diff --git a/paddle/framework/backward.cc b/paddle/framework/backward.cc
index b9018ecdba8303fd6b37c87edd99e192aa604228..bc0da55cdae3575414e0d9b36471056c20946489 100644
--- a/paddle/framework/backward.cc
+++ b/paddle/framework/backward.cc
@@ -522,7 +522,7 @@ ParamGradInfoMap AppendBackward(
       new OpDescBind("fill_constant", {}, {{"Out", {fill_one_op_out}}},
                      {{"shape", std::vector<int>{1}},
                       {"value", static_cast<float>(1.0)},
-                      {"data_type", target.GetDataType()}}));
+                      {"dtype", target.GetDataType()}}));
   // infer var type of fill_one_op
   fill_one_op->InferVarType(root_block);
 
diff --git a/paddle/framework/tensor_array.cc b/paddle/framework/tensor_array.cc
index 0947e33548130a923e998f8bad68db00097af909..6058f1b8b1f78181bc4a47e9e3d4135f5139980f 100644
--- a/paddle/framework/tensor_array.cc
+++ b/paddle/framework/tensor_array.cc
@@ -302,7 +302,7 @@ LoDTensor TensorArray::Stack() const {
 
   const auto& first_dims = values_.front().dims();
   // check all the values have the same shape
-  // TODO(superjom) check the same dtypes
+  // TODO(superjom) check the same data_type
   for (size_t idx = 1; idx < size(); idx++) {
     const auto& value_dims = values_[idx].dims();
     PADDLE_ENFORCE_EQ(first_dims, value_dims);
diff --git a/paddle/operators/cast_op.cc b/paddle/operators/cast_op.cc
index 70ee7861bab3a982eae60dd85b10c2e41f5827d0..3082a53ccfbe4f8666cfdfc2efed6b46ffdfede9 100644
--- a/paddle/operators/cast_op.cc
+++ b/paddle/operators/cast_op.cc
@@ -25,8 +25,8 @@ class CastOpProtoMaker : public framework::OpProtoAndCheckerMaker {
       : OpProtoAndCheckerMaker(proto, op_checker) {
     AddInput("X", "The input tensor of cast op");
     AddOutput("Out", "The output tensor of cast op");
-    AddAttr<int>("out_data_type", "output data type");
-    AddAttr<int>("in_data_type", "input data type");
+    AddAttr<int>("out_dtype", "output data type");
+    AddAttr<int>("in_dtype", "input data type");
     AddComment(R"DOC(
 Cast Operator.
 
@@ -58,8 +58,8 @@ class CastOpGradMaker : public framework::SingleGradOpDescMaker {
     grad->SetType("cast");
     grad->SetInput("X", OutputGrad("Out"));
     grad->SetOutput("Out", InputGrad("X"));
-    grad->SetAttr("out_data_type", GetAttr("in_data_type"));
-    grad->SetAttr("in_data_type", GetAttr("out_data_type"));
+    grad->SetAttr("out_dtype", GetAttr("in_dtype"));
+    grad->SetAttr("in_dtype", GetAttr("out_dtype"));
     return std::unique_ptr<framework::OpDescBind>(grad);
   }
 };
diff --git a/paddle/operators/cast_op.h b/paddle/operators/cast_op.h
index ffdbff7030afedab2efc06479ac86ad70c185f48..850dc8e3498351e54d41fcd2b6596c6fe668df14 100644
--- a/paddle/operators/cast_op.h
+++ b/paddle/operators/cast_op.h
@@ -55,7 +55,7 @@ class CastOpKernel : public framework::OpKernel<InT> {
     auto* in = context.Input<framework::Tensor>("X");
     auto* out = context.Output<framework::Tensor>("Out");
     framework::VisitDataType(
-        static_cast<framework::DataType>(context.Attr<int>("out_data_type")),
+        static_cast<framework::DataType>(context.Attr<int>("out_dtype")),
         CastOpFunctor<Place, InT>(in, out, context.device_context()));
   }
 };
diff --git a/paddle/operators/fill_constant_batch_size_like_op.cc b/paddle/operators/fill_constant_batch_size_like_op.cc
index 985b5d1e865e513d833bff72dcd20a8f20851d8c..892922cd3aaec8bf8194320c5c3a0dd0365bb589 100644
--- a/paddle/operators/fill_constant_batch_size_like_op.cc
+++ b/paddle/operators/fill_constant_batch_size_like_op.cc
@@ -52,7 +52,7 @@ class FillConstantBatchSizeLikeOp : public framework::OperatorWithKernel {
   framework::OpKernelType GetKernelType(
       const framework::ExecutionContext &ctx) const override {
     return framework::OpKernelType(
-        static_cast<framework::DataType>(ctx.Attr<int>("data_type")),
+        static_cast<framework::DataType>(ctx.Attr<int>("dtype")),
         ctx.device_context());
   }
 };
@@ -63,7 +63,7 @@ class FillConstantBatchSizeLikeOpMaker
   FillConstantBatchSizeLikeOpMaker(framework::OpProto *proto,
                                    framework::OpAttrChecker *op_checker)
       : framework::OpProtoAndCheckerMaker(proto, op_checker) {
-    AddAttr<int>("data_type",
+    AddAttr<int>("dtype",
                  "(int, default 5 (FP32)) "
                  "Output data type")
         .SetDefault(framework::DataType::FP32);
diff --git a/paddle/operators/fill_constant_op.cc b/paddle/operators/fill_constant_op.cc
index 818f113b90a4c239a857791fb9957e51d3287b97..3d5f84bc239615797a5cf01a74150fdb7dfc1b80 100644
--- a/paddle/operators/fill_constant_op.cc
+++ b/paddle/operators/fill_constant_op.cc
@@ -34,7 +34,7 @@ class FillConstantOp : public framework::OperatorBase {
   using framework::OperatorBase::OperatorBase;
   void Run(const framework::Scope &scope,
            const platform::DeviceContext &dev_ctx) const override {
-    auto data_type = static_cast<framework::DataType>(Attr<int>("data_type"));
+    auto data_type = static_cast<framework::DataType>(Attr<int>("dtype"));
     auto value = Attr<float>("value");
     auto force_cpu = Attr<bool>("force_cpu");
     auto &out =
@@ -55,7 +55,7 @@ class FillConstantOpMaker : public framework::OpProtoAndCheckerMaker {
   FillConstantOpMaker(framework::OpProto *proto,
                       framework::OpAttrChecker *op_checker)
       : framework::OpProtoAndCheckerMaker(proto, op_checker) {
-    AddAttr<int>("data_type",
+    AddAttr<int>("dtype",
                  "(int, default 5 (FP32)) "
                  "Output data type")
         .SetDefault(framework::DataType::FP32);
diff --git a/paddle/operators/gaussian_random_op.cc b/paddle/operators/gaussian_random_op.cc
index 53ad86c6c48d1868f4495af51661d91b39a84f0b..254c83e1378a121d99c89d9d8705935b5f06edc8 100644
--- a/paddle/operators/gaussian_random_op.cc
+++ b/paddle/operators/gaussian_random_op.cc
@@ -60,7 +60,7 @@ class GaussianRandomOp : public framework::OperatorWithKernel {
   framework::OpKernelType GetKernelType(
       const framework::ExecutionContext& ctx) const override {
     return framework::OpKernelType(
-        static_cast<framework::DataType>(ctx.Attr<int>("data_type")),
+        static_cast<framework::DataType>(ctx.Attr<int>("dtype")),
         ctx.device_context());
   }
 };
@@ -88,7 +88,7 @@ class GaussianRandomOpMaker : public framework::OpProtoAndCheckerMaker {
                  "Random seed of generator."
                  "0 means use system wide seed.")
         .SetDefault(0);
-    AddAttr<int>("data_type",
+    AddAttr<int>("dtype",
                  "(int, default 5(FP32)) "
                  "Output data type.")
         .SetDefault(framework::DataType::FP32);
diff --git a/paddle/operators/nccl_op.cc b/paddle/operators/nccl_op.cc
index 66fcc09bc877867e66a37adc73230d8dabf4cbed..22a37ff1bbf6b8cfb2cbc3c3dbbb20a87c5ea4e7 100644
--- a/paddle/operators/nccl_op.cc
+++ b/paddle/operators/nccl_op.cc
@@ -49,7 +49,7 @@ class NCCLInitOpMaker : public framework::OpProtoAndCheckerMaker {
     AddOutput("Communicator",
               "Create Communicator for communicating between gpus");
     AddAttr<std::vector<int>>("gpus", "(vector<int>) GPU id lists");
-    AddAttr<int>("data_type",
+    AddAttr<int>("dtype",
                  "(int, default 5 (FP32)) "
                  "Output data type")
         .SetDefault(framework::DataType::FP32);
diff --git a/paddle/operators/recurrent_op.cc b/paddle/operators/recurrent_op.cc
index 0075ccd24271bf83f139e121efad00c2316cc11b..ea60665e398978c612321df1f340e5669038e28f 100644
--- a/paddle/operators/recurrent_op.cc
+++ b/paddle/operators/recurrent_op.cc
@@ -401,7 +401,7 @@ class RecurrentGradOp : public RecurrentBase {
             auto &inside_tensor = cur_scope.FindVar(inside_grad_name)
                                       ->Get<framework::LoDTensor>();
             framework::AttributeMap attrs;
-            attrs["data_type"] = framework::ToDataType(inside_tensor.type());
+            attrs["dtype"] = framework::ToDataType(inside_tensor.type());
             attrs["shape"] = framework::vectorize2int(inside_tensor.dims());
             attrs["value"] = 0.0f;
 
diff --git a/paddle/operators/rnn_memory_helper_op.cc b/paddle/operators/rnn_memory_helper_op.cc
index b621c7f1ba3f9e9613dea5bc98ef74c7c6dae9a0..3a035f0b9acb94bab60659938e11b4996b8eaa0f 100644
--- a/paddle/operators/rnn_memory_helper_op.cc
+++ b/paddle/operators/rnn_memory_helper_op.cc
@@ -62,7 +62,7 @@ class RNNMemoryHelperOpInfoMaker : public framework::OpProtoAndCheckerMaker {
       : OpProtoAndCheckerMaker(proto, op_checker) {
     AddInput("X", "");
     AddOutput("Out", "");
-    AddAttr<int>("data_type",
+    AddAttr<int>("dtype",
                  "(int, default 5 (FP32)) "
                  "Output data type")
         .SetDefault(framework::DataType::FP32);
@@ -95,7 +95,7 @@ class RNNMemoryHelperGradOp : public framework::OperatorBase {
       auto &in_var_tensor = in_var->Get<framework::LoDTensor>();
 
       framework::AttributeMap attrs;
-      attrs["data_type"] = framework::ToDataType(in_var_tensor.type());
+      attrs["dtype"] = framework::ToDataType(in_var_tensor.type());
       attrs["shape"] = framework::vectorize2int(in_var_tensor.dims());
       attrs["value"] = 0.0f;
 
