMBEDDING_SIZE);
     LoadParamFloat(argc, argv, "attminmax", &minmax, 0.1F);
 
     InitTensor2D(&wk, d, dk, X_FLOAT, devID, mem);

source/sample/transformer/T2TEmbedding.cpp

@@ -53,12 +53,10 @@ void T2TEmbedder::InitModel(int argc, const char ** argv, int myDevID, XMem * my
     devID = myDevID;
     mem = myMem;
     
-    int d = 0;
-
     LoadParamInt(argc, argv, "vsize", &vSize, -1);
-    LoadParamInt(argc, argv, "maxlen", &maxLength, 256);
-    LoadParamInt(argc, argv, "d", &eSize, DEFAULT_BEDDING_SIZE);
-    LoadParamInt(argc, argv, "d", &d, DEFAULT_BEDDING_SIZE);
+    LoadParamInt(argc, argv, "maxlen", &maxLength, 512);
+    LoadParamInt(argc, argv, "d", &eSize, DEFAULT_EMBEDDING_SIZE);
+    LoadParamInt(argc, argv, "d", &d, DEFAULT_EMBEDDING_SIZE);
 
     InitTensor2D(&w, vSize, eSize, X_FLOAT, devID, mem);
 
@@ -135,10 +133,10 @@ XTensor T2TEmbedder::Make(XTensor &input)
     XTensor wordEmbedding;
 
     /* then we make word embeddings */
-    wordEmbedding = MMul(input, w);
+    wordEmbedding = Linear(MMul(input, w), (float)sqrt((float)d));
 
     /* we sum over the two embeddings */
-    return wordEmbedding + posEmbedding;
+    return wordEmbedding +posEmbedding;
 }
 
 }

source/sample/transformer/T2TEmbedding.h

@@ -29,7 +29,7 @@ using namespace nts;
 namespace transformer
 {
 
-#define DEFAULT_BEDDING_SIZE 512
+#define DEFAULT_EMBEDDING_SIZE 512
 
 /* 
 embedding (of word at position i):
@@ -53,6 +53,9 @@ public:
     /* maximum length of the sequence */
     int maxLength;
 
+    /* dimension size of the hidden layers in the t2t model */
+    int d;
+
     /* word embedding matrix */
     XTensor w;
 

source/sample/transformer/T2TEncoder.cpp

@@ -38,7 +38,8 @@ AttEncoder::~AttEncoder()
 {
     delete[] attentions;
     delete[] fnns;
-    delete[] layerNorms;
+    delete[] attLayerNorms;
+    delete[] fnnLayerNorms;
 }
 
 /* 
@@ -54,11 +55,10 @@ void AttEncoder::InitModel(int argc, const char ** argv, int myDevID, XMem * myM
     mem = myMem;
     
     LoadParamInt(argc, argv, "nlayer", &nlayer, 6);
-    LoadParamInt(argc, argv, "hsize", &hSize, 512);
-    LoadParamInt(argc, argv, "esize", &eSize, 512);
+    LoadParamInt(argc, argv, "hsize", &hSize, DEFAULT_EMBEDDING_SIZE);
+    LoadParamInt(argc, argv, "esize", &eSize, DEFAULT_EMBEDDING_SIZE);
     LoadParamInt(argc, argv, "vsize", &vSize, -1);
 
-
     CheckNTErrors(nlayer >= 1, "We have one encoding layer at least!");
     CheckNTErrors(vSize > 1, "set vocabulary size by \"-vsize\"");
 
@@ -67,13 +67,15 @@ void AttEncoder::InitModel(int argc, const char ** argv, int myDevID, XMem * myM
 
     attentions = new T2TAttention[nlayer];
     fnns = new T2TFNN[nlayer];
-    layerNorms = new T2TLN[nlayer];
+    attLayerNorms = new T2TLN[nlayer];
+    fnnLayerNorms = new T2TLN[nlayer];
 
     /* initialize the stacked layers */
     for(int i = 0; i < nlayer; i++){
         attentions[i].InitModel(argc, argv, myDevID, myMem);
         fnns[i].InitModel(argc, argv, myDevID, myMem);
-        layerNorms[i].InitModel(argc, argv, myDevID, myMem);
+        attLayerNorms[i].InitModel(argc, argv, myDevID, myMem);
+        fnnLayerNorms[i].InitModel(argc, argv, myDevID, myMem);
     }
 }
 
@@ -103,7 +105,7 @@ XTensor AttEncoder::Make(XTensor &input)
         /* TODO: dropout */
 
         /* layer normalization */
-        x = layerNorms[i].Make(res);
+        x = attLayerNorms[i].Make(res);
 
