Skip to content
体验新版
项目
组织
正在加载...
登录
切换导航
打开侧边栏
wmsofts
Paddle
提交
24144bdb
P
Paddle
项目概览
wmsofts
/
Paddle
与 Fork 源项目一致
Fork自
PaddlePaddle / Paddle
通知
1
Star
0
Fork
0
代码
文件
提交
分支
Tags
贡献者
分支图
Diff
Issue
0
列表
看板
标记
里程碑
合并请求
0
Wiki
0
Wiki
分析
仓库
DevOps
项目成员
Pages
P
Paddle
项目概览
项目概览
详情
发布
仓库
仓库
文件
提交
分支
标签
贡献者
分支图
比较
Issue
0
Issue
0
列表
看板
标记
里程碑
合并请求
0
合并请求
0
Pages
分析
分析
仓库分析
DevOps
Wiki
0
Wiki
成员
成员
收起侧边栏
关闭侧边栏
动态
分支图
创建新Issue
提交
Issue看板
体验新版 GitCode,发现更多精彩内容 >>
提交
24144bdb
编写于
1月 16, 2018
作者:
W
wanghaoshuang
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
Add notice about norm_by_times and change 'ctc' to 'CTC'
上级
fb62f8cb
变更
1
隐藏空白更改
内联
并排
Showing
1 changed file
with
8 addition
and
7 deletion
+8
-7
python/paddle/v2/fluid/layers/nn.py
python/paddle/v2/fluid/layers/nn.py
+8
-7
未找到文件。
python/paddle/v2/fluid/layers/nn.py
浏览文件 @
24144bdb
...
...
@@ -1508,10 +1508,11 @@ def reduce_min(input, dim=None, keep_dim=False):
def
warpctc
(
input
,
label
,
blank
=
0
,
norm_by_times
=
False
,
**
kwargs
):
"""
An operator integrating the open source warp-ctc library
An operator integrating the open source Warp-CTC library
(https://github.com/baidu-research/warp-ctc)
to compute Connectionist Temporal Classification (CTC) loss.
It can be aliased as softmax with
ctc
, since a native softmax activation is
interated to the
warp-ctc
library, to to normlize values for each row of the
It can be aliased as softmax with
CTC
, since a native softmax activation is
interated to the
Warp-CTC
library, to to normlize values for each row of the
input tensor.
Args:
...
...
@@ -1525,12 +1526,12 @@ def warpctc(input, label, blank=0, norm_by_times=False, **kwargs):
of variable-length sequence, which is a 2-D Tensor with LoD
information. It is of the shape [Lg, 1], where Lg is th sum of
all labels' length.
blank: (int, default: 0), the blank label of Connectionist
blank: (int, default: 0), the blank label
index
of Connectionist
Temporal Classification (CTC) loss, which is in the
half-opened interval [0, num_classes + 1).
norm_by_times: (bool, default: false), whether to
normalize the gradients by the number of time-step,
which is also the sequence's length
.
norm_by_times: (bool, default: false), whether to
normalize the gradients
by the number of time-step,which is also the sequence's length.
There is no need to normalize the gradients if warpctc layer was follewed by a mean_op
.
Returns:
Variable: The Connectionist Temporal Classification (CTC) loss, which is a 2-D Tensor of the shape [batch_size, 1].
...
...
编辑
预览
Markdown
is supported
0%
请重试
或
添加新附件
.
添加附件
取消
You are about to add
0
people
to the discussion. Proceed with caution.
先完成此消息的编辑!
取消
想要评论请
注册
或
登录