@@ -121,7 +121,7 @@ class RNNMemoryHelperGradOpInfoMaker
     AddInput("X", "");
     AddInput("Out", "");
     AddOutput(framework::GradVarName("X"), "");
-    AddAttr<int>("data_type",
+    AddAttr<int>("dtype",
                  "(int, default 5 (FP32)) "
                  "Output data type")
         .SetDefault(framework::DataType::FP32);
diff --git a/paddle/operators/uniform_random_op.cc b/paddle/operators/uniform_random_op.cc
index 7975efc7cf134aaf591385a6866254a9c5f2a0bb..fff1dc7ccddf1d8cee0c8311828fd38888283cd1 100644
--- a/paddle/operators/uniform_random_op.cc
+++ b/paddle/operators/uniform_random_op.cc
@@ -66,7 +66,7 @@ class UniformRandomOp : public framework::OperatorWithKernel {
   framework::OpKernelType GetKernelType(
       const framework::ExecutionContext& ctx) const override {
     return framework::OpKernelType(
-        static_cast<framework::DataType>(ctx.Attr<int>("data_type")),
+        static_cast<framework::DataType>(ctx.Attr<int>("dtype")),
         ctx.device_context());
   }
 };
@@ -99,7 +99,7 @@ uniform distribution.
                  "Random seed used for generating samples. "
                  "0 means use a seed generated by the system.")
         .SetDefault(0);
-    AddAttr<int>("data_type", "(int, default 5(FP32)) Output tensor data type")
+    AddAttr<int>("dtype", "(int, default 5(FP32)) Output tensor data type")
         .SetDefault(framework::DataType::FP32);
   }
 };
diff --git a/paddle/operators/while_op.cc b/paddle/operators/while_op.cc
index dcc59f5ff2ae3a8ca999d72a20cfd5c759987d89..68b4f7705995e5ecb6c9b8216db7373c1777a31e 100644
--- a/paddle/operators/while_op.cc
+++ b/paddle/operators/while_op.cc
@@ -180,7 +180,7 @@ class WhileGradOp : public framework::OperatorBase {
           if (var->IsType<LoDTensor>()) {
             auto &inside_tensor = var->Get<framework::LoDTensor>();
             framework::AttributeMap attrs;
-            attrs["data_type"] = framework::ToDataType(inside_tensor.type());
+            attrs["dtype"] = framework::ToDataType(inside_tensor.type());
             attrs["shape"] = framework::vectorize2int(inside_tensor.dims());
             attrs["value"] = 0.0f;
 
diff --git a/paddle/pybind/protobuf.cc b/paddle/pybind/protobuf.cc
index 5a1ff9b7976abbe4a37f8366181d9d1ae78ea4a0..6c8f06cccb92fa9cd22fdb89a9d410e6853895cc 100644
--- a/paddle/pybind/protobuf.cc
+++ b/paddle/pybind/protobuf.cc
@@ -202,9 +202,9 @@ void BindVarDsec(py::module &m) {
            },
            py::return_value_policy::reference)
       .def("set_shape", &VarDescBind::SetShape)
-      .def("set_data_type", &VarDescBind::SetDataType)
+      .def("set_dtype", &VarDescBind::SetDataType)
       .def("shape", &VarDescBind::Shape, py::return_value_policy::reference)
-      .def("data_type", &VarDescBind::GetDataType)
+      .def("dtype", &VarDescBind::GetDataType)
       .def("lod_level", &VarDescBind::GetLodLevel)
       .def("set_lod_level", &VarDescBind::SetLoDLevel)
       .def("type", &VarDescBind::GetType)
diff --git a/python/paddle/v2/fluid/evaluator.py b/python/paddle/v2/fluid/evaluator.py
index 3a8f1831cf2c44c81aee62c6ee172942db188217..0057ed62163ec2c7989c9279fa9ccedc0ab6e37b 100644
--- a/python/paddle/v2/fluid/evaluator.py
+++ b/python/paddle/v2/fluid/evaluator.py
@@ -8,7 +8,7 @@ def _clone_var_in_block_(block, var):
     return block.create_var(
         name=var.name,
         shape=var.shape,
-        dtype=var.data_type,
+        dtype=var.dtype,
         type=var.type,
         lod_level=var.lod_level,
         persistable=True)
@@ -57,7 +57,7 @@ class Evaluator(object):
                 attrs={
                     "shape": g_var.shape,
                     "value": .0,
-                    "data_type": 5,
+                    "dtype": 5,
                 })
             block.append_op(
                 type="scale", inputs={"X": zeros}, outputs={"Out": g_var})
@@ -93,7 +93,7 @@ class Accuracy(Evaluator):
 
     def _update_ops(self, input, label, k=1, **kwargs):
         block = self._main_program.global_block()
-        topk_out = block.create_var(dtype=input.data_type)
+        topk_out = block.create_var(dtype=input.dtype)
         topk_indices = block.create_var(dtype="int64")
         block.append_op(
             type="top_k",
@@ -122,16 +122,16 @@ class Accuracy(Evaluator):
             inputs={"X": [self._states["Total"]]},
             outputs={"Out": [self._states["Total"]]},
             attrs={
-                "in_data_type": 5,  # float32
-                "out_data_type": 2,  #int32
+                "in_dtype": 5,  # float32
+                "out_dtype": 2,  # int32
             })
         block.append_op(
             type="cast",
             inputs={"X": [self._states["Correct"]]},
             outputs={"Out": [self._states["Correct"]]},
             attrs={
-                "in_data_type": 5,
-                "out_data_type": 2,
+                "in_dtype": 5,
+                "out_dtype": 2,
             })
 
         block.append_op(
@@ -153,7 +153,7 @@ class Accuracy(Evaluator):
         else:
             eval_program = Program()
         block = eval_program.global_block()
-        eval_out = block.create_var(dtype=self._states["Total"].data_type)
+        eval_out = block.create_var(dtype=self._states["Total"].dtype)
         e_total = _clone_var_in_block_(block, self._states["Total"])
         e_correct = _clone_var_in_block_(block, self._states["Correct"])
         block.append_op(
@@ -161,16 +161,16 @@ class Accuracy(Evaluator):
             inputs={"X": [e_total]},
             outputs={"Out": [e_total]},
             attrs={
-                "in_data_type": 2,  #int32
-                "out_data_type": 5,  #float32
+                "in_dtype": 2,  # int32
+                "out_dtype": 5,  # float32
             })
         block.append_op(
             type="cast",
             inputs={"X": [e_correct]},
             outputs={"Out": [e_correct]},
             attrs={
-                "in_data_type": 2,
-                "out_data_type": 5,
+                "in_dtype": 2,
+                "out_dtype": 5,
             })
         block.append_op(
             type="elementwise_div",
diff --git a/python/paddle/v2/fluid/framework.py b/python/paddle/v2/fluid/framework.py
index 7f7c310ad87f64e5d047ecfc2876d516914c75c8..fb1c57d29605fea383bdbe2cf4f0a6ba12fb05ef 100644
--- a/python/paddle/v2/fluid/framework.py
+++ b/python/paddle/v2/fluid/framework.py
@@ -99,9 +99,9 @@ class Variable(object):
             if not isinstance(dtype, core.DataType):
                 dtype = convert_np_dtype_to_dtype_(dtype)
             if is_new_var:
-                self.desc.set_data_type(dtype)
+                self.desc.set_dtype(dtype)
             else:
-                old_dtype = self.data_type
+                old_dtype = self.dtype
                 if dtype != old_dtype:
                     raise ValueError("Variable {0} has been created before. "
                                      "The previous data type is {1}; the new "
@@ -162,8 +162,8 @@ class Variable(object):
         return tuple(self.desc.shape())
 
     @property
-    def data_type(self):
-        return self.desc.data_type()
+    def dtype(self):
+        return self.desc.dtype()
 
     @property
     def lod_level(self):
diff --git a/python/paddle/v2/fluid/initializer.py b/python/paddle/v2/fluid/initializer.py
index 1a9d804ee7ee8e6463d42fefb809fb45888fd064..9f23e68a7635b6e6ae927603dbcc47d63f9c7f3d 100644
--- a/python/paddle/v2/fluid/initializer.py
+++ b/python/paddle/v2/fluid/initializer.py
@@ -93,7 +93,7 @@ class ConstantInitializer(Initializer):
             outputs={"Out": var},
             attrs={
                 "shape": var.shape,
-                "data_type": int(var.data_type),
+                "dtype": int(var.dtype),
                 "value": self._value
             })
         var.op = op
@@ -140,7 +140,7 @@ class UniformInitializer(Initializer):
             outputs={"Out": var},
             attrs={
                 "shape": var.shape,
-                "data_type": int(var.data_type),
+                "dtype": int(var.dtype),
                 "min": self._low,
                 "max": self._high,
                 "seed": self._seed
@@ -188,7 +188,7 @@ class NormalInitializer(Initializer):
             outputs={"Out": var},
             attrs={
                 "shape": var.shape,
-                "data_type": int(var.data_type),
+                "dtype": int(var.dtype),
                 "mean": self._mean,
                 "std": self._std_dev,
                 "seed": self._seed
@@ -265,7 +265,7 @@ class XavierInitializer(Initializer):
                 outputs={"Out": var},
                 attrs={
                     "shape": var.shape,
-                    "data_type": int(var.data_type),
+                    "dtype": int(var.dtype),
                     "min": -limit,
                     "max": limit,
                     "seed": self._seed
@@ -278,7 +278,7 @@ class XavierInitializer(Initializer):
                 outputs={"Out": var},
                 attrs={
                     "shape": var.shape,
-                    "data_type": int(var.data_type),
+                    "dtype": int(var.dtype),
                     "mean": 0.0,
                     "std": std,
                     "seed": self._seed
@@ -348,7 +348,7 @@ class MSRAInitializer(Initializer):
                 outputs={"Out": var},
                 attrs={
                     "shape": var.shape,
-                    "data_type": int(var.data_type),
+                    "dtype": int(var.dtype),
                     "min": -limit,
                     "max": limit,
                     "seed": self._seed
@@ -361,7 +361,7 @@ class MSRAInitializer(Initializer):
                 outputs={"Out": var},
                 attrs={
                     "shape": var.shape,
-                    "data_type": int(var.data_type),
+                    "dtype": int(var.dtype),
                     "mean": 0.0,
                     "std": std,
                     "seed": self._seed
diff --git a/python/paddle/v2/fluid/io.py b/python/paddle/v2/fluid/io.py
index 2d070814eef0b099ba71bef223596e30388ac48a..6f55fe9e74d715ec7ac8c22b5532604fc0337c5e 100644
--- a/python/paddle/v2/fluid/io.py
+++ b/python/paddle/v2/fluid/io.py
@@ -23,7 +23,7 @@ def _clone_var_in_block_(block, var):
     return block.create_var(
         name=var.name,
         shape=var.shape,
-        dtype=var.data_type,
+        dtype=var.dtype,
         type=var.type,
         lod_level=var.lod_level,
         persistable=True)
diff --git a/python/paddle/v2/fluid/layer_helper.py b/python/paddle/v2/fluid/layer_helper.py
index e40551ca73e991edd8e1d1df5b103c36367b7050..e0880354fbc5a09bd49de7ec9c5dffc1e3c6259e 100644
--- a/python/paddle/v2/fluid/layer_helper.py
+++ b/python/paddle/v2/fluid/layer_helper.py
@@ -108,8 +108,8 @@ class LayerHelper(object):
         dtype = None
         for each in inputs:
             if dtype is None:
-                dtype = each.data_type
-            elif dtype != each.data_type:
+                dtype = each.dtype
+            elif dtype != each.dtype:
                 raise ValueError("Data Type mismatch")
         return dtype
 
