Skip to content
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

fix docs bugs:docs\api\paddle\nn\RNN_cn.rst #6320

Merged
merged 3 commits into from
Nov 23, 2023
Merged
Changes from 1 commit
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 3 additions & 2 deletions docs/api/paddle/nn/RNN_cn.rst
Original file line number Diff line number Diff line change
Expand Up @@ -9,13 +9,13 @@ RNN

**循环神经网络**

循环神经网络(RNN)的封装,将输入的 Cell 封装为一个循环神经网络。它能够重复执行 :code:`cell.forward()` 直到遍历完 input 中的所有 Tensor
循环神经网络(RNN)的封装,将输入的 Cell 封装为一个循环神经网络。它能够重复执行 :code:`cell.forward()` 直到达到 inputs 的最大长度

参数
::::::::::::

- **cell** (RNNCellBase) - RNNCellBase 类的一个实例。
- **is_reverse** (bool,可选) - 指定遍历 input 的方向。默认为 False
- **is_reverse** (bool,可选) - 指定遍历 input 的方向。默认为 False
- **time_major** (bool,可选) - 指定 input 的第一个维度是否是 time steps。默认为 False。

输入
Expand All @@ -24,6 +24,7 @@ RNN
- **inputs** (Tensor) - 输入(可以是多层嵌套的)。如果 time_major 为 False,则 Tensor 的形状为[batch_size,time_steps,input_size],如果 time_major 为 True,则 Tensor 的形状为[time_steps,batch_size,input_size],input_size 为 cell 的 input_size。
- **initial_states** (Tensor|list|tuple,可选) - 输入 cell 的初始状态(可以是多层嵌套的),如果没有给出则会调用 :code:`cell.get_initial_states` 生成初始状态。默认为 None。
- **sequence_length** (Tensor,可选) - 指定输入序列的长度,形状为[batch_size],数据类型为 int64 或 int32。在输入序列中所有 time step 不小于 sequence_length 的元素都会被当作填充元素处理(状态不再更新)。
- **kwargs** - 指定附加在 cell 前面的关键字参数。
fsczz marked this conversation as resolved.
Show resolved Hide resolved

输出
::::::::::::
Expand Down