!41609 【doc】Modify the Chinese documentation of conv2d functional interface, to be consistent with the English documentation

Merge pull request !41609 from happy徐/conv2d_doc
This commit is contained in:
i-robot 2022-09-07 09:07:23 +00:00 committed by Gitee
commit 4a237776e2
No known key found for this signature in database
GPG Key ID: 173E9B9CA92EEF8F
1 changed files with 1 additions and 2 deletions

View File

@ -1,7 +1,7 @@
mindspore.ops.conv2d
====================
.. py:function:: mindspore.ops.conv2d(inputs, weight, mode=1, pad_mode="valid", padding=0, stride=1, dilation=1, group=1)
.. py:function:: mindspore.ops.conv2d(inputs, weight, pad_mode="valid", padding=0, stride=1, dilation=1, group=1)
二维卷积层。
@ -20,7 +20,6 @@ mindspore.ops.conv2d
参数:
- **inputs** (Tensor) - shape为 :math:`(N, C_{in}, H_{in}, W_{in})` 的Tensor。
- **weight** (Tensor) - 设置卷积核的大小为 :math:`(\text{kernel_size[0]}, \text{kernel_size[1]})` 则shape为 :math:`(C_{out}, C_{in}, \text{kernel_size[0]}, \text{kernel_size[1]})`
- **mode** (int) - 指定不同的卷积模式。此值目前未被使用。默认值1。
- **pad_mode** (str) - 指定填充模式。取值为"same""valid",或"pad"。默认值:"valid"。
- **same**: 输出的高度和宽度分别与输入整除 `stride` 后的值相同。填充将被均匀地添加到高和宽的两侧,剩余填充量将被添加到维度末端。若设置该模式,`padding` 的值必须为0。