Add lrn layer

doc/fluid/dev/src/fc.py

@@ -79,3 +79,45 @@ def fc(input,
           data = fluid.layers.data(name="data", shape=[32, 32], dtype="float32")
           fc = fluid.layers.fc(input=data, size=1000, act="tanh")
     """
+
+
+def lrn(input, n=5, k=2.0, alpha=1e-4, beta=0.75, name=None):
+    """
+    **Local Response Normalization Operator**
+
+    This operator comes from the paper:
+    <<ImageNet Classification with Deep Convolutional Neural Networks>>.
+
+    .. math::
+
+        Output(i, x, y) = Input(i, x, y) / \left(
+        k + \alpha \sum\limits^{\min(C, c + n/2)}_{j = \max(0, c - n/2)}
+        (Input(j, x, y))^2 \right)^{\beta}
+
+    In the above equation:
+
+    * :math:`n`: The number of channels to sum over.
+    * :math:`k`: The offset (usually positive to avoid dividing by 0).
+    * :math:`alpha`: The scaling parameter.
+    * :math:`beta`: The exponent.
+
+    Args:
+        input(Variable): The input tensor of this layer. The dims of the input tensor must be 4 and it's order should be 'NCHW'.
+        n(int, default 5): The number of channels to sum over.
+        k(float, default 2.0): An offset (usually positive to avoid dividing by 0).
+        alpha(float, default 1e-4): The scaling parameter.
+        beta(float, default 0.75): The exponent.
+        name(str, default None): A name for this operation.
+
+    Raises:
+        ValueError: If rank of the input tensor is not 4.
+
+    Returns:
+        A tensor variable storing the transformation result.
+
+    Examples:
+        .. code-block:: python
+
+          data = fluid.layers.data(name="data", shape=[3, 112, 112], dtype="float32")
+          lrn = fluid.layers.lrn(input=data)
+    """

python/paddle/fluid/layers/nn.py

@@ -73,6 +73,7 @@
     'smooth_l1',
     'one_hot',
     'autoincreased_step_counter',
+    'lrn',
 ]
 
 
@@ -3292,3 +3293,70 @@ def autoincreased_step_counter(counter_name=None, begin=1, step=1):
         counter.stop_gradient = True
 
     return counter
+
+
+def lrn(input, n=5, k=2.0, alpha=1e-4, beta=0.75, name=None):
+    """
+    **Local Response Normalization Operator**
+
+    This operator comes from the paper:
+    <<ImageNet Classification with Deep Convolutional Neural Networks>>.
+
+    .. math::
+
+        Output(i, x, y) = Input(i, x, y) / \left(
+        k + \alpha \sum\limits^{\min(C, c + n/2)}_{j = \max(0, c - n/2)}
+        (Input(j, x, y))^2 \right)^{\beta}
+
+    In the above equation:
+
+    * :math:`n`: The number of channels to sum over.
+    * :math:`k`: The offset (usually positive to avoid dividing by 0).
+    * :math:`alpha`: The scaling parameter.
+    * :math:`beta`: The exponent parameter.
+
+    Args:
+        input(Variable): The input tensor of this layer, and the dims of the input tensor must be 4.
+        n(int, default 5): The number of channels to sum over.
+        k(float, default 2.0): An offset (usually positive to avoid dividing by 0).
+        alpha(float, default 1e-4): The scaling parameter.
+        beta(float, default 0.75): The exponent.
+        name(str, default None): A name for this operation.
+
+    Raises:
+        ValueError: If rank of the input tensor is not 4.
+
+    Returns:
+        A tensor variable storing the transformation result.
+
+    Examples:
+        .. code-block:: python
+
+          data = fluid.layers.data(name="data", shape=[3, 112, 112], dtype="float32")
+          lrn = fluid.layers.lrn(input=data)
+    """
+    helper = LayerHelper('lrn', **locals())
+    dtype = helper.input_dtype()
+    input_shape = input.shape
+    dims = len(input_shape)
+
+    if dims != 4:
+        raise ValueError(
+            "dims of input must be 4(not %d), and it's order must be NCHW" %
+            (dims))
+
+    mid_out = helper.create_tmp_variable(dtype=dtype, stop_gradient=True)
+    lrn_out = helper.create_tmp_variable(dtype)
+    helper.append_op(
+        type="lrn",
+        inputs={"X": input},
+        outputs={
+            "Out": lrn_out,
+            "MidOut": mid_out,
+        },
+        attrs={"n": n,
+               "k": k,
+               "alpha": alpha,
+               "beta": beta})
+
+    return lrn_out

python/paddle/fluid/tests/unittests/test_layers.py

@@ -231,6 +231,13 @@ def test_softmax(self):
             self.assertIsNotNone(layers.softmax(hid))
         print(str(program))
 
+    def test_lrn(self):
+        program = Program()
+        with program_guard(program):
+            data = layers.data(name='data', shape=[6, 2, 2], dtype='float32')
+            self.assertIsNotNone(layers.lrn(data))
+        print(str(program))
+
     def test_get_places(self):
         program = Program()
         with program_guard(program):