         /* fnn */
         fnn = fnns[i].Make(x);
@@ -114,7 +116,7 @@ XTensor AttEncoder::Make(XTensor &input)
         /* TODO: dropout */
 
         /* layer normalization */
-        x = layerNorms[i].Make(res);
+        x = fnnLayerNorms[i].Make(res);
     }
 
     return x;

source/sample/transformer/T2TEncoder.h

@@ -86,8 +86,11 @@ public:
     /* attention model of each layer */
     T2TAttention * attentions;
 
-    /* layer normalization */
-    T2TLN * layerNorms;
+    /* layer normalization for fnn */
+    T2TLN * fnnLayerNorms;
+
+    /* layer normalization for attention */
+    T2TLN * attLayerNorms;
 
     /* input tensor of the encoder */
     XTensor * input;

source/sample/transformer/T2TFNN.cpp

@@ -56,9 +56,9 @@ void T2TFNN::InitModel(int argc, const char ** argv, int myDevID, XMem * myMem)
     
     float minmax = 0;
 
-    LoadParamInt(argc, argv, "d", &inSize, DEFAULT_BEDDING_SIZE);
-    LoadParamInt(argc, argv, "d", &outSize, DEFAULT_BEDDING_SIZE);
-    LoadParamInt(argc, argv, "fnnh", &hSize, DEFAULT_BEDDING_SIZE);
+    LoadParamInt(argc, argv, "d", &inSize, DEFAULT_EMBEDDING_SIZE);
+    LoadParamInt(argc, argv, "d", &outSize, DEFAULT_EMBEDDING_SIZE);
+    LoadParamInt(argc, argv, "fnnh", &hSize, DEFAULT_EMBEDDING_SIZE);
     LoadParamFloat(argc, argv, "fnnminmax", &minmax, 0.1F);
 
     InitTensor2D(&w1, inSize, hSize, X_FLOAT, devID, mem);

source/sample/transformer/T2TLayerNormal.cpp

@@ -20,6 +20,8 @@
  */
 
 #include "T2TLayerNormal.h"
+#include "T2TUtility.h"
+#include "T2TEmbedding.h"
 #include "../../tensor/core/CHeader.h"
 
 namespace transformer
@@ -48,6 +50,18 @@ void T2TLN::InitModel(int argc, const char ** argv, int myDevID, XMem * myMem)
 {
     devID = myDevID;
     mem = myMem;
+
+    int d = 0;
+    LoadParamInt(argc, argv, "d", &d, DEFAULT_EMBEDDING_SIZE);
+
+    InitTensor2D(&w, d, d, X_FLOAT, devID, mem);
+    InitTensor1D(&b, d, X_FLOAT, devID, mem);
+
+    float scale = 1.0F;
+    float finfout = (float)sqrt(6.0F * scale / (d + d));
+
+    w.SetDataRand(-finfout, finfout);
+    b.SetZeroAll();
 }
     
 /*
@@ -60,6 +74,7 @@ y =
 XTensor T2TLN::Make(XTensor &input)
 {
     XTensor &x = input;
+    XTensor xn;
     XTensor mean;
     XTensor variance;
     XTensor standard;
@@ -67,7 +82,7 @@ XTensor T2TLN::Make(XTensor &input)
     XTensor standardFilled;
 
     /* \mu = (sum_i x_i)/m */
-    mean = ReduceSum(x, x.order - 1);
+    mean = ReduceMean(x, x.order - 1);
 
     /* \sigma = (sum_i (x_i - \mu)^2)/m */
     variance = ReduceVariance(x, x.order - 1, mean);
@@ -81,7 +96,10 @@ XTensor T2TLN::Make(XTensor &input)
     standardFilled = Unsqueeze(standard, x.order - 1, x.GetDim(-1));
 
     /* x' = (x - \mu)/standard */
-    return (x - meanFilled)/standardFilled;
+    xn = (x - meanFilled)/standardFilled ;
+
+    /* result = x' * w + b   */
+    return MMul(xn, w) + b;
 }
 
 }

source/sample/transformer/T2TLayerNormal.h

@@ -29,6 +29,8 @@ using namespace nts;
 namespace transformer
 {
 
+/* layer normalization: y = norm(x) * w + b 
+   where norm(x) = (x - mean)/standardDeviation */
 class T2TLN
 {
 public:
@@ -37,6 +39,12 @@ public:
     
     /* memory pool */
     XMem * mem;
+
+    /* the transformation matrix w */
+    XTensor w;
+
+    /* the bias term b */
+    XTensor b;
     
 public:
     /* constructor */

source/sample/transformer/T2TOutput.cpp

@@ -57,8 +57,8 @@ void T2TOutput::InitModel(int argc, const char ** argv, int myDevID, XMem * myMe
     float minmax = 0;
 
