diff --git a/python/paddle/trainer/config_parser.py b/python/paddle/trainer/config_parser.py
index b7418101d83fde1b91781d3a42b056cc7708cba9..2965c922fa60bb00b77410563b040013af251ce6 100644
--- a/python/paddle/trainer/config_parser.py
+++ b/python/paddle/trainer/config_parser.py
@@ -1741,6 +1741,59 @@ class ParameterReluLayer(LayerBase):
         self.create_input_parameter(0, input_layer.size / partial_sum)
 
 
+@config_layer('depthwise_conv')
+class DepthwiseConvLayer(LayerBase):
+    layer_type = 'depthwise_conv'
+
+    def __init__(self,
+                 name,
+                 inputs=[],
+                 bias=True,
+                 num_filters=None,
+                 shared_biases=False,
+                 **xargs):
+        super(DepthwiseConvLayer, self).__init__(
+            name, self.layer_type, 0, inputs=inputs, **xargs)
+
+        if num_filters is not None:
+            self.config.num_filters = num_filters
+
+        use_gpu = int(g_command_config_args.get("use_gpu", 0))
+        parallel_nn = int(g_command_config_args.get("parallel_nn", 0))
+
+        # Automatically select cudnn_type for GPU and exconv for CPU
+        # if set type=conv, but still reserve the way user specify
+        # exconv or cudnn_conv manually.
+        self.layer_type = "depthwise_conv"
+        # need to specify layer in config
+        self.config.type = self.layer_type
+
+        if shared_biases is not None:
+            self.config.shared_biases = shared_biases
+
+        for input_index in xrange(len(self.inputs)):
+            input_layer = self.get_input_layer(input_index)
+            conv_conf = self.config.inputs[input_index].conv_conf
+            #set the groups
+            self.inputs[input_index].conv.groups = self.inputs[
+                input_index].conv.channels
+            parse_conv(self.inputs[input_index].conv, input_layer.name,
+                       conv_conf, num_filters)
+            psize = self.calc_parameter_size(conv_conf)
+            self.create_input_parameter(input_index, psize)
+            self.set_cnn_layer(name, conv_conf.output_y, conv_conf.output_x,
+                               self.config.num_filters)
+
+        psize = self.config.size
+        if shared_biases:
+            psize = self.config.num_filters
+        self.create_bias_parameter(bias, psize, [psize, 1])
+
+    def calc_parameter_size(self, conv_conf):
+        return self.config.num_filters * conv_conf.filter_channels \
+                    * (conv_conf.filter_size * conv_conf.filter_size_y)
+
+
 @config_layer('conv')
 class ConvLayerBase(LayerBase):
     layer_type = 'conv'
@@ -3145,6 +3198,10 @@ def ParameterHook(type, **kwargs):
         if sparsity_ratio is not None:
             hook.sparsity_ratio = sparsity_ratio
         return hook
+    elif type == 'dpruning':
+        hook = ParameterUpdaterHookConfig()
+        hook.type = type
+        return hook
     else:
         return None
 
diff --git a/python/paddle/trainer_config_helpers/layers.py b/python/paddle/trainer_config_helpers/layers.py
index a601d5c84ad222785e68b9fa81c51b1e120b4f29..073e853bc2d1bace19bae3aa8a9a0c08c869bdeb 100755
--- a/python/paddle/trainer_config_helpers/layers.py
+++ b/python/paddle/trainer_config_helpers/layers.py
@@ -57,6 +57,7 @@ __all__ = [
     'classification_cost',
     'LayerOutput',
     'img_conv_layer',
+    'img_depthwise_conv_layer',
     'img_pool_layer',
     'batch_norm_layer',
     'img_cmrnorm_layer',
@@ -148,6 +149,7 @@ class LayerType(object):
     HSIGMOID = 'hsigmoid'
     CONV_LAYER = 'conv'
     CONVTRANS_LAYER = 'convt'
+    DEPTHWISE_CONV_LAYER = 'depthwise_conv'
     EXCONV_LAYER = 'exconv'
     EXCONVTRANS_LAYER = 'exconvt'
     CUDNNCONV_LAYER = 'cudnn_conv'
@@ -2085,6 +2087,94 @@ def hsigmoid(input,
         name, LayerType.HSIGMOID, parents=parents, size=l.config.size)
 
 
+@wrap_name_default("depthwise_conv")
+@wrap_param_attr_default()
+@wrap_bias_attr_default()
+@wrap_act_default(act=ReluActivation())
+@layer_support(DROPOUT)
+def img_depthwise_conv_layer(input,
+                             filter_size,
+                             num_filters,
+                             name=None,
+                             num_channels=None,
+                             act=None,
+                             groups=1,
+                             stride=1,
+                             padding=0,
+                             bias_attr=None,
+                             param_attr=None,
+                             shared_biases=True,
+                             layer_attr=None,
+                             filter_size_y=None,
+                             stride_y=None,
+                             padding_y=None,
+                             trans=False,
+                             layer_type=None):
+
+    if num_channels is None:
+        assert input.num_filters is not None
+        num_channels = input.num_filters
+
+    if filter_size_y is None:
+        if isinstance(filter_size, collections.Sequence):
+            assert len(filter_size) == 2
+            filter_size, filter_size_y = filter_size
+        else:
+            filter_size_y = filter_size
+
+    if stride_y is None:
+        if isinstance(stride, collections.Sequence):
+            assert len(stride) == 2
+            stride, stride_y = stride
+        else:
+            stride_y = stride
+
+    if padding_y is None:
+        if isinstance(padding, collections.Sequence):
+            assert len(padding) == 2
+            padding, padding_y = padding
+        else:
+            padding_y = padding
+
+    if param_attr.attr.get('initial_smart'):
+        # special initial for conv layers.
+        init_w = (2.0 / (filter_size**2 * num_channels))**0.5
+        param_attr.attr["initial_mean"] = 0.0
+        param_attr.attr["initial_std"] = init_w
+        param_attr.attr["initial_strategy"] = 0
+        param_attr.attr["initial_smart"] = False
+
+    lt = LayerType.DEPTHWISE_CONV_LAYER
+
+    l = Layer(
+        name=name,
+        inputs=Input(
+            input.name,
+            conv=Conv(
+                filter_size=filter_size,
+                padding=padding,
+                stride=stride,
+                channels=num_channels,
+                groups=groups,
+                filter_size_y=filter_size_y,
+                padding_y=padding_y,
+                stride_y=stride_y),
+            **param_attr.attr),
+        active_type=act.name,
+        num_filters=num_filters,
+        bias=ParamAttr.to_bias(bias_attr),
+        shared_biases=shared_biases,
+        type=lt,
+        **ExtraLayerAttribute.to_kwargs(layer_attr))
+    return LayerOutput(
+        name,
+        lt,
+        parents=[input],
+        activation=act,
+        num_filters=num_filters,
+        size=l.config.size)
+
+
 @wrap_name_default("conv")
 @wrap_param_attr_default()
 @wrap_bias_attr_default()