move tree_conv to fluid.contrib.layers (#19918)

* move tree_conv to fluid.contrib.layers

test=develop

* update API.spec for tree_conv

test=develop

* update tree_conv api to increase unit coverage

test=develop

paddle/fluid/API.spec

@@ -285,7 +285,6 @@ paddle.fluid.layers.prroi_pool (ArgSpec(args=['input', 'rois', 'output_channels'
 paddle.fluid.layers.teacher_student_sigmoid_loss (ArgSpec(args=['input', 'label', 'soft_max_up_bound', 'soft_max_lower_bound'], varargs=None, keywords=None, defaults=(15.0, -15.0)), ('document', '07cb0d95a646dba1b9cc7cdce89e59f0'))
 paddle.fluid.layers.huber_loss (ArgSpec(args=['input', 'label', 'delta'], varargs=None, keywords=None, defaults=None), ('document', '11bb8e62cc9256958eff3991fe4834da'))
 paddle.fluid.layers.kldiv_loss (ArgSpec(args=['x', 'target', 'reduction', 'name'], varargs=None, keywords=None, defaults=('mean', None)), ('document', '18bc95c62d3300456c3c7da5278b47bb'))
-paddle.fluid.layers.tree_conv (ArgSpec(args=['nodes_vector', 'edge_set', 'output_size', 'num_filters', 'max_depth', 'act', 'param_attr', 'bias_attr', 'name'], varargs=None, keywords=None, defaults=(1, 2, 'tanh', None, None, None)), ('document', '864f3cdc5e0c6152e2a39b136171644f'))
 paddle.fluid.layers.npair_loss (ArgSpec(args=['anchor', 'positive', 'labels', 'l2_reg'], varargs=None, keywords=None, defaults=(0.002,)), ('document', '6b6ee1170fe20a79cf0631a1f49b0df2'))
 paddle.fluid.layers.pixel_shuffle (ArgSpec(args=['x', 'upscale_factor'], varargs=None, keywords=None, defaults=None), ('document', '7e5cac851fd9bad344230e1044b6a565'))
 paddle.fluid.layers.fsp_matrix (ArgSpec(args=['x', 'y'], varargs=None, keywords=None, defaults=None), ('document', '20992b20d19c2e5983f366150827b4a6'))
@@ -519,6 +518,7 @@ paddle.fluid.contrib.fused_elemwise_activation (ArgSpec(args=['x', 'y', 'functor
 paddle.fluid.contrib.sequence_topk_avg_pooling (ArgSpec(args=['input', 'row', 'col', 'topks', 'channel_num'], varargs=None, keywords=None, defaults=None), ('document', '5218c85dd4122b626da9bb92f3b50042'))
 paddle.fluid.contrib.var_conv_2d (ArgSpec(args=['input', 'row', 'col', 'input_channel', 'output_channel', 'filter_size', 'stride', 'param_attr', 'act', 'dtype', 'name'], varargs=None, keywords=None, defaults=(1, None, None, 'float32', None)), ('document', 'f52a6edf6d3e970568788604da3329c2'))
 paddle.fluid.contrib.match_matrix_tensor (ArgSpec(args=['x', 'y', 'channel_num', 'act', 'param_attr', 'dtype', 'name'], varargs=None, keywords=None, defaults=(None, None, 'float32', None)), ('document', '3bdc4b2891c1460bc630fdcd22766b21'))
+paddle.fluid.contrib.tree_conv (ArgSpec(args=['nodes_vector', 'edge_set', 'output_size', 'num_filters', 'max_depth', 'act', 'param_attr', 'bias_attr', 'name'], varargs=None, keywords=None, defaults=(1, 2, 'tanh', None, None, None)), ('document', '7c727562ebdda38274106d1a9b338e5b'))
 paddle.fluid.contrib.BasicGRUUnit ('paddle.fluid.contrib.layers.rnn_impl.BasicGRUUnit', ('document', '2aed2540ed1540f081be9f4d08f2a65e'))
 paddle.fluid.contrib.BasicGRUUnit.__init__ (ArgSpec(args=['self', 'name_scope', 'hidden_size', 'param_attr', 'bias_attr', 'gate_activation', 'activation', 'dtype'], varargs=None, keywords=None, defaults=(None, None, None, None, 'float32')), ('document', '6adf97f83acf6453d4a6a4b1070f3754'))
 paddle.fluid.contrib.BasicGRUUnit.add_parameter (ArgSpec(args=['self', 'name', 'parameter'], varargs=None, keywords=None, defaults=None), ('document', 'f35ab374c7d5165c3daf3bd64a5a2ec1'))

