未验证 提交 b8de1401 编写于 作者: C Cao Ying 提交者: GitHub

Merge pull request #6919 from lcy-seso/fix_doc

fix doc.
......@@ -70,16 +70,17 @@ class TransposeOpMaker : public framework::OpProtoAndCheckerMaker {
Transpose Operator.
The input tensor will be permuted according to the axis values given.
The op functions similar to how numpy.transpose works in python.
For example:
>> input = numpy.arange(6).reshape((2,3))
>> input
array([[0, 1, 2],
The op functions is similar to how numpy.transpose works in python.
For example: input = numpy.arange(6).reshape((2,3))
the input is:
array([[0, 1, 2],
[3, 4, 5]])
>> axis = [1, 0]
>> output = input.transpose(axis)
>> output
array([[0, 3],
given axis is: [1, 0]
output = input.transpose(axis)
then the output is:
array([[0, 3],
[1, 4],
[2, 5]])
So, given a input tensor of shape(N, C, H, W) and the axis is {0, 2, 3, 1},
......
......@@ -53,9 +53,8 @@ class Unpool2dOpMaker : public framework::OpProtoAndCheckerMaker {
"(string), unpooling type, can be \"max\" for max-unpooling ")
.InEnum({"max"});
AddComment(R"DOC(
"Input shape: $(N, C_{in}, H_{in}, W_{in})$,
Output shape: $(N, C_{out}, H_{out}, W_{out})$
Where
Input shape is: $(N, C_{in}, H_{in}, W_{in})$, Output shape is:
$(N, C_{out}, H_{out}, W_{out})$, where
$$
H_{out} = (H_{in}−1) * strides[0] − 2 * paddings[0] + ksize[0] \\
W_{out} = (W_{in}−1) * strides[1] − 2 * paddings[1] + ksize[1]
......
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