[NN] [Doc] Fix nn api doc (#2047)

* fix mxnet nn doc and no note on chebconv

* change notes to note to highlight

python/dgl/nn/pytorch/conv/sgconv.py

@@ -47,8 +47,8 @@ class SGConv(nn.Module):
         0-in-degree nodes in input graph. By setting ``True``, it will suppress the check
         and let the users handle it by themselves. Default: ``False``.
 
-    Notes
-    -----
+    Note
+    ----
     Zero in-degree nodes will lead to invalid output value. This is because no message
     will be passed to those nodes, the aggregation function will be appied on empty input.
     A common practice to avoid this is to add a self-loop for each node in the graph if
@@ -107,8 +107,8 @@ class SGConv(nn.Module):
         -----------
         Reinitialize learnable parameters.
 
-        Notes
-        -----
+        Note
+        ----
         The model parameters are initialized using xavier initialization
         and the bias is initialized to be zero.
         """
@@ -158,8 +158,8 @@ class SGConv(nn.Module):
             since no message will be passed to those nodes. This will cause invalid output.
             The error can be ignored by setting ``allow_zero_in_degree`` parameter to ``True``.
 
-        Notes
-        -----
+        Note
+        ----
         If ``cache`` is set to True, ``feat`` and ``graph`` should not change during
         training, or you will get wrong results.
         """

python/dgl/nn/pytorch/conv/tagconv.py

@@ -82,8 +82,8 @@ class TAGConv(nn.Module):
         -----------
         Reinitialize learnable parameters.
 
-        Notes
-        -----
+        Note
+        ----
         The model parameters are initialized using Glorot uniform initialization.
         """
         gain = nn.init.calculate_gain('relu')

python/dgl/nn/tensorflow/conv/chebconv.py

@@ -44,10 +44,6 @@ class ChebConv(layers.Layer):
     bias : bool, optional
         If True, adds a learnable bias to the output. Default: ``True``.
 
-    Note
-    ----
-    ChebConv only support DGLGraph as input for now. Heterograph will report error. To be fixed.
-
     Example
     -------
     >>> import dgl

python/dgl/nn/tensorflow/conv/densechebconv.py

@@ -29,30 +29,6 @@ class DenseChebConv(layers.Layer):
     bias : bool, optional
         If True, adds a learnable bias to the output. Default: ``True``.
 
-    Example
-    -------
-    >>> import dgl
-    >>> import numpy as np
-    >>> import tensorflow as tf
-    >>> from dgl.nn import DenseChebConv
-    >>>
-    >>> feat = tf.ones(6, 10)
-    >>> adj = tf.tensor([[0., 0., 1., 0., 0., 0.],
-    ...         [1., 0., 0., 0., 0., 0.],
-    ...         [0., 1., 0., 0., 0., 0.],
-    ...         [0., 0., 1., 0., 0., 1.],
-    ...         [0., 0., 0., 1., 0., 0.],
-    ...         [0., 0., 0., 0., 0., 0.]])
-    >>> conv = DenseChebConv(10, 2, 2)
-    >>> res = conv(adj, feat)
-    >>> res
-    tensor([[-3.3516, -2.4797],
-            [-3.3516, -2.4797],
-            [-3.3516, -2.4797],
-            [-4.5192, -3.0835],
-            [-2.5259, -2.0527],
-            [-0.5327, -1.0219]])
-
     See also
     --------
     `ChebConv <https://docs.dgl.ai/api/python/nn.tensorflow.html#chebconv>`__

python/dgl/nn/tensorflow/conv/gatconv.py

@@ -63,8 +63,8 @@ class GATConv(layers.Layer):
         0-in-degree nodes in input graph. By setting ``True``, it will suppress the check
         and let the users handle it by themselves. Defaults: ``False``.
 
-    Notes
-    -----
+    Note
+    ----
     Zero in-degree nodes will lead to invalid output value. This is because no message
     will be passed to those nodes, the aggregation function will be appied on empty input.
     A common practice to avoid this is to add a self-loop for each node in the graph if

python/dgl/nn/tensorflow/conv/graphconv.py

@@ -60,8 +60,8 @@ class GraphConv(layers.Layer):
     bias : torch.Tensor
         The learnable bias tensor.
 
-    Notes
-    -----
+    Note
+    ----
     Zero in-degree nodes will lead to invalid output value. This is because no message
     will be passed to those nodes, the aggregation function will be appied on empty input.
     A common practice to avoid this is to add a self-loop for each node in the graph if
@@ -208,8 +208,8 @@ class GraphConv(layers.Layer):
             since no message will be passed to those nodes. This will cause invalid output.
             The error can be ignored by setting ``allow_zero_in_degree`` parameter to ``True``.
 
-        Notes
-        -----
+        Note
+        ----
         * Input shape: :math:`(N, *, \text{in_feats})` where * means any number of additional
           dimensions, :math:`N` is the number of nodes.
         * Output shape: :math:`(N, *, \text{out_feats})` where all but the last dimension are

python/dgl/nn/tensorflow/conv/sgconv.py

@@ -49,8 +49,8 @@ class SGConv(layers.Layer):
         0-in-degree nodes in input graph. By setting ``True``, it will suppress the check
         and let the users handle it by themselves. Default: ``False``.
 
-    Notes
-    -----
+    Note
+    ----
     Zero in-degree nodes will lead to invalid output value. This is because no message
     will be passed to those nodes, the aggregation function will be appied on empty input.
     A common practice to avoid this is to add a self-loop for each node in the graph if
@@ -145,8 +145,8 @@ class SGConv(layers.Layer):
             since no message will be passed to those nodes. This will cause invalid output.
             The error can be ignored by setting ``allow_zero_in_degree`` parameter to ``True``.
 
-        Notes
-        -----
+        Note
+        ----
         If ``cache`` is set to True, ``feat`` and ``graph`` should not change during
         training, or you will get wrong results.
         """