python/paddle/fluid/contrib/layers/nn.py

@@ -29,6 +29,7 @@ __all__ = [
     'sequence_topk_avg_pooling',
     'var_conv_2d',
     'match_matrix_tensor',
+    'tree_conv',
 ]
 
 
@@ -361,3 +362,68 @@ def sequence_topk_avg_pooling(input, row, col, topks, channel_num):
                'channel_num': channel_num})
 
     return out
+
+
+def tree_conv(nodes_vector,
+              edge_set,
+              output_size,
+              num_filters=1,
+              max_depth=2,
+              act='tanh',
+              param_attr=None,
+              bias_attr=None,
+              name=None):
+    """ 
+    ${comment}
+    		
+    Args:
+        nodes_vector(${nodes_vector_type}): ${nodes_vector_comment}
+        edge_set(${edge_set_type}): ${edge_set_comment}
+        output_size(int): output feature width
+        num_filters(int): number of filters, Default 1
+        max_depth(int): max depth of filters, Default 2
+        act(str): activation function, Default tanh
+        param_attr(ParamAttr): the parameter attribute for the filters, Default None
+        bias_attr(ParamAttr): the parameter attribute for the bias of this layer, Default None
+        name(str): a name of this layer(optional). If set None, the layer will be named automatically, Default None
+
+    Returns:
+        out(${out_type}): ${out_comment}
+
+    Examples:
+        .. code-block:: python
+
+          import paddle.fluid as fluid
+          # 10 for max_node_size of dataset, 5 for vector width
+          nodes_vector = fluid.layers.data(name='vectors', shape=[10, 5], dtype='float32')
+          # 10 for max_node_size of dataset, 2 for every edge has two nodes
+          # edges must be directional
+          edge_set = fluid.layers.data(name='edge_set', shape=[10, 2], dtype='float32')
+          # the shape of output will be [10, 6, 1],
+          # 10 for max_node_size of dataset, 6 for output size, 1 for 1 filter
+          out_vector = fluid.layers.tree_conv(nodes_vector, edge_set, 6, 1, 2)
+          # After reshape, output tensor could be nodes_vector for next tree convolution
+          out_vector = fluid.layers.reshape(out_vector, shape=[-1, 10, 6])
+          out_vector_2 = fluid.layers.tree_conv(out_vector, edge_set, 3, 4, 2)
+          # also output tensor could be pooling(the pooling in paper called global pooling)
+          pooled = fluid.layers.reduce_max(out_vector, dim=2) # global pooling
+    """
+    helper = LayerHelper("tree_conv", **locals())
+    dtype = helper.input_dtype('nodes_vector')
+    feature_size = nodes_vector.shape[2]
+    W_shape = [feature_size, 3, output_size, num_filters]
+    W = helper.create_parameter(
+        attr=param_attr, shape=W_shape, dtype=dtype, is_bias=False)
+    out = helper.create_variable_for_type_inference(dtype=dtype)
+    helper.append_op(
+        type='tree_conv',
+        inputs={'NodesVector': nodes_vector,
+                'EdgeSet': edge_set,
+                'Filter': W},
+        outputs={'Out': out, },
+        attrs={'max_depth': max_depth})
+    if helper.bias_attr:
+        pre_activation = helper.append_bias_op(out)
+    else:
+        pre_activation = out
+    return helper.append_activation(pre_activation)

python/paddle/fluid/layers/nn.py

@@ -208,7 +208,6 @@ __all__ = [
     'teacher_student_sigmoid_loss',
     'huber_loss',
     'kldiv_loss',
-    'tree_conv',
     'npair_loss',
     'pixel_shuffle',
     'fsp_matrix',
@@ -13272,75 +13271,6 @@ def kldiv_loss(x, target, reduction='mean', name=None):
     return loss
 