@@ -149,7 +149,7 @@ class LayerHelper(object):
         self.startup_program.global_block().create_var(
             name=var.name,
             type=var.type,
-            dtype=var.data_type,
+            dtype=var.dtype,
             shape=var.shape,
             persistable=True,
             initializer=initializer)
@@ -180,10 +180,10 @@ class LayerHelper(object):
         b = self.create_parameter(
             attr=bias_attr,
             shape=size,
-            dtype=input_var.data_type,
+            dtype=input_var.dtype,
             suffix='b',
             initializer=bias_initializer)
-        tmp = self.create_tmp_variable(dtype=input_var.data_type)
+        tmp = self.create_tmp_variable(dtype=input_var.dtype)
         self.append_op(
             type='elementwise_add',
             inputs={'X': [input_var],
@@ -198,7 +198,7 @@ class LayerHelper(object):
             return input_var
         if isinstance(act, basestring):
             act = {'type': act}
-        tmp = self.create_tmp_variable(dtype=input_var.data_type)
+        tmp = self.create_tmp_variable(dtype=input_var.dtype)
         act_type = act.pop('type')
         self.append_op(
             type=act_type,
diff --git a/python/paddle/v2/fluid/layers.py b/python/paddle/v2/fluid/layers.py
index fac91aac97267b1ecc867bb9b0b1f8fd40f2f299..d094035fe5cae2e77fc2364e8ccb03c350f1301a 100644
--- a/python/paddle/v2/fluid/layers.py
+++ b/python/paddle/v2/fluid/layers.py
@@ -114,7 +114,7 @@ def embedding(input,
               is_sparse=False,
               param_initializer=None,
               param_attr=None,
-              data_type='float32',
+              dtype='float32',
               main_program=None,
               startup_program=None):
     """
@@ -125,7 +125,7 @@ def embedding(input,
        size: The size of the layer
        is_sparse: A flag that decleares whether the input is sparse
        param_attr: Parameters for this layer
-       data_type: The type of data : float32, float_16, int etc
+       dtype: The type of data : float32, float_16, int etc
        main_program: Name of the main program that calls this
        startup_program: Name of the startup program
 
@@ -145,9 +145,9 @@ def embedding(input,
     w = helper.create_parameter(
         attr=helper.param_attr,
         shape=size,
-        dtype=data_type,
+        dtype=dtype,
         initializer=param_initializer or _get_default_param_initializer())
-    tmp = helper.create_tmp_variable(data_type)
+    tmp = helper.create_tmp_variable(dtype)
     helper.append_op(
         type='lookup_table',
         inputs={'Ids': input,
@@ -167,23 +167,23 @@ def dynamic_lstm(input,
                  gate_activation='sigmoid',
                  cell_activation='tanh',
                  candidate_activation='tanh',
-                 data_type='float32',
+                 dtype='float32',
                  main_program=None,
                  startup_program=None):
     helper = LayerHelper('lstm', **locals())
     size = size / 4
     weight = helper.create_parameter(
-        attr=helper.param_attr, shape=[size, 4 * size], dtype=data_type)
+        attr=helper.param_attr, shape=[size, 4 * size], dtype=dtype)
     bias_size = [1, 7 * size]
     if not use_peepholes:
         bias_size[1] = 4 * size
     bias = helper.create_parameter(
-        attr=helper.bias_attr, shape=bias_size, dtype=data_type, suffix='b')
+        attr=helper.bias_attr, shape=bias_size, dtype=dtype, suffix='b')
 
-    hidden = helper.create_tmp_variable(data_type)
-    cell = helper.create_tmp_variable(data_type)
-    batch_gate = helper.create_tmp_variable(data_type)
-    batch_cell_pre_act = helper.create_tmp_variable(data_type)
+    hidden = helper.create_tmp_variable(dtype)
+    cell = helper.create_tmp_variable(dtype)
+    batch_gate = helper.create_tmp_variable(dtype)
+    batch_cell_pre_act = helper.create_tmp_variable(dtype)
 
     helper.append_op(
         type='lstm',
@@ -209,7 +209,7 @@ def dynamic_lstm(input,
 def data(name,
          shape,
          append_batch_size=True,
-         data_type='float32',
+         dtype='float32',
          type=core.VarDesc.VarType.LOD_TENSOR,
          main_program=None,
          startup_program=None,
@@ -221,7 +221,7 @@ def data(name,
        name: The name/alias of the function
        shape: Tuple declaring the shape.
        append_batch_size: Whether or not to append the data as a batch.
-       data_type: The type of data : float32, float_16, int etc
+       dtype: The type of data : float32, float_16, int etc
        type: The output type. By default it is LOD_TENSOR.
        main_program: Name of the main program that calls this
        startup_program: Name of the startup program
@@ -251,7 +251,7 @@ def data(name,
     return helper.create_global_variable(
         name=name,
         shape=shape,
-        dtype=data_type,
+        dtype=dtype,
         type=type,
         stop_gradient=stop_gradient)
 
@@ -362,9 +362,9 @@ def _create_op_func_(op_type):
     o_name = not_intermediate_outputs[0].name
     intermediate_output_names = [output.name for output in intermediate_outputs]
 
-    def infer_and_check_data_type(op_proto, **kwargs):
+    def infer_and_check_dtype(op_proto, **kwargs):
         """
-        This function performs the sanity check for data_type and
+        This function performs the sanity check for dtype and
         instance type.
         """
         dtype = None
@@ -379,8 +379,8 @@ def _create_op_func_(op_type):
                         op_type))
 
                 if dtype is None:
-                    dtype = each.data_type
-                elif dtype != each.data_type:
+                    dtype = each.dtype
+                elif dtype != each.dtype:
                     raise ValueError(
                         "operator {0} must input same dtype".format(op_type))
 
@@ -389,7 +389,7 @@ def _create_op_func_(op_type):
     def func(**kwargs):
         helper = LayerHelper(op_type, **kwargs)
 
-        dtype = infer_and_check_data_type(op_proto, **kwargs)
+        dtype = infer_and_check_dtype(op_proto, **kwargs)
 
         inputs = dict()
         for ipt in op_proto.inputs:
@@ -426,19 +426,19 @@ _create_op_func_('reshape')
 _create_op_func_('transpose')
 
 
-def cast(x, data_type, main_program=None):
+def cast(x, dtype, main_program=None):
     """
-    This function takes in the input with input_data_type
-    and casts it to the output_data_type as the output.
+    This function takes in the input with input_dtype
+    and casts it to the output_dtype as the output.
     """
     helper = LayerHelper('cast', **locals())
-    out = helper.create_tmp_variable(dtype=data_type)
+    out = helper.create_tmp_variable(dtype=dtype)
     helper.append_op(
         type='cast',
         inputs={'X': [x]},
         outputs={'Out': [out]},
-        attrs={'in_data_type': x.data_type,
-               'out_data_type': out.data_type})
+        attrs={'in_dtype': x.dtype,
+               'out_dtype': out.dtype})
     return out
 
 
@@ -519,8 +519,8 @@ def split_lod_tensor(input,
                      main_program=None,
                      startup_program=None):
     helper = LayerHelper('split_lod_tensor', **locals())
-    out_true = helper.create_tmp_variable(dtype=input.data_type)
-    out_false = helper.create_tmp_variable(dtype=input.data_type)
+    out_true = helper.create_tmp_variable(dtype=input.dtype)
+    out_false = helper.create_tmp_variable(dtype=input.dtype)
     helper.append_op(
         type='split_lod_tensor',
         inputs={
@@ -541,7 +541,7 @@ def merge_lod_tensor(in_true,
                      main_program=None,
                      startup_program=None):
     helper = LayerHelper('merge_lod_tensor', **locals())
-    out = helper.create_tmp_variable(dtype=in_true.data_type)
+    out = helper.create_tmp_variable(dtype=in_true.dtype)
     helper.append_op(
         type='merge_lod_tensor',
         inputs={'X': x,
@@ -559,9 +559,9 @@ def cos_sim(X, Y, **kwargs):
     X and Y and returns that as the output.
     """
     helper = LayerHelper('cos_sim', **kwargs)
-    out = helper.create_tmp_variable(dtype=X.data_type)
-    xnorm = helper.create_tmp_variable(dtype=X.data_type)
-    ynorm = helper.create_tmp_variable(dtype=X.data_type)
+    out = helper.create_tmp_variable(dtype=X.dtype)
+    xnorm = helper.create_tmp_variable(dtype=X.dtype)
+    ynorm = helper.create_tmp_variable(dtype=X.dtype)
     helper.append_op(
         type='cos_sim',
         inputs={'X': [X],
@@ -577,7 +577,7 @@ def cross_entropy(input, label, **kwargs):
     This function computes cross_entropy using the input and label.
     """
     helper = LayerHelper('cross_entropy', **kwargs)
-    out = helper.create_tmp_variable(dtype=input.data_type)
+    out = helper.create_tmp_variable(dtype=input.dtype)
     helper.append_op(
         type='cross_entropy',
         inputs={'X': [input],
@@ -593,14 +593,14 @@ def square_error_cost(input, label, **kwargs):
     The output is appending the op to do the above.
     """
     helper = LayerHelper('square_error_cost', **kwargs)
-    minus_out = helper.create_tmp_variable(dtype=input.data_type)
+    minus_out = helper.create_tmp_variable(dtype=input.dtype)
     helper.append_op(
         type='elementwise_sub',
         inputs={'X': [input],
                 'Y': [label]},
         outputs={'Out': [minus_out]})
 
