diff --git a/python/paddle/v2/framework/framework.py b/python/paddle/v2/framework/framework.py
index f8d2f67410a6c06a1642180d2d62c881ec6bda3d..b3493fc378f4d866d16a6a0a739e0ccc8e44d97c 100644
--- a/python/paddle/v2/framework/framework.py
+++ b/python/paddle/v2/framework/framework.py
@@ -354,8 +354,8 @@ class Block(object):
 
     def create_var(self, *args, **kwargs):
         var = Variable(self, *args, **kwargs)
-        if 'init_attr' in kwargs:
-            self._prepend_initialize_ops_(var, kwargs['init_attr'])
+        if 'initializer' in kwargs:
+            kwargs['initializer'](var, self)
         return var
 
     def has_var(self, name):
@@ -364,8 +364,8 @@ class Block(object):
     def create_parameter(self, *args, **kwargs):
         global_block = self.program.global_block()
         param = Parameter(global_block, *args, **kwargs)
-        if 'init_attr' in kwargs:
-            self._prepend_initialize_ops_(param, kwargs['init_attr'])
+        if 'initializer' in kwargs:
+            kwargs['initializer'](param, self)
         return param
 
     def append_op(self, *args, **kwargs):
@@ -424,17 +424,6 @@ class Block(object):
         for index in range(len(self.ops)):
             assert self.ops[index].desc == ops_in_cpp[index]
 
-    def _prepend_initialize_ops_(self, param, init_attr):
-        op_type = init_attr['type']
-        init_attr['shape'] = param.shape
-        init_attr['data_type'] = int(param.data_type)
-        op = self.prepend_op(
-            type=op_type,
-            inputs=None,
-            outputs={'Out': [param]},
-            attrs=init_attr)
-        param.op = op
-
 
 class Program(object):
     def __init__(self):
diff --git a/python/paddle/v2/framework/initializer.py b/python/paddle/v2/framework/initializer.py
new file mode 100644
index 0000000000000000000000000000000000000000..377d33271355651e6dbda0d31da0692f1a4c883d
--- /dev/null
+++ b/python/paddle/v2/framework/initializer.py
@@ -0,0 +1,109 @@
+import paddle.v2.framework.framework as framework
+
+__all__ = ['ConstantInitializer', 'UniformInitializer']
+
+
+class Initializer(object):
+    """Base class for variable initializers
+
+    Defines the common interface of variable initializers.
+    They add operations to the init program that are used
+    to initialize variables. Users should not use this class
+    directly, but need to use one of its implementations.
+    """
+
+    def __init_(self):
+        pass
+
+    def __call__(self, param, block):
+        """Add corresponding initialization operations to the network
+        """
+        raise NotImplementedError()
+
+
+class ConstantInitializer(Initializer):
+    """Implements the constant initializer
+    """
+
+    def __init__(self, value=0.0):
+        """Constructor for ConstantInitializer
+
+        Args:
+            value: constant value to initialize the variable
+        """
+        assert value is not None
+        super(ConstantInitializer, self).__init__()
+        self._value = value
+
+    def __call__(self, var, block):
+        """Add constant initialization ops for a variable
+
+        Args:
+            var: Variable that needs to be initialized
+            block: The block in which initialization ops
+                   should be added
+
+        Returns:
+            the initialization op
+        """
+        assert isinstance(var, framework.Variable)
+        assert isinstance(block, framework.Block)
+        # Initialization Ops should be prepended and not appended
+        op = block.prepend_op(
+            type="fill_constant",
+            outputs={"Out": var},
+            attrs={
+                "shape": var.shape,
+                "data_type": int(var.data_type),
+                "value": self._value
+            })
+        var.op = op
+        return op
+
+
+class UniformInitializer(Initializer):
+    """Implements for random uniform distribution initializer
+    """
+
+    def __init__(self, low=-1.0, high=1.0, seed=0):
+        """Constructor for UniformInitializer
+
+        Args:
+            low: lower boundary of the uniform distribution
+            high: upper boundary of the uniform distribution
+            seed: random seed
+        """
+        assert low is not None
+        assert high is not None
+        assert seed is not None
+        super(UniformInitializer, self).__init__()
+        self._low = low
+        self._high = high
+        self._seed = seed
+
+    def __call__(self, var, block):
+        """Add uniform distribution initialization ops for a variable
+
+        Args:
+            var: Variable that needs to be initialized
+            block: The block in which initialization ops
+                   should be added
+
+        Returns:
+            the initialization op
+        """
+        assert isinstance(var, framework.Variable)
+        assert isinstance(block, framework.Block)
+        # Initialization Ops should be prepended and not appended
+        op = block.prepend_op(
+            type="uniform_random",
+            outputs={"Out": var},
+            attrs={
+                "shape": var.shape,
+                "data_type": int(var.data_type),
+                "min": self._low,
+                "max": self._high,
+                "seed": self._seed
+            })
+        var.op = op
+        return op
diff --git a/python/paddle/v2/framework/layer_helper.py b/python/paddle/v2/framework/layer_helper.py
index d96dbe172c22617182e7ebf4aab175c6142352b7..c57776441c32e39bfa93a9fdf09dba238359af7b 100644
--- a/python/paddle/v2/framework/layer_helper.py
+++ b/python/paddle/v2/framework/layer_helper.py
@@ -5,6 +5,8 @@ import paddle.v2.framework.core as core
 
 from paddle.v2.framework.framework import Variable, g_program, \
     g_init_program
+from paddle.v2.framework.initializer import ConstantInitializer, \
+    UniformInitializer
 
 
 def unique_name(prefix):
@@ -66,14 +68,7 @@ class LayerHelper(object):
 