 
-@templatedoc()
-def tree_conv(nodes_vector,
-              edge_set,
-              output_size,
-              num_filters=1,
-              max_depth=2,
-              act='tanh',
-              param_attr=None,
-              bias_attr=None,
-              name=None):
-    """ 
-    ${comment}
-    		
-    Args:
-        nodes_vector(${nodes_vector_type}): ${nodes_vector_comment}
-        edge_set(${edge_set_type}): ${edge_set_comment}
-        output_size(int): output feature width
-        num_filters(int): number of filters, Default 1
-        max_depth(int): max depth of filters, Default 2
-        act(str): activation function, Default tanh
-        param_attr(ParamAttr): the parameter attribute for the filters, Default None
-        bias_attr(ParamAttr): the parameter attribute for the bias of this layer, Default None
-        name(str): a name of this layer(optional). If set None, the layer will be named automatically, Default None
-
-    Returns:
-        out(${out_type}): ${out_comment}
-
-    Examples:
-        .. code-block:: python
-
-          import paddle.fluid as fluid
-          # 10 for max_node_size of dataset, 5 for vector width
-          nodes_vector = fluid.layers.data(name='vectors', shape=[10, 5], dtype='float32')
-          # 10 for max_node_size of dataset, 2 for every edge has two nodes
-          # edges must be directional
-          edge_set = fluid.layers.data(name='edge_set', shape=[10, 2], dtype='float32')
-          # the shape of output will be [10, 6, 1],
-          # 10 for max_node_size of dataset, 6 for output size, 1 for 1 filter
-          out_vector = fluid.layers.tree_conv(nodes_vector, edge_set, 6, 1, 2)
-          # After reshape, output tensor could be nodes_vector for next tree convolution
-          out_vector = fluid.layers.reshape(out_vector, shape=[-1, 10, 6])
-          out_vector_2 = fluid.layers.tree_conv(out_vector, edge_set, 3, 4, 2)
-          # also output tensor could be pooling(the pooling in paper called global pooling)
-          pooled = fluid.layers.reduce_max(out_vector, dim=2) # global pooling
-    """
-    helper = LayerHelper("tree_conv", **locals())
-    dtype = helper.input_dtype('nodes_vector')
-    feature_size = nodes_vector.shape[2]
-    W_shape = [feature_size, 3, output_size, num_filters]
-    W = helper.create_parameter(
-        attr=param_attr, shape=W_shape, dtype=dtype, is_bias=False)
-    if name == None:
-        out = helper.create_variable_for_type_inference(dtype=dtype)
-    else:
-        out = helper.create_variable(name=name, dtype=dtype, persistable=False)
-    helper.append_op(
-        type='tree_conv',
-        inputs={'NodesVector': nodes_vector,
-                'EdgeSet': edge_set,
-                'Filter': W},
-        outputs={'Out': out, },
-        attrs={'max_depth': max_depth})
-    if helper.bias_attr:
-        pre_activation = helper.append_bias_op(out)
-    else:
-        pre_activation = out
-    return helper.append_activation(pre_activation)
-
-
 from .ops import square
 from .control_flow import equal
 

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

@@ -876,7 +876,7 @@ class TestLayer(LayerTest):
                 dtype='int32',
                 lod_level=1,
                 append_batch_size=False)
-            ret = layers.tree_conv(
+            ret = fluid.contrib.layers.tree_conv(
                 nodes_vector=NodesVector,
                 edge_set=EdgeSet,
                 output_size=6,