-    square_out = helper.create_tmp_variable(dtype=input.data_type)
+    square_out = helper.create_tmp_variable(dtype=input.dtype)
     helper.append_op(
         type='square', inputs={'X': [minus_out]}, outputs={'Y': [square_out]})
     return square_out
@@ -612,7 +612,7 @@ def accuracy(input, label, k=1, **kwargs):
     The output is the top_k inputs and their indices.
     """
     helper = LayerHelper("accuracy", **kwargs)
-    topk_out = helper.create_tmp_variable(dtype=input.data_type)
+    topk_out = helper.create_tmp_variable(dtype=input.dtype)
     topk_indices = helper.create_tmp_variable(dtype="int64")
     helper.append_op(
         type="top_k",
@@ -883,12 +883,12 @@ def batch_norm(input,
         initializer=ConstantInitializer(0.0))
 
     mean = helper.create_global_variable(
-        dtype=input.data_type, shape=param_shape, persistable=True)
+        dtype=input.dtype, shape=param_shape, persistable=True)
     helper.set_variable_initializer(
         var=mean, initializer=ConstantInitializer(0.0))
 
     variance = helper.create_global_variable(
-        dtype=input.data_type, shape=param_shape, persistable=True)
+        dtype=input.dtype, shape=param_shape, persistable=True)
     helper.set_variable_initializer(
         var=variance, initializer=ConstantInitializer(1.0))
 
@@ -927,8 +927,8 @@ def batch_norm(input,
 
 def beam_search_decode(ids, scores, main_program=None, startup_program=None):
     helper = LayerHelper('beam_search_decode', **locals())
-    sentence_ids = helper.create_tmp_variable(dtype=ids.data_type)
-    sentence_scores = helper.create_tmp_variable(dtype=ids.data_type)
+    sentence_ids = helper.create_tmp_variable(dtype=ids.dtype)
+    sentence_scores = helper.create_tmp_variable(dtype=ids.dtype)
 
     helper.append_op(
         type="beam_search_decode",
@@ -1066,7 +1066,7 @@ class StaticRNN(object):
             boot_var = parent_block.create_var(
                 name=var_name,
                 shape=shape,
-                dtype=batch_ref.data_type,
+                dtype=batch_ref.dtype,
                 persistable=False)
 
             parent_block.append_op(
@@ -1076,7 +1076,7 @@ class StaticRNN(object):
                 attrs={
                     'value': init_value,
                     'shape': boot_var.shape,
-                    'data_type': boot_var.data_type,
+                    'dtype': boot_var.dtype,
                     'input_dim_idx': ref_batch_dim_idx,
                     'output_dim_idx': init_batch_dim_idx
                 })
@@ -1085,7 +1085,7 @@ class StaticRNN(object):
         else:
             pre_mem = self.helper.create_variable(
                 name=unique_name("@".join([self.helper.name, "mem"])),
-                dtype=init.data_type,
+                dtype=init.dtype,
                 shape=init.shape)
             self.memories[pre_mem.name] = StaticRNNMemoryLink(
                 init=init, pre_mem=pre_mem)
@@ -1101,10 +1101,7 @@ class StaticRNN(object):
             raise ValueError("Static RNN only take fix seq_len input")
 
         ipt = self.helper.create_variable(
-            name=x.name,
-            dtype=x.data_type,
-            shape=list(x.shape[1:]),
-            type=x.type)
+            name=x.name, dtype=x.dtype, shape=list(x.shape[1:]), type=x.type)
         self.inputs.append(ipt)
         return ipt
 
@@ -1113,17 +1110,17 @@ class StaticRNN(object):
         if not isinstance(o, Variable):
             raise TypeError("step output takes a Variable")
 
-        tmp_o = self.helper.create_tmp_variable(dtype=o.data_type)
+        tmp_o = self.helper.create_tmp_variable(dtype=o.dtype)
         self.helper.append_op(
             type='rnn_memory_helper',
             inputs={'X': [o]},
             outputs={'Out': tmp_o},
-            attrs={'data_type': o.data_type})
+            attrs={'dtype': o.dtype})
 
         out_var = self.parent_block().create_var(
             name=tmp_o.name,
             shape=[self.seq_len] + list(tmp_o.shape),
-            dtype=tmp_o.data_type)
+            dtype=tmp_o.dtype)
 
         self.outputs.append(out_var)
 
@@ -1195,13 +1192,13 @@ class StaticRNN(object):
             pre_memories.append(mem.pre_mem.name)
             mem_var = rnn_block.var(mem.mem.name)
             assert isinstance(mem_var, Variable)
-            new_mem = self.helper.create_tmp_variable(dtype=mem_var.data_type)
+            new_mem = self.helper.create_tmp_variable(dtype=mem_var.dtype)
 
             rnn_block.append_op(
                 type='rnn_memory_helper',
                 inputs={'X': [mem_var]},
                 outputs={'Out': [new_mem]},
-                attrs={'data_type': mem_var.data_type})
+                attrs={'dtype': mem_var.dtype})
 
             memories.append(new_mem.name)
 
@@ -1251,7 +1248,7 @@ class While(object):
         if not isinstance(cond, Variable):
             raise TypeError("condition should be a variable")
         assert isinstance(cond, Variable)
-        if cond.data_type != core.DataType.BOOL:
+        if cond.dtype != core.DataType.BOOL:
             raise TypeError("condition should be a bool variable")
         if reduce(lambda a, b: a * b, cond.shape, 1) != 1:
             raise TypeError("condition should be a bool scalar")
@@ -1323,9 +1320,9 @@ def lstm(x,
                       main_program=main_program,
                       startup_program=startup_program)
 
-        data_type = x.data_type
-        c = helper.create_tmp_variable(data_type)
-        h = helper.create_tmp_variable(data_type)
+        dtype = x.dtype
+        c = helper.create_tmp_variable(dtype)
+        h = helper.create_tmp_variable(dtype)
 
         helper.append_op(
             type='lstm_unit',
@@ -1367,7 +1364,7 @@ def lod_tensor_to_array(x, table, main_program=None):
     array = helper.create_variable(
         name=unique_name("lod_tensor_to_array"),
         type=core.VarDesc.VarType.LOD_TENSOR_ARRAY,
-        dtype=x.data_type)
+        dtype=x.dtype)
     helper.append_op(
         type='lod_tensor_to_array',
         inputs={'X': x,
@@ -1382,7 +1379,7 @@ def array_to_lod_tensor(x, table, main_program=None):
     LOD_Tensor.
     """
     helper = LayerHelper("array_to_lod_tensor", **locals())
-    tmp = helper.create_tmp_variable(dtype=x.data_type)
+    tmp = helper.create_tmp_variable(dtype=x.dtype)
     helper.append_op(
         type="array_to_lod_tensor",
         inputs={'X': x,
@@ -1394,7 +1391,7 @@ def array_to_lod_tensor(x, table, main_program=None):
 def fill_constant(shape, dtype, value, main_program=None, startup_program=None):
     """
     This function creates a tensor , with shape as mentioned in the input and
-    specified data_type and fills this up with a constant value that
+    specified dtype and fills this up with a constant value that
     comes in the input. It also sets the stop_gradient to be True.
     """
     helper = LayerHelper("fill_constant", **locals())
@@ -1403,11 +1400,9 @@ def fill_constant(shape, dtype, value, main_program=None, startup_program=None):
         type='fill_constant',
         inputs={},
         outputs={'Out': [out]},
-        attrs={
-            'shape': shape,
-            'data_type': out.data_type,
-            'value': float(value)
-        })
+        attrs={'shape': shape,
+               'dtype': out.dtype,
+               'value': float(value)})
     out.stop_gradient = True
     return out
 
@@ -1428,7 +1423,7 @@ def fill_constant_batch_size_like(input,
         outputs={'Out': [out]},
         attrs={
             'shape': shape,
-            'data_type': out.data_type,
+            'dtype': out.dtype,
             'value': float(value),
             'input_dim_idx': input_dim_idx,
             'output_dim_idx': output_dim_idx
@@ -1461,7 +1456,7 @@ def increment(x, value=1.0, in_place=True, main_program=None):
     """
     helper = LayerHelper("increment", **locals())
     if not in_place:
-        out = helper.create_tmp_variable(dtype=x.data_type)
+        out = helper.create_tmp_variable(dtype=x.dtype)
     else:
         out = x
     helper.append_op(
@@ -1482,7 +1477,7 @@ def array_write(x, i, array=None, main_program=None):
         array = helper.create_variable(
             name="{0}.out".format(helper.name),
             type=core.VarDesc.VarType.LOD_TENSOR_ARRAY,
-            dtype=x.data_type)
+            dtype=x.dtype)
     helper.append_op(
         type='write_to_array',
         inputs={'X': [x],
@@ -1521,7 +1516,7 @@ def array_read(array, i, main_program=None):
             array,
             Variable) or array.type != core.VarDesc.VarType.LOD_TENSOR_ARRAY:
         raise TypeError("array should be tensor array vairable")
-    out = helper.create_tmp_variable(dtype=array.data_type)
+    out = helper.create_tmp_variable(dtype=array.dtype)
     helper.append_op(
         type='read_from_array',
         inputs={'X': [array],
@@ -1536,7 +1531,7 @@ def shrink_memory(x, i, table, main_program=None):
     as mentioned in the input parameter.
     """
     helper = LayerHelper('shrink_memory', **locals())
-    out = helper.create_tmp_variable(dtype=x.data_type)
+    out = helper.create_tmp_variable(dtype=x.dtype)
     helper.append_op(
         type='shrink_rnn_memory',
         inputs={'X': [x],
@@ -1698,11 +1693,11 @@ class IfElse(object):
             parent_block = self.parent_block()
             out_true = parent_block.create_var(
                 name=unique_name('ifelse_input' + self.helper.name),
-                dtype=x.data_type)
+                dtype=x.dtype)
 
             out_false = parent_block.create_var(
                 name=unique_name('ifelse_input' + self.helper.name),
-                dtype=x.data_type)
+                dtype=x.dtype)
             parent_block.append_op(
                 type='split_lod_tensor',
                 inputs={
@@ -1744,7 +1739,7 @@ class IfElse(object):
             # create outside tensor
             outside_out = parent_block.create_var(
                 name=unique_name("_".join([self.helper.name, 'output'])),
-                dtype=each_out.data_type)
+                dtype=each_out.dtype)
             out_table.append(outside_out)
 
