Merge pull request #5084 from lcy-seso/crf

Add the LinearChainCrf operator.

Author: lcy-seso

paddle/framework/operator.cc

@@ -37,32 +37,32 @@ ExecutionContext::GetEigenDevice<platform::GPUPlace, Eigen::GpuDevice>() const {
 std::string OperatorBase::Input(const std::string& name) const {
   auto& ins = Inputs(name);
   PADDLE_ENFORCE_LE(ins.size(), 1UL,
-                    "Op %s input %s should contain only one variable", type_,
-                    name);
+                    "Operator %s's input %s should contain only one variable.",
+                    type_, name);
   return ins.empty() ? kEmptyVarName : ins[0];
 }
 
 const std::vector<std::string>& OperatorBase::Inputs(
     const std::string& name) const {
   auto it = inputs_.find(name);
-  PADDLE_ENFORCE(it != inputs_.end(), "Op %s do not have input %s", type_,
-                 name);
+  PADDLE_ENFORCE(it != inputs_.end(), "Operator %s does not have the input %s.",
+                 type_, name);
   return it->second;
 }
 
 std::string OperatorBase::Output(const std::string& name) const {
   auto& outs = Outputs(name);
   PADDLE_ENFORCE_LE(outs.size(), 1UL,
-                    "Op %s output %s should contain only one variable", type_,
-                    name);
+                    "Operator %s's output %s should contain only one variable.",
+                    type_, name);
   return outs.empty() ? kEmptyVarName : outs[0];
 }
 
 const std::vector<std::string>& OperatorBase::Outputs(
     const std::string& name) const {
   auto it = outputs_.find(name);
-  PADDLE_ENFORCE(it != outputs_.end(), "Op %s does not have output called %s",
-                 type_, name);
+  PADDLE_ENFORCE(it != outputs_.end(),
+                 "Operator %s does not have an output called %s.", type_, name);
   return it->second;
 }
 

paddle/framework/operator.h

@@ -427,7 +427,8 @@ class OperatorWithKernel : public OperatorBase {
             int tmp = static_cast<int>(ToDataType(t->type()));
             VLOG(3) << "Input " << ipt_name << " with data_type " << tmp;
             PADDLE_ENFORCE(tmp == data_type || data_type == -1,
-                           "DataType of Paddle Op %s must be same.", Type());
+                           "DataType of Paddle Op %s must be the same.",
+                           Type());
             data_type = tmp;
           }
         }

paddle/framework/tensor.h

@@ -118,10 +118,12 @@ class Tensor {
                              const platform::DeviceContext& ctx);
 
   /**
-   * @brief   Return the slice of the tensor.
+   * @brief  Return a sub-tensor of the given tensor.
    *
-   * @param[in] begin_idx   The begin index of the slice.
-   * @param[in] end_idx     The end index of the slice.
+   * @param[in] begin_idx   The index of the start row(inclusive) to slice.
+   *                        The index number begins from 0.
+   * @param[in] end_idx     The index of the end row(exclusive) to slice.
+   *                        The index number begins from 0.
    */
   inline Tensor Slice(const int& begin_idx, const int& end_idx) const;
 

paddle/framework/tensor_impl.h

@@ -112,9 +112,10 @@ inline void* Tensor::mutable_data(platform::Place place, std::type_index type) {
   if (holder_ != nullptr) {
     holder_->set_type(type);
   }
-  PADDLE_ENFORCE_GT(numel(), 0,
-                    "Tensor's numel must be larger than zero to call "
-                    "Tensor::mutable_data. Call Tensor::set_dim first.");
+  PADDLE_ENFORCE_GT(
+      numel(), 0,
+      "When calling this method, the Tensor's numel must be larger than zero. "
+      "Please check Tensor::Resize has been called first.");
   int64_t size = numel() * SizeOfType(type);
   /* some versions of boost::variant don't have operator!= */
   if (holder_ == nullptr || !(holder_->place() == place) ||
@@ -229,10 +230,12 @@ inline void Tensor::CopyFromVector(const std::vector<T>& src,
 