     LoadParamInt(argc, argv, "vsize", &vSize, -1);
-    LoadParamInt(argc, argv, "d", &inSize, DEFAULT_BEDDING_SIZE);
-    LoadParamInt(argc, argv, "d", &hSize, DEFAULT_BEDDING_SIZE);
+    LoadParamInt(argc, argv, "d", &inSize, DEFAULT_EMBEDDING_SIZE);
+    LoadParamInt(argc, argv, "d", &hSize, DEFAULT_EMBEDDING_SIZE);
     LoadParamFloat(argc, argv, "outputminmax", &minmax, 0.08F);
 
     InitTensor2D(&w, hSize, vSize, X_FLOAT, devID, mem);

source/sample/transformer/T2TTrainer.cpp

@@ -113,7 +113,7 @@ void T2TTrainer::Train(const char * fn, T2TModel * model)
             
             /* learning rate */
             lr = (1 / (float)sqrt((float)d)) * (float)MIN(pow(step + 1, -0.5), (step + 1) * pow(nwarmup, -1.5));
-            lr = 0.000002F;
+            //lr = 0.00005F;
             
             /* update the parameters */
             Update(model, lr);
@@ -138,6 +138,9 @@ void T2TTrainer::Train(const char * fn, T2TModel * model)
         }
         
         fclose(file);
+
+        if (isEnd)
+            break;
     }
     
     double elapsed = GetClockSec() - startT;
@@ -345,6 +348,10 @@ void T2TTrainer::Update(T2TModel * model, const float lr)
         ws.Add(&model->encoder.attentions[i].wk);
         ws.Add(&model->encoder.attentions[i].wq);
         ws.Add(&model->encoder.attentions[i].wv);
+        ws.Add(&model->encoder.fnnLayerNorms[i].w);
+        ws.Add(&model->encoder.fnnLayerNorms[i].b);
+        ws.Add(&model->encoder.attLayerNorms[i].w);
+        ws.Add(&model->encoder.attLayerNorms[i].b);
     }
 
     ws.Add(&model->encoder.embedder.w);
@@ -353,11 +360,37 @@ void T2TTrainer::Update(T2TModel * model, const float lr)
         XTensor * para = (XTensor*)ws.Get(i);
         XTensor * paraGrad = para->grad;
 
+        if (para == NULL || paraGrad == NULL)
+            continue;
+
         CheckNTErrors(para != NULL, "NULL parameter tensor!");
         CheckNTErrors(paraGrad != NULL, "NULL gradient tensor!");
 
+        /*
+        DTYPE * d = new DTYPE[para->unitNum * para->unitSize];
+        DTYPE * g = new DTYPE[para->unitNum * para->unitSize];
+
+        XMemCopy(d, -1, para->data, para->devID, para->unitNum * para->unitSize);
+        XMemCopy(g, -1, paraGrad->data, paraGrad->devID, para->unitNum * para->unitSize);
+
+        for (int i = 0; i < para->unitNum; i++) {
+            if (IsNAN(d[i]) || IsINF(d[i])) {
+                int nnn = 0;
+            }
+            if (IsNAN(g[i]) || IsINF(g[i])) {
+                int nnn = 0;
+            }
+        }
+
+        delete[] d;
+        delete[] g;
+        */
+
         /* the delta rule */
         _Sum(para, paraGrad, para, -lr);
+
+        /* clear gradient */
+        paraGrad->SetZeroAll();
     }
 }
 

source/sample/transformer/T2TUtility.cpp

@@ -26,6 +26,8 @@
 namespace transformer
 {
 
+FILE * tmpFILE;
+
 void LoadParamString(int argc, const char ** argv, const char * name, char * p, const char * defaultP)
 {
     char vname[128];

source/sample/transformer/T2TUtility.h

@@ -27,6 +27,8 @@
 namespace transformer
 {
 
+extern FILE * tmpFILE;
+
 /* load arguments */
 void LoadParamString(int argc, const char ** argv, const char * name, char * p, const char * defaultP);
 void LoadParamInt(int argc, const char ** argv, const char * name, int * p, int defaultP);

source/sample/transformer/Transformer.cpp

@@ -33,6 +33,8 @@ int TransformerMain(int argc, const char ** argv)
     if(argc == 0)
         return 1;
 
+    tmpFILE = fopen("tmp.txt", "wb");
+
     ShowParams(argc, argv);
 
     char * trainFN = new char[MAX_LINE_LENGTH];
@@ -51,6 +53,8 @@ int TransformerMain(int argc, const char ** argv)
 
     delete[] trainFN;
 
+    fclose(tmpFILE);
+
     return 0;
 }