             # assign local var to outside
diff --git a/python/paddle/v2/fluid/optimizer.py b/python/paddle/v2/fluid/optimizer.py
index 87a478c2903b77d955ebde49a4a0e507c9e9ffd3..e82f0f060de6af63f63d5601ae94059192076e6f 100644
--- a/python/paddle/v2/fluid/optimizer.py
+++ b/python/paddle/v2/fluid/optimizer.py
@@ -92,7 +92,7 @@ class Optimizer(object):
         var = self.helper.create_global_variable(
             name=unique_name(name),
             persistable=True,
-            dtype=dtype or param.data_type,
+            dtype=dtype or param.dtype,
             type=param.type,
             shape=param.shape)
         self.helper.set_variable_initializer(
@@ -202,7 +202,7 @@ class Optimizer(object):
         """
         params_grads = append_backward_ops(loss, parameter_list, no_grad_set or
                                            set())
-        # Add regularization if any 
+        # Add regularization if any
         params_grads = append_regularization_ops(params_grads)
         optimize_ops = self.create_optimization_pass(params_grads, loss,
                                                      startup_program)
diff --git a/python/paddle/v2/fluid/tests/book/test_fit_a_line.py b/python/paddle/v2/fluid/tests/book/test_fit_a_line.py
index a7f3bfc0caf76302674a00c80c2bd9ebf834f872..a899f1088d77c4ca6462cf5306393444ea114e6c 100644
--- a/python/paddle/v2/fluid/tests/book/test_fit_a_line.py
+++ b/python/paddle/v2/fluid/tests/book/test_fit_a_line.py
@@ -7,11 +7,11 @@ from paddle.v2.fluid.executor import Executor
 from paddle.v2.fluid.io import save_persistables, load_persistables
 from paddle.v2.fluid.optimizer import SGDOptimizer
 
-x = layers.data(name='x', shape=[13], data_type='float32')
+x = layers.data(name='x', shape=[13], dtype='float32')
 
 y_predict = layers.fc(input=x, size=1, act=None)
 
-y = layers.data(name='y', shape=[1], data_type='float32')
+y = layers.data(name='y', shape=[1], dtype='float32')
 
 cost = layers.square_error_cost(input=y_predict, label=y)
 avg_cost = layers.mean(x=cost)
diff --git a/python/paddle/v2/fluid/tests/book/test_image_classification_train.py b/python/paddle/v2/fluid/tests/book/test_image_classification_train.py
index efe63a68f0745eb728b569a03d0344877c1484f7..a3acab67cec29b69055b61046ffb10891af8fadd 100644
--- a/python/paddle/v2/fluid/tests/book/test_image_classification_train.py
+++ b/python/paddle/v2/fluid/tests/book/test_image_classification_train.py
@@ -90,8 +90,8 @@ def vgg16_bn_drop(input):
 classdim = 10
 data_shape = [3, 32, 32]
 
-images = layers.data(name='pixel', shape=data_shape, data_type='float32')
-label = layers.data(name='label', shape=[1], data_type='int64')
+images = layers.data(name='pixel', shape=data_shape, dtype='float32')
+label = layers.data(name='label', shape=[1], dtype='int64')
 
 # Add neural network config
 # option 1. resnet
diff --git a/python/paddle/v2/fluid/tests/book/test_label_semantic_roles.py b/python/paddle/v2/fluid/tests/book/test_label_semantic_roles.py
index f66e6e748b76dec53a9e24b5b352d31395ce6bde..9c9064ba9639829ef3afd8111278b17035bee84a 100644
--- a/python/paddle/v2/fluid/tests/book/test_label_semantic_roles.py
+++ b/python/paddle/v2/fluid/tests/book/test_label_semantic_roles.py
@@ -34,26 +34,26 @@ def load_parameter(file_name, h, w):
 
 def db_lstm():
     # 8 features
-    word = layers.data(name='word_data', shape=[1], data_type='int64')
-    predicate = layers.data(name='verb_data', shape=[1], data_type='int64')
-    ctx_n2 = layers.data(name='ctx_n2_data', shape=[1], data_type='int64')
-    ctx_n1 = layers.data(name='ctx_n1_data', shape=[1], data_type='int64')
-    ctx_0 = layers.data(name='ctx_0_data', shape=[1], data_type='int64')
-    ctx_p1 = layers.data(name='ctx_p1_data', shape=[1], data_type='int64')
-    ctx_p2 = layers.data(name='ctx_p2_data', shape=[1], data_type='int64')
-    mark = layers.data(name='mark_data', shape=[1], data_type='int64')
+    word = layers.data(name='word_data', shape=[1], dtype='int64')
+    predicate = layers.data(name='verb_data', shape=[1], dtype='int64')
+    ctx_n2 = layers.data(name='ctx_n2_data', shape=[1], dtype='int64')
+    ctx_n1 = layers.data(name='ctx_n1_data', shape=[1], dtype='int64')
+    ctx_0 = layers.data(name='ctx_0_data', shape=[1], dtype='int64')
+    ctx_p1 = layers.data(name='ctx_p1_data', shape=[1], dtype='int64')
+    ctx_p2 = layers.data(name='ctx_p2_data', shape=[1], dtype='int64')
+    mark = layers.data(name='mark_data', shape=[1], dtype='int64')
 
     predicate_embedding = layers.embedding(
         input=predicate,
         size=[pred_len, word_dim],
-        data_type='float32',
+        dtype='float32',
         is_sparse=IS_SPARSE,
         param_attr={'name': 'vemb'})
 
     mark_embedding = layers.embedding(
         input=mark,
         size=[mark_dict_len, mark_dim],
-        data_type='float32',
+        dtype='float32',
         is_sparse=IS_SPARSE)
 
     word_input = [word, ctx_n2, ctx_n1, ctx_0, ctx_p1, ctx_p2]
@@ -125,7 +125,7 @@ def to_lodtensor(data, place):
 def main():
     # define network topology
     feature_out = db_lstm()
-    target = layers.data(name='target', shape=[1], data_type='int64')
+    target = layers.data(name='target', shape=[1], dtype='int64')
     crf_cost = layers.linear_chain_crf(
         input=feature_out,
         label=target,
diff --git a/python/paddle/v2/fluid/tests/book/test_recognize_digits_conv.py b/python/paddle/v2/fluid/tests/book/test_recognize_digits_conv.py
index 8f737689609fec4d1819ae58b9665298547a3716..0bea5f95c895b278db86f25f54e2795d3ec0af69 100644
--- a/python/paddle/v2/fluid/tests/book/test_recognize_digits_conv.py
+++ b/python/paddle/v2/fluid/tests/book/test_recognize_digits_conv.py
@@ -8,8 +8,8 @@ import paddle.v2.fluid.nets as nets
 from paddle.v2.fluid.executor import Executor
 from paddle.v2.fluid.optimizer import AdamOptimizer
 
-images = layers.data(name='pixel', shape=[1, 28, 28], data_type='float32')
-label = layers.data(name='label', shape=[1], data_type='int64')
+images = layers.data(name='pixel', shape=[1, 28, 28], dtype='float32')
+label = layers.data(name='label', shape=[1], dtype='int64')
 conv_pool_1 = nets.simple_img_conv_pool(
     input=images,
     filter_size=5,
diff --git a/python/paddle/v2/fluid/tests/book/test_recognize_digits_mlp.py b/python/paddle/v2/fluid/tests/book/test_recognize_digits_mlp.py
index e42e4c9cc0024e193b0732df6d9ca3200df5f0b9..03d38815499a4e4ae1af45e642dd33ae7aa8f1d1 100644
--- a/python/paddle/v2/fluid/tests/book/test_recognize_digits_mlp.py
+++ b/python/paddle/v2/fluid/tests/book/test_recognize_digits_mlp.py
@@ -10,7 +10,7 @@ from paddle.v2.fluid.optimizer import MomentumOptimizer
 from paddle.v2.fluid.regularizer import L2DecayRegularizer
 
 BATCH_SIZE = 128
-image = layers.data(name='x', shape=[784], data_type='float32')
+image = layers.data(name='x', shape=[784], dtype='float32')
 
 param_attr = {
     'name': None,
@@ -27,7 +27,7 @@ predict = layers.fc(input=hidden2,
                     act='softmax',
                     param_attr=param_attr)
 
-label = layers.data(name='y', shape=[1], data_type='int64')
+label = layers.data(name='y', shape=[1], dtype='int64')
 
 cost = layers.cross_entropy(input=predict, label=label)
 avg_cost = layers.mean(x=cost)
diff --git a/python/paddle/v2/fluid/tests/book/test_recommender_system.py b/python/paddle/v2/fluid/tests/book/test_recommender_system.py
index 55ded3aed3a23c8cd7795f915dc1cbd512c6d945..f8dc1518579d5a9d7a8d0498dcc5fd8a6d1692c4 100644
--- a/python/paddle/v2/fluid/tests/book/test_recommender_system.py
+++ b/python/paddle/v2/fluid/tests/book/test_recommender_system.py
@@ -18,11 +18,11 @@ def get_usr_combined_features():
 
     USR_DICT_SIZE = paddle.dataset.movielens.max_user_id() + 1
 
-    uid = layers.data(name='user_id', shape=[1], data_type='int64')
+    uid = layers.data(name='user_id', shape=[1], dtype='int64')
 
     usr_emb = layers.embedding(
         input=uid,
-        data_type='float32',
+        dtype='float32',
         size=[USR_DICT_SIZE, 32],
         param_attr={'name': 'user_table'},
         is_sparse=IS_SPARSE)
@@ -31,7 +31,7 @@ def get_usr_combined_features():
 
     USR_GENDER_DICT_SIZE = 2
 
-    usr_gender_id = layers.data(name='gender_id', shape=[1], data_type='int64')
+    usr_gender_id = layers.data(name='gender_id', shape=[1], dtype='int64')
 
     usr_gender_emb = layers.embedding(
         input=usr_gender_id,
@@ -42,7 +42,7 @@ def get_usr_combined_features():
     usr_gender_fc = layers.fc(input=usr_gender_emb, size=16)
 
     USR_AGE_DICT_SIZE = len(paddle.dataset.movielens.age_table)
-    usr_age_id = layers.data(name='age_id', shape=[1], data_type="int64")
+    usr_age_id = layers.data(name='age_id', shape=[1], dtype="int64")
 
     usr_age_emb = layers.embedding(
         input=usr_age_id,
@@ -53,7 +53,7 @@ def get_usr_combined_features():
     usr_age_fc = layers.fc(input=usr_age_emb, size=16)
 
     USR_JOB_DICT_SIZE = paddle.dataset.movielens.max_job_id() + 1
-    usr_job_id = layers.data(name='job_id', shape=[1], data_type="int64")
+    usr_job_id = layers.data(name='job_id', shape=[1], dtype="int64")
 
     usr_job_emb = layers.embedding(
         input=usr_job_id,
@@ -75,11 +75,11 @@ def get_mov_combined_features():
 
