!11343 fix bugs of op BatchNorm1d, FastGelu in API

From: @lihongkang1
Reviewed-by: @liangchenghui,@wuxuejian
Signed-off-by: @liangchenghui

mindspore/nn/layer/activation.py

@@ -392,7 +392,7 @@ class GELU(Cell):
 
 class FastGelu(Cell):
     r"""
-    fast Gaussian error linear unit activation function.
+    Fast Gaussian error linear unit activation function.
 
     Applies FastGelu function to each element of the input. The input is a Tensor with any valid shape.
 

mindspore/nn/layer/normalization.py

@@ -267,7 +267,7 @@ class BatchNorm1d(_BatchNorm):
         Tensor, the normalized, scaled, offset tensor, of shape :math:`(N, C_{out})`.
 
     Supported Platforms:
-        ``Ascend``
+        ``Ascend`` ``GPU``
 
     Examples:
         >>> net = nn.BatchNorm1d(num_features=4)