-
Notifications
You must be signed in to change notification settings - Fork 758
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[Docathon][Add CN Doc No.24-25] #6360
Conversation
感谢你贡献飞桨文档,文档预览构建中,Docs-New 跑完后即可预览,预览链接:http://preview-pr-6360.paddle-docs-preview.paddlepaddle.org.cn/documentation/docs/zh/api/index_cn.html |
|
||
.. py:function:: paddle.sparse.nn.functional.conv2d(x, weight, bias=None, stride=1, padding=0, dilation=1, groups=1, data_format='NHWC', name=None) | ||
|
||
稀疏二维卷积层(sparse convolution2d),根据输入、卷积核、步长(stride)、填充(padding)、空洞大小(dilations)一组参数计算得到输出特征层大小。输入和输出是 NHWC 格式,其中 N 是批尺寸,H 是特征的高度,W 是特征层宽度,C 是通道数。如果 bias_attr 不为 False,卷积计算会添加偏置项。 |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
空洞大小(dilations)一组参数
->空洞大小(dilations)、组参数(groups)
- 计算得到的是
输出特征
,而不是输出特征层大小
multidimensional SparseCooTensors
信息遗漏了
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
multidimensional SparseCooTensors
信息遗漏了
遗漏信息补充: 输入(Input)和输出(Output)是形状为[N,H,W,C]的多维稀疏坐标格式张量(SparseCooTensors)。
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Done
|
||
稀疏二维卷积层(sparse convolution2d),根据输入、卷积核、步长(stride)、填充(padding)、空洞大小(dilations)一组参数计算得到输出特征层大小。输入和输出是 NHWC 格式,其中 N 是批尺寸,H 是特征的高度,W 是特征层宽度,C 是通道数。如果 bias_attr 不为 False,卷积计算会添加偏置项。 | ||
|
||
对于每个输入 X,方程为: |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
方程为
-> 计算公式为
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Done
其中: | ||
|
||
- :math:`X` :输入值,NHWC 格式的 Tensor | ||
- :math:`W` :卷积核值,MCDHW 格式的 Tensor |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
此处与英文文档中的信息不相符
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Done
|
||
**稀疏二维卷积层** | ||
|
||
二维稀疏卷积层(Sparse convolution2d layer)根据输入、卷积核、步长(stride)、填充(padding)、空洞大小(dilations)一组参数计算得到输出特征层大小。 |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
整体请参考conv2d
的review comment检查一遍
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Done
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM for the content
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
sparse.Overview
也加上相应描述
Co-authored-by: zachary sun <70642955+sunzhongkai588@users.noreply.github.com>
Done @sunzhongkai588 |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM
PR types
Others
PR changes
Docs
Description
中文文档添加任务
#6193
新增中文文档:
英文文档链接:
@Xreki @sunzhongkai588