     MOV_DICT_SIZE = paddle.dataset.movielens.max_movie_id() + 1
 
-    mov_id = layers.data(name='movie_id', shape=[1], data_type='int64')
+    mov_id = layers.data(name='movie_id', shape=[1], dtype='int64')
 
     mov_emb = layers.embedding(
         input=mov_id,
-        data_type='float32',
+        dtype='float32',
         size=[MOV_DICT_SIZE, 32],
         param_attr={'name': 'movie_table'},
         is_sparse=IS_SPARSE)
@@ -88,7 +88,7 @@ def get_mov_combined_features():
 
     CATEGORY_DICT_SIZE = len(paddle.dataset.movielens.movie_categories())
 
-    category_id = layers.data(name='category_id', shape=[1], data_type='int64')
+    category_id = layers.data(name='category_id', shape=[1], dtype='int64')
 
     mov_categories_emb = layers.embedding(
         input=category_id, size=[CATEGORY_DICT_SIZE, 32], is_sparse=IS_SPARSE)
@@ -98,7 +98,7 @@ def get_mov_combined_features():
 
     MOV_TITLE_DICT_SIZE = len(paddle.dataset.movielens.get_movie_title_dict())
 
-    mov_title_id = layers.data(name='movie_title', shape=[1], data_type='int64')
+    mov_title_id = layers.data(name='movie_title', shape=[1], dtype='int64')
 
     mov_title_emb = layers.embedding(
         input=mov_title_id, size=[MOV_TITLE_DICT_SIZE, 32], is_sparse=IS_SPARSE)
@@ -126,7 +126,7 @@ def model():
     # need cos sim
     inference = layers.cos_sim(X=usr_combined_features, Y=mov_combined_features)
 
-    label = layers.data(name='score', shape=[1], data_type='float32')
+    label = layers.data(name='score', shape=[1], dtype='float32')
 
     square_cost = layers.square_error_cost(input=inference, label=label)
 
diff --git a/python/paddle/v2/fluid/tests/book/test_understand_sentiment_conv.py b/python/paddle/v2/fluid/tests/book/test_understand_sentiment_conv.py
index 4929f7cf615e61de5c4f61ef44c5340e9ac4492a..3103be83a63d64fcba87132ddc5d830b92047b27 100644
--- a/python/paddle/v2/fluid/tests/book/test_understand_sentiment_conv.py
+++ b/python/paddle/v2/fluid/tests/book/test_understand_sentiment_conv.py
@@ -10,8 +10,8 @@ from paddle.v2.fluid.optimizer import AdamOptimizer
 
 
 def convolution_net(input_dim, class_dim=2, emb_dim=32, hid_dim=32):
-    data = layers.data(name="words", shape=[1], data_type="int64")
-    label = layers.data(name="label", shape=[1], data_type="int64")
+    data = layers.data(name="words", shape=[1], dtype="int64")
+    label = layers.data(name="label", shape=[1], dtype="int64")
 
     emb = layers.embedding(input=data, size=[input_dim, emb_dim])
     conv_3 = nets.sequence_conv_pool(
diff --git a/python/paddle/v2/fluid/tests/book/test_understand_sentiment_dynamic_lstm.py b/python/paddle/v2/fluid/tests/book/test_understand_sentiment_dynamic_lstm.py
index b3ee91938865afb929670a388a561b156aec1fe9..208978224f4e83a23efadae37fbe51d0d59dafe8 100644
--- a/python/paddle/v2/fluid/tests/book/test_understand_sentiment_dynamic_lstm.py
+++ b/python/paddle/v2/fluid/tests/book/test_understand_sentiment_dynamic_lstm.py
@@ -14,8 +14,8 @@ def stacked_lstm_net(input_dim,
                      hid_dim=512,
                      stacked_num=3):
     assert stacked_num % 2 == 1
-    data = layers.data(name="words", shape=[1], data_type="int64")
-    label = layers.data(name="label", shape=[1], data_type="int64")
+    data = layers.data(name="words", shape=[1], dtype="int64")
+    label = layers.data(name="label", shape=[1], dtype="int64")
 
     emb = layers.embedding(input=data, size=[input_dim, emb_dim])
     # add bias attr
diff --git a/python/paddle/v2/fluid/tests/book/test_understand_sentiment_lstm.py b/python/paddle/v2/fluid/tests/book/test_understand_sentiment_lstm.py
index 9a51a2f207ebed340b8e5c60e7ebeb82a611dbc5..8aebeba653cf49438929fa51312b5af33c3b438d 100644
--- a/python/paddle/v2/fluid/tests/book/test_understand_sentiment_lstm.py
+++ b/python/paddle/v2/fluid/tests/book/test_understand_sentiment_lstm.py
@@ -12,19 +12,19 @@ def lstm_net(dict_dim, class_dim=2, emb_dim=32, seq_len=80, batch_size=50):
         name="words",
         shape=[seq_len * batch_size, 1],
         append_batch_size=False,
-        data_type="int64")
+        dtype="int64")
     label = layers.data(
         name="label",
         shape=[batch_size, 1],
         append_batch_size=False,
-        data_type="int64")
+        dtype="int64")
 
     emb = layers.embedding(input=data, size=[dict_dim, emb_dim])
     emb = layers.reshape(x=emb, shape=[batch_size, seq_len, emb_dim])
     emb = layers.transpose(x=emb, axis=[1, 0, 2])
 
     c_pre_init = layers.fill_constant(
-        dtype=emb.data_type, shape=[batch_size, emb_dim], value=0.0)
+        dtype=emb.dtype, shape=[batch_size, emb_dim], value=0.0)
     layer_1_out = layers.lstm(emb, c_pre_init=c_pre_init, hidden_dim=emb_dim)
     layer_1_out = layers.transpose(x=layer_1_out, axis=[1, 0, 2])
 
diff --git a/python/paddle/v2/fluid/tests/book/test_word2vec.py b/python/paddle/v2/fluid/tests/book/test_word2vec.py
index afa7b285198e0349317e123e4bd98e8336217afa..0629e1cab7fd7e501d9cbf3ae8ee22fe9383ad2b 100644
--- a/python/paddle/v2/fluid/tests/book/test_word2vec.py
+++ b/python/paddle/v2/fluid/tests/book/test_word2vec.py
@@ -16,34 +16,34 @@ IS_SPARSE = True
 word_dict = paddle.dataset.imikolov.build_dict()
 dict_size = len(word_dict)
 
-first_word = layers.data(name='firstw', shape=[1], data_type='int64')
-second_word = layers.data(name='secondw', shape=[1], data_type='int64')
-third_word = layers.data(name='thirdw', shape=[1], data_type='int64')
-forth_word = layers.data(name='forthw', shape=[1], data_type='int64')
-next_word = layers.data(name='nextw', shape=[1], data_type='int64')
+first_word = layers.data(name='firstw', shape=[1], dtype='int64')
+second_word = layers.data(name='secondw', shape=[1], dtype='int64')
+third_word = layers.data(name='thirdw', shape=[1], dtype='int64')
+forth_word = layers.data(name='forthw', shape=[1], dtype='int64')
+next_word = layers.data(name='nextw', shape=[1], dtype='int64')
 
 embed_first = layers.embedding(
     input=first_word,
     size=[dict_size, EMBED_SIZE],
-    data_type='float32',
+    dtype='float32',
     is_sparse=IS_SPARSE,
     param_attr={'name': 'shared_w'})
 embed_second = layers.embedding(
     input=second_word,
     size=[dict_size, EMBED_SIZE],
-    data_type='float32',
+    dtype='float32',
     is_sparse=IS_SPARSE,
     param_attr={'name': 'shared_w'})
 embed_third = layers.embedding(
     input=third_word,
     size=[dict_size, EMBED_SIZE],
-    data_type='float32',
+    dtype='float32',
     is_sparse=IS_SPARSE,
     param_attr={'name': 'shared_w'})
 embed_forth = layers.embedding(
     input=forth_word,
     size=[dict_size, EMBED_SIZE],
-    data_type='float32',
+    dtype='float32',
     is_sparse=IS_SPARSE,
     param_attr={'name': 'shared_w'})
 
diff --git a/python/paddle/v2/fluid/tests/op_test.py b/python/paddle/v2/fluid/tests/op_test.py
index 90269e308a31d2606b23d741ce0d0fa91a0a6aeb..51023bd19a8326152335eabc9e96600427527f26 100644
--- a/python/paddle/v2/fluid/tests/op_test.py
+++ b/python/paddle/v2/fluid/tests/op_test.py
@@ -458,7 +458,7 @@ class OpTest(unittest.TestCase):
         mean_inputs = map(block.var, output_names)
 
         if len(mean_inputs) == 1:
-            loss = block.create_var(dtype=mean_inputs[0].data_type, shape=[1])
+            loss = block.create_var(dtype=mean_inputs[0].dtype, shape=[1])
             op = block.append_op(
                 inputs={"X": mean_inputs}, outputs={"Out": loss}, type='mean')
             op.desc.infer_var_type(block.desc)
@@ -466,8 +466,7 @@ class OpTest(unittest.TestCase):
         else:
             avg_sum = []
             for cur_loss in mean_inputs:
-                cur_avg_loss = block.create_var(
-                    dtype=cur_loss.data_type, shape=[1])
+                cur_avg_loss = block.create_var(dtype=cur_loss.dtype, shape=[1])
                 op = block.append_op(
                     inputs={"X": [cur_loss]},
                     outputs={"Out": [cur_avg_loss]},
@@ -476,13 +475,13 @@ class OpTest(unittest.TestCase):
                 op.desc.infer_shape(block.desc)
                 avg_sum.append(cur_avg_loss)
 
-            loss_sum = block.create_var(dtype=avg_sum[0].data_type, shape=[1])
+            loss_sum = block.create_var(dtype=avg_sum[0].dtype, shape=[1])
             op_sum = block.append_op(
                 inputs={"X": avg_sum}, outputs={"Out": loss_sum}, type='sum')
             op_sum.desc.infer_var_type(block.desc)
             op_sum.desc.infer_shape(block.desc)
 