     @property
     def param_attr(self):
-        default = {
-            'name': None,
-            'init_attr': {
-                'type': 'uniform_random',
-                'min': -1.0,
-                'max': 1.0
-            }
-        }
+        default = {'name': None, 'initializer': UniformInitializer()}
         actual = self.kwargs.get('param_attr', None)
         if actual is None:
             actual = default
@@ -83,13 +78,7 @@ class LayerHelper(object):
         return actual
 
     def bias_attr(self):
-        default = {
-            'name': None,
-            'init_attr': {
-                'type': 'fill_constant',
-                'value': 0.0
-            }
-        }
+        default = {'name': None, 'initializer': ConstantInitializer()}
         bias_attr = self.kwargs.get('bias_attr', None)
         if bias_attr is True:
             bias_attr = default
diff --git a/python/paddle/v2/framework/layers.py b/python/paddle/v2/framework/layers.py
index 5fdad52f2124da4568f685851d12d3660dcac78f..dab72f0195fd9f7ec8219be7867e8ddde9036db9 100644
--- a/python/paddle/v2/framework/layers.py
+++ b/python/paddle/v2/framework/layers.py
@@ -1,6 +1,7 @@
 from paddle.v2.framework.layer_helper import LayerHelper, unique_name
 import paddle.v2.framework.core as core
 from paddle.v2.framework.framework import OpProtoHolder, Variable, Program
+from paddle.v2.framework.initializer import ConstantInitializer
 import re
 
 __all__ = [
@@ -440,26 +441,12 @@ def batch_norm(input,
         else:
             raise ValueError("unsupported data layout:" + data_layout)
 
-    def get_init_attr(value):
-        if not isinstance(value, float):
-            raise ValueError("attr value should be a float")
-        return {'type': 'fill_constant', 'value': value}
-
-    def prepend_init_op(var, init_attr):
-        assert isinstance(var, Variable)
-        op_type = init_attr['type']
-        init_attr['shape'] = var.shape
-        init_attr['data_type'] = int(var.data_type)
-        op = var.block.prepend_op(
-            type=op_type, inputs=None, outputs={'Out': [var]}, attrs=init_attr)
-        return op
-
-    def create_persistable_var(dtype, shape, init_attr=None):
+    def create_persistable_var(dtype, shape, initializer=None):
         name = unique_name(".".join([helper.name, "xxxx"]))
         var = init_program.global_block().create_var(
             dtype=dtype, shape=shape, name=name, persistable=True)
-        if 'init_attr' is not None:
-            prepend_init_op(var, init_attr)
+        if initializer is not None:
+            initializer(var, var.block)
         return program.global_block().create_var(
             name=name, dtype=dtype, shape=shape, persistable=True)
 
@@ -472,8 +459,9 @@ def batch_norm(input,
         attr=helper.param_attr, shape=param_shape, dtype=dtype)
 
     # create input
-    mean = create_persistable_var(dtype, param_shape, get_init_attr(0.0))
-    variance = create_persistable_var(dtype, param_shape, get_init_attr(1.0))
+    mean = create_persistable_var(dtype, param_shape, ConstantInitializer(0.0))
+    variance = create_persistable_var(dtype, param_shape,
+                                      ConstantInitializer(1.0))
 
     # create output
     # mean and mean_out share the same memory
diff --git a/python/paddle/v2/framework/tests/test_recognize_digits_mlp.py b/python/paddle/v2/framework/tests/test_recognize_digits_mlp.py
index a8a34b2a952c8d374089ab8142b530610b2afe59..9916569d042d5d5077732281487ca3ae4366b39c 100644
--- a/python/paddle/v2/framework/tests/test_recognize_digits_mlp.py
+++ b/python/paddle/v2/framework/tests/test_recognize_digits_mlp.py
@@ -3,9 +3,10 @@ import paddle.v2.framework.layers as layers
 import paddle.v2.framework.core as core
 import paddle.v2.framework.optimizer as optimizer
 
-from paddle.v2.framework.framework import Program, g_program
+from paddle.v2.framework.framework import Program
 from paddle.v2.framework.executor import Executor
 from paddle.v2.framework.regularizer import L2DecayRegularizer
+from paddle.v2.framework.initializer import UniformInitializer
 
 import numpy as np
 
@@ -21,11 +22,8 @@ image = layers.data(
 
 param_attr = {
     'name': None,
-    'init_attr': {
-        'type': 'uniform_random',
-        'min': -1.0,
-        'max': 1.0
-    },
+    'initializer': UniformInitializer(
+        low=-1.0, high=1.0),
     'regularization': L2DecayRegularizer(0.0005 * BATCH_SIZE)
 }