未验证 提交 ebc616b0 编写于 作者: E emailweixu 提交者: GitHub

Fix comment to layers.fc

x_num_col_dims => num_flatten_dims
上级 564dba17
...@@ -64,14 +64,14 @@ def fc(input, ...@@ -64,14 +64,14 @@ def fc(input,
is flattened: the first `num_flatten_dims` is flattened: the first `num_flatten_dims`
dimensions will be flatten to form the first dimensions will be flatten to form the first
dimension of the final matrix (height of the dimension of the final matrix (height of the
matrix), and the rest `rank(X) - num_col_dims` matrix), and the rest `rank(X) - num_flatten_dims`
dimensions are flattened to form the second dimensions are flattened to form the second
dimension of the final matrix (width of the matrix). dimension of the final matrix (width of the matrix).
For example, suppose `X` is a 6-dimensional tensor For example, suppose `X` is a 6-dimensional tensor
with a shape [2, 3, 4, 5, 6], and with a shape [2, 3, 4, 5, 6], and
`x_num_col_dims` = 3. Then, the flattened matrix `num_flatten_dims` = 3. Then, the flattened matrix
will have a shape [2 x 3 x 4, 5 x 6] = [24, 30]. will have a shape [2 x 3 x 4, 5 x 6] = [24, 30].
By default, `x_num_col_dims` is set to 1. By default, `num_flatten_dims` is set to 1.
param_attr(ParamAttr|list): The parameter attribute for learnable param_attr(ParamAttr|list): The parameter attribute for learnable
parameters/weights of the fully connected parameters/weights of the fully connected
layer. layer.
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册