-            loss = block.create_var(dtype=loss_sum.data_type, shape=[1])
+            loss = block.create_var(dtype=loss_sum.dtype, shape=[1])
             op_loss = block.append_op(
                 inputs={"X": loss_sum},
                 outputs={"Out": loss},
diff --git a/python/paddle/v2/fluid/tests/test_cast_op.py b/python/paddle/v2/fluid/tests/test_cast_op.py
index 0c4b6310652e84d3dd7f281a8b98ae0435072afb..4e431bb88da6070718d64a68467be20ca87f8fb9 100644
--- a/python/paddle/v2/fluid/tests/test_cast_op.py
+++ b/python/paddle/v2/fluid/tests/test_cast_op.py
@@ -10,8 +10,8 @@ class TestCastOp(op_test.OpTest):
         self.inputs = {'X': ipt.astype('float32')}
         self.outputs = {'Out': ipt.astype('float64')}
         self.attrs = {
-            'in_data_type': int(core.DataType.FP32),
-            'out_data_type': int(core.DataType.FP64)
+            'in_dtype': int(core.DataType.FP32),
+            'out_dtype': int(core.DataType.FP64)
         }
         self.op_type = 'cast'
 
diff --git a/python/paddle/v2/fluid/tests/test_conditional_block.py b/python/paddle/v2/fluid/tests/test_conditional_block.py
index 293803f004a1513611fba30634d5552e1da84fef..2a30fd107968ce0fa188bda44e731ad760dce1f5 100644
--- a/python/paddle/v2/fluid/tests/test_conditional_block.py
+++ b/python/paddle/v2/fluid/tests/test_conditional_block.py
@@ -9,7 +9,7 @@ import numpy
 
 class ConditionalBlock(unittest.TestCase):
     def test_forward(self):
-        data = layers.data(name='X', shape=[1], data_type='float32')
+        data = layers.data(name='X', shape=[1], dtype='float32')
         data.stop_gradient = False
         cond = layers.ConditionalBlock(inputs=[data])
         out = layers.create_tensor(dtype='float32')
diff --git a/python/paddle/v2/fluid/tests/test_executor_and_mul.py b/python/paddle/v2/fluid/tests/test_executor_and_mul.py
index 709250d0c86dde84ac22c37d8e2385ca4a80a40a..da64739de5eb4eca8db8ac8370276c41692a7242 100644
--- a/python/paddle/v2/fluid/tests/test_executor_and_mul.py
+++ b/python/paddle/v2/fluid/tests/test_executor_and_mul.py
@@ -8,11 +8,11 @@ import numpy
 
 class TestExecutor(unittest.TestCase):
     def test_mul(self):
-        a = data(name='a', shape=[784], data_type='float32')
+        a = data(name='a', shape=[784], dtype='float32')
         b = data(
             name='b',
             shape=[784, 100],
-            data_type='float32',
+            dtype='float32',
             append_batch_size=False)
         out = mul(x=a, y=b)
         place = core.CPUPlace()
diff --git a/python/paddle/v2/fluid/tests/test_image_classification_layer.py b/python/paddle/v2/fluid/tests/test_image_classification_layer.py
index bf5444107fa1609e67b09823b82e5fb92234b0a4..8e8e1b0a8c07a60cb1404462f976d10fe26e87f6 100644
--- a/python/paddle/v2/fluid/tests/test_image_classification_layer.py
+++ b/python/paddle/v2/fluid/tests/test_image_classification_layer.py
@@ -32,7 +32,7 @@ class TestLayer(unittest.TestCase):
         images = layers.data(
             name='pixel',
             shape=[3, 48, 48],
-            data_type='float32',
+            dtype='float32',
             main_program=main_program)
         layers.batch_norm(
             input=images,
@@ -47,7 +47,7 @@ class TestLayer(unittest.TestCase):
         images = layers.data(
             name='pixel',
             shape=[3, 48, 48],
-            data_type='float32',
+            dtype='float32',
             main_program=main_program)
         layers.dropout(
             x=images,
@@ -64,7 +64,7 @@ class TestLayer(unittest.TestCase):
         images = layers.data(
             name='pixel',
             shape=[3, 48, 48],
-            data_type='float32',
+            dtype='float32',
             main_program=main_program,
             startup_program=startup_program)
         conv1 = conv_block(images, 64, 2, [0.3, 0], main_program,
@@ -80,13 +80,13 @@ class TestLayer(unittest.TestCase):
         image1 = layers.data(
             name='pixel1',
             shape=[3, 48, 48],
-            data_type='float32',
+            dtype='float32',
             main_program=main_program,
             startup_program=startup_program)
         image2 = layers.data(
             name='pixel2',
             shape=[3, 48, 48],
-            data_type='float32',
+            dtype='float32',
             main_program=main_program,
             startup_program=startup_program)
         out = layers.elementwise_add(
diff --git a/python/paddle/v2/fluid/tests/test_inference_model_io.py b/python/paddle/v2/fluid/tests/test_inference_model_io.py
index 98b95713b73e8eba93bd6a58eaaed603cfae7952..74f1ce23262bbc969f9544885a7390534c76cdf6 100644
--- a/python/paddle/v2/fluid/tests/test_inference_model_io.py
+++ b/python/paddle/v2/fluid/tests/test_inference_model_io.py
@@ -19,13 +19,13 @@ class TestBook(unittest.TestCase):
         x = layers.data(
             name='x',
             shape=[2],
-            data_type='float32',
+            dtype='float32',
             main_program=program,
             startup_program=init_program)
         y = layers.data(
             name='y',
             shape=[1],
-            data_type='float32',
+            dtype='float32',
             main_program=program,
             startup_program=init_program)
 
diff --git a/python/paddle/v2/fluid/tests/test_layers.py b/python/paddle/v2/fluid/tests/test_layers.py
index f88e0b4e15f7115be21ef136cbb96ce96af9d99e..87dc6d1a6270e0f8425b56601d04049450c73380 100644
--- a/python/paddle/v2/fluid/tests/test_layers.py
+++ b/python/paddle/v2/fluid/tests/test_layers.py
@@ -9,11 +9,11 @@ class TestBook(unittest.TestCase):
     def test_fit_a_line(self):
         program = Program()
         x = layers.data(
-            name='x', shape=[13], data_type='float32', main_program=program)
+            name='x', shape=[13], dtype='float32', main_program=program)
         y_predict = layers.fc(input=x, size=1, act=None, main_program=program)
 
         y = layers.data(
-            name='y', shape=[1], data_type='float32', main_program=program)
+            name='y', shape=[1], dtype='float32', main_program=program)
         cost = layers.square_error_cost(
             input=y_predict, label=y, main_program=program)
 
@@ -28,12 +28,9 @@ class TestBook(unittest.TestCase):
 
         # Change g_program, so the rest layers use `g_program`
         images = layers.data(
-            name='pixel',
-            shape=[784],
-            data_type='float32',
-            main_program=program)
+            name='pixel', shape=[784], dtype='float32', main_program=program)
         label = layers.data(
-            name='label', shape=[1], data_type='int32', main_program=program)
+            name='label', shape=[1], dtype='int32', main_program=program)
         hidden1 = layers.fc(input=images,
                             size=128,
                             act='relu',
@@ -58,7 +55,7 @@ class TestBook(unittest.TestCase):
         images = layers.data(
             name='pixel',
             shape=[3, 48, 48],
-            data_type='int32',
+            dtype='int32',
             main_program=program)
         layers.conv2d(
             input=images,
@@ -74,10 +71,10 @@ class TestBook(unittest.TestCase):
         images = layers.data(
             name='pixel',
             shape=[1, 28, 28],
-            data_type='float32',
+            dtype='float32',
             main_program=program)
         label = layers.data(
-            name='label', shape=[1], data_type='int32', main_program=program)
+            name='label', shape=[1], dtype='int32', main_program=program)
         conv_pool_1 = nets.simple_img_conv_pool(
             input=images,
             filter_size=5,
@@ -112,39 +109,39 @@ class TestBook(unittest.TestCase):
         dict_size = 10000
         embed_size = 32
         first_word = layers.data(
-            name='firstw', shape=[1], data_type='int64', main_program=program)
+            name='firstw', shape=[1], dtype='int64', main_program=program)
         second_word = layers.data(
-            name='secondw', shape=[1], data_type='int64', main_program=program)
+            name='secondw', shape=[1], dtype='int64', main_program=program)
         third_word = layers.data(
-            name='thirdw', shape=[1], data_type='int64', main_program=program)
+            name='thirdw', shape=[1], dtype='int64', main_program=program)
         forth_word = layers.data(
-            name='forthw', shape=[1], data_type='int64', main_program=program)
+            name='forthw', shape=[1], dtype='int64', main_program=program)
         next_word = layers.data(
-            name='nextw', shape=[1], data_type='int64', main_program=program)
+            name='nextw', shape=[1], dtype='int64', main_program=program)
 
         embed_first = layers.embedding(
             input=first_word,
             size=[dict_size, embed_size],
-            data_type='float32',
+            dtype='float32',
             param_attr={'name': 'shared_w'},
             main_program=program)
         embed_second = layers.embedding(
             input=second_word,
             size=[dict_size, embed_size],
-            data_type='float32',
+            dtype='float32',
             param_attr={'name': 'shared_w'},
             main_program=program)
 
         embed_third = layers.embedding(
             input=third_word,
             size=[dict_size, embed_size],
-            data_type='float32',
+            dtype='float32',
             param_attr={'name': 'shared_w'},
             main_program=program)
         embed_forth = layers.embedding(
             input=forth_word,
             size=[dict_size, embed_size],
-            data_type='float32',
+            dtype='float32',
             param_attr={'name': 'shared_w'},
             main_program=program)
 
@@ -173,12 +170,9 @@ class TestBook(unittest.TestCase):
 
         # Change g_program, so the rest layers use `g_program`
         images = layers.data(
-            name='pixel',
-            shape=[784],
-            data_type='float32',
-            main_program=program)
+            name='pixel', shape=[784], dtype='float32', main_program=program)
         label = layers.data(
-            name='label', shape=[1], data_type='int32', main_program=program)
+            name='label', shape=[1], dtype='int32', main_program=program)
         hidden = layers.fc(input=images, size=128, main_program=program)
         crf = layers.linear_chain_crf(
             input=hidden, label=label, main_program=program)
diff --git a/python/paddle/v2/fluid/tests/test_lod_tensor_array_ops.py b/python/paddle/v2/fluid/tests/test_lod_tensor_array_ops.py
index b18cb6b49fa41f26e1b6de1128690507c5a2f099..16e64b8cd52d72a3bbc84e43d772b843dad0129a 100644
--- a/python/paddle/v2/fluid/tests/test_lod_tensor_array_ops.py
+++ b/python/paddle/v2/fluid/tests/test_lod_tensor_array_ops.py
@@ -132,7 +132,7 @@ class TestCPULoDTensorArrayOpGrad(unittest.TestCase):
         x = layers.data(
             name='x',
             shape=[1],
-            data_type='float32',
+            dtype='float32',
             main_program=program,
             stop_gradient=False)
         table = layers.lod_rank_table(x, level=0, main_program=program)
diff --git a/python/paddle/v2/fluid/tests/test_mnist_if_else_op.py b/python/paddle/v2/fluid/tests/test_mnist_if_else_op.py
index 8af99005dc0b5d50de60ca89c2ddf870b1537edb..e76357a5be07d79eafee4c3a27911efe8a3eaef4 100644
--- a/python/paddle/v2/fluid/tests/test_mnist_if_else_op.py
+++ b/python/paddle/v2/fluid/tests/test_mnist_if_else_op.py
@@ -11,10 +11,9 @@ import numpy as np
 class TestMNISTIfElseOp(unittest.TestCase):
     def test_raw_api(self):
         kwargs = {'startup_program': Program(), 'main_program': Program()}
-        image = layers.data(
-            name='x', shape=[784], data_type='float32', **kwargs)
+        image = layers.data(name='x', shape=[784], dtype='float32', **kwargs)
 