 inline Tensor Tensor::Slice(const int& begin_idx, const int& end_idx) const {
   check_memory_size();
-  PADDLE_ENFORCE_GE(begin_idx, 0, "Slice begin index is less than zero.");
-  PADDLE_ENFORCE_LE(end_idx, dims_[0], "Slice end index is out of bound.");
-  PADDLE_ENFORCE_LT(begin_idx, end_idx,
-                    "Begin index must be less than end index.");
+  PADDLE_ENFORCE_GE(begin_idx, 0,
+                    "The start row index must be greater than 0.");
+  PADDLE_ENFORCE_LE(end_idx, dims_[0], "The end row index is out of bound.");
+  PADDLE_ENFORCE_LT(
+      begin_idx, end_idx,
+      "The start row index must be lesser than the end row index.");
 
   if (dims_[0] == 1) {
     return *this;

paddle/gserver/layers/CRFLayer.cpp

@@ -101,8 +101,10 @@ void CRFLayer::backward(const UpdateCallback& callback) {
                               : real(1.0f);
     instanceWeight *= coeff_;
 
-    MatrixPtr grad = output.grad->subRowMatrix(starts[i], starts[i + 1]);
-    grad->add(*crfs_[i].getXGrad(), real(1.0f), instanceWeight);
+    if (output.grad) {
+      MatrixPtr grad = output.grad->subRowMatrix(starts[i], starts[i + 1]);
+      grad->add(*crfs_[i].getXGrad(), real(1.0f), instanceWeight);
+    }
     if (needWGrad) {
       weight_->getWGrad()->add(
           *crfs_[i].getWGrad(), real(1.0f), instanceWeight);

paddle/gserver/layers/LinearChainCRF.cpp

@@ -102,7 +102,6 @@ real LinearChainCRF::forward(real* x, int* s, int length) {
 }
 
 void LinearChainCRF::backward(real* x, int* s, int length, bool needWGrad) {
-  MatrixPtr matX = Matrix::create(x, length, numClasses_);
   Matrix::resizeOrCreate(matGrad_, length, numClasses_);
   Matrix::resizeOrCreate(beta_, length, numClasses_);
   real* b = b_->getData();

paddle/operators/cross_entropy_op.cc

@@ -28,8 +28,9 @@ class CrossEntropyOp : public framework::OperatorWithKernel {
 
     auto x_dims = ctx->GetInputDim("X");
     auto label_dims = ctx->GetInputDim("Label");
-    PADDLE_ENFORCE_EQ(x_dims.size(), 2, "Input(X)'s rank should be 2.");
-    PADDLE_ENFORCE_EQ(label_dims.size(), 2, "Input(Label)'s rank should be 2.");
+    PADDLE_ENFORCE_EQ(x_dims.size(), 2UL, "Input(X)'s rank should be 2.");
+    PADDLE_ENFORCE_EQ(label_dims.size(), 2UL,
+                      "Input(Label)'s rank should be 2.");
     PADDLE_ENFORCE_EQ(x_dims[0], label_dims[0],
                       "The 1st dimension of Input(X) and Input(Label) should "
                       "be equal.");
@@ -38,8 +39,8 @@ class CrossEntropyOp : public framework::OperatorWithKernel {
                         "If Attr(soft_label) == true, the 2nd dimension of "
                         "Input(X) and Input(Label) should be equal.");
     } else {
-      PADDLE_ENFORCE_EQ(label_dims[1], 1,
-                        "If Attr(soft_label) == false, the 2nd dimension of "
+      PADDLE_ENFORCE_EQ(label_dims[1], 1UL,
+                        "If Attr(softLabel) == false, the 2nd dimension of "
                         "Input(Label) should be 1.");
     }
 
@@ -48,7 +49,8 @@ class CrossEntropyOp : public framework::OperatorWithKernel {
   }
 
  protected:
-  // CrossEntropy's data type just determined by "X"
+  // Explicitly set that data type of the output of the cross_entropy operator
+  // is determined by its input "X".
   framework::DataType IndicateDataType(
       const framework::ExecutionContext& ctx) const override {
     return framework::ToDataType(ctx.Input<Tensor>("X")->type());