-        label = layers.data(name='y', shape=[1], data_type='int64', **kwargs)
+        label = layers.data(name='y', shape=[1], dtype='int64', **kwargs)
 
         limit = layers.fill_constant_batch_size_like(
             input=label, dtype='int64', shape=[1], value=5.0, **kwargs)
@@ -84,10 +83,9 @@ class TestMNISTIfElseOp(unittest.TestCase):
 
     def test_ifelse(self):
         kwargs = {'startup_program': Program(), 'main_program': Program()}
-        image = layers.data(
-            name='x', shape=[784], data_type='float32', **kwargs)
+        image = layers.data(name='x', shape=[784], dtype='float32', **kwargs)
 
-        label = layers.data(name='y', shape=[1], data_type='int64', **kwargs)
+        label = layers.data(name='y', shape=[1], dtype='int64', **kwargs)
 
         limit = layers.fill_constant_batch_size_like(
             input=label, dtype='int64', shape=[1], value=5.0, **kwargs)
diff --git a/python/paddle/v2/fluid/tests/test_parameter.py b/python/paddle/v2/fluid/tests/test_parameter.py
index a633d22c2b1db2728b6eb767078ce4aec6cce163..d467e4bbb79b291c442c643158ef6c0d630920dd 100644
--- a/python/paddle/v2/fluid/tests/test_parameter.py
+++ b/python/paddle/v2/fluid/tests/test_parameter.py
@@ -20,7 +20,7 @@ class TestParameter(unittest.TestCase):
         self.assertIsNotNone(param)
         self.assertEqual('fc.w', param.name)
         self.assertEqual((784, 100), param.shape)
-        self.assertEqual(core.DataType.FP32, param.data_type)
+        self.assertEqual(core.DataType.FP32, param.dtype)
         self.assertEqual(0, param.block.idx)
         exe = Executor(core.CPUPlace())
         p = exe.run(g_main_program, fetch_list=[param])[0]
diff --git a/python/paddle/v2/fluid/tests/test_protobuf_descs.py b/python/paddle/v2/fluid/tests/test_protobuf_descs.py
index 098a9802dfc6763ce2a2356b7267a439145b7939..d8abe17606c4ddb2ff51d5f918b1e5d7e110f7fa 100644
--- a/python/paddle/v2/fluid/tests/test_protobuf_descs.py
+++ b/python/paddle/v2/fluid/tests/test_protobuf_descs.py
@@ -101,13 +101,13 @@ class TestVarDesc(unittest.TestCase):
         self.assertEqual(src_shape, res_shape)
         self.assertEqual(core.VarDesc.VarType.SELECTED_ROWS, var.type())
 
-    def test_data_type(self):
+    def test_dtype(self):
         program_desc = core.ProgramDesc()
         block = program_desc.block(0)
         var = block.var('my_var')
         var.set_type(core.VarDesc.VarType.LOD_TENSOR)
-        var.set_data_type(core.DataType.INT32)
-        self.assertEqual(core.DataType.INT32, var.data_type())
+        var.set_dtype(core.DataType.INT32)
+        self.assertEqual(core.DataType.INT32, var.dtype())
         self.assertEqual(core.VarDesc.VarType.LOD_TENSOR, var.type())
 
 
diff --git a/python/paddle/v2/fluid/tests/test_recurrent_op.py b/python/paddle/v2/fluid/tests/test_recurrent_op.py
index b623d1231838faff9e91c9234befb1f647fe8ec2..88bcdc3e6a21881ace2be53c22a62d78df30a974 100644
--- a/python/paddle/v2/fluid/tests/test_recurrent_op.py
+++ b/python/paddle/v2/fluid/tests/test_recurrent_op.py
@@ -118,14 +118,14 @@ class RecurrentOpTest1(unittest.TestCase):
     def create_rnn_op(self):
         x = layers.data(
             shape=[self.sent_len, self.batch_size, self.input_dim],
-            data_type='float32',
+            dtype='float32',
             name='x',
             append_batch_size=False,
             **self.p_info)
         x.stop_gradient = False
         h_boot = layers.data(
             shape=[self.input_dim],
-            data_type='float32',
+            dtype='float32',
             name='h_boot',
             **self.p_info)
         h_boot.stop_gradient = False
@@ -251,14 +251,14 @@ class RecurrentOpTest2(RecurrentOpTest1):
     def create_rnn_op(self):
         x = layers.data(
             shape=[self.sent_len, self.batch_size, self.input_dim],
-            data_type='float32',
+            dtype='float32',
             name='x',
             append_batch_size=False,
             **self.p_info)
         x.stop_gradient = False
         h_boot = layers.data(
             shape=[self.input_dim],
-            data_type='float32',
+            dtype='float32',
             name='h_boot',
             **self.p_info)
         h_boot.stop_gradient = False
@@ -350,21 +350,21 @@ class RecurrentOpMultipleMemoryTest(RecurrentOpTest1):
     def create_rnn_op(self):
         x = layers.data(
             shape=[self.sent_len, self.batch_size, self.input_dim],
-            data_type='float32',
+            dtype='float32',
             name='x',
             append_batch_size=False,
             **self.p_info)
         x.stop_gradient = False
         h_boot1 = layers.data(
             shape=[self.batch_size, self.input_dim],
-            data_type='float32',
+            dtype='float32',
             name='h_boot1',
             append_batch_size=False,
             **self.p_info)
         h_boot1.stop_gradient = False
         h_boot2 = layers.data(
             shape=[self.batch_size, self.input_dim],
-            data_type='float32',
+            dtype='float32',
             name='h_boot2',
             append_batch_size=False,
             **self.p_info)
@@ -435,7 +435,7 @@ class RecurrentOpNoMemBootTest(RecurrentOpTest1):
     def create_rnn_op(self):
         x = layers.data(
             shape=[self.sent_len, self.batch_size, self.input_dim],
-            data_type='float32',
+            dtype='float32',
             name='x',
             append_batch_size=False,
             **self.p_info)
diff --git a/python/paddle/v2/fluid/tests/test_shrink_rnn_memory.py b/python/paddle/v2/fluid/tests/test_shrink_rnn_memory.py
index 1a3b88e18e38b88d75ad17a0bb6a2965d1e60406..953629d610e183cdddf97081f94a77951fe979d8 100644
--- a/python/paddle/v2/fluid/tests/test_shrink_rnn_memory.py
+++ b/python/paddle/v2/fluid/tests/test_shrink_rnn_memory.py
@@ -9,7 +9,7 @@ import numpy
 
 class TestShrinkRNNMemory(unittest.TestCase):
     def test_shrink_rnn_memory(self):
-        x = layers.data('x', shape=[100], data_type='float32')
+        x = layers.data('x', shape=[100], dtype='float32')
         x.stop_gradient = False
         table = layers.lod_rank_table(x=x)
         i = layers.zeros(dtype='int64', shape=[1])
diff --git a/python/paddle/v2/fluid/tests/test_split_and_merge_lod_tensor_op.py b/python/paddle/v2/fluid/tests/test_split_and_merge_lod_tensor_op.py
index 3aed83b2ea3418c54f9540279ae6e2e0045421fa..a98cb3bbab8442886206b59a2b591fee96deeb9f 100644
--- a/python/paddle/v2/fluid/tests/test_split_and_merge_lod_tensor_op.py
+++ b/python/paddle/v2/fluid/tests/test_split_and_merge_lod_tensor_op.py
@@ -123,13 +123,13 @@ class TestCPUSplitMergeLoDTensorGrad(unittest.TestCase):
         x = layers.data(
             name='x',
             shape=[1],
-            data_type='float32',
+            dtype='float32',
             main_program=program,
             stop_gradient=False)
         y = layers.data(
             name='y',
             shape=[1],
-            data_type='bool',
+            dtype='bool',
             main_program=program,
             stop_gradient=False)
 
diff --git a/python/paddle/v2/fluid/tests/test_variable.py b/python/paddle/v2/fluid/tests/test_variable.py
index c3e1f9ac0a70e7448fd8d1983b1c04d27af9771c..92ffdceb6c84fb2669f8c1bb556c46fb1c03c411 100644
--- a/python/paddle/v2/fluid/tests/test_variable.py
+++ b/python/paddle/v2/fluid/tests/test_variable.py
@@ -22,13 +22,13 @@ class TestVariable(unittest.TestCase):
         w = b.create_var(
             dtype="float64", shape=[784, 100], lod_level=0, name="fc.w")
         self.assertNotEqual(str(w), "")
-        self.assertEqual(core.DataType.FP64, w.data_type)
+        self.assertEqual(core.DataType.FP64, w.dtype)
         self.assertEqual((784, 100), w.shape)
         self.assertEqual("fc.w", w.name)
         self.assertEqual(0, w.lod_level)
 
         w = b.create_var(name='fc.w')
-        self.assertEqual(core.DataType.FP64, w.data_type)
+        self.assertEqual(core.DataType.FP64, w.dtype)
         self.assertEqual((784, 100), w.shape)
         self.assertEqual("fc.w", w.name)
         self.assertEqual(0, w.lod_level)
diff --git a/python/paddle/v2/fluid/tests/test_while_op.py b/python/paddle/v2/fluid/tests/test_while_op.py
index 84b432333f950f754a97bc1a051b59c16fb22aed..fca0cdcc319ff661ced33b6bcd242c894941576c 100644
--- a/python/paddle/v2/fluid/tests/test_while_op.py
+++ b/python/paddle/v2/fluid/tests/test_while_op.py
@@ -9,11 +9,11 @@ import numpy
 class TestWhileOp(unittest.TestCase):
     def test_simple_forward(self):
         d0 = layers.data(
-            "d0", shape=[10], append_batch_size=False, data_type='float32')
+            "d0", shape=[10], append_batch_size=False, dtype='float32')
         d1 = layers.data(
-            "d1", shape=[10], append_batch_size=False, data_type='float32')
+            "d1", shape=[10], append_batch_size=False, dtype='float32')
         d2 = layers.data(
-            "d2", shape=[10], append_batch_size=False, data_type='float32')
+            "d2", shape=[10], append_batch_size=False, dtype='float32')
         i = layers.zeros(shape=[1], dtype='int64')
         i.stop_gradient = True
         init = layers.zeros(shape=[10], dtype='float32')