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
PaddlePaddle
DeepSpeech
提交
1d163ad1
D
DeepSpeech
项目概览
PaddlePaddle
/
DeepSpeech
12 个月 前同步成功
通知
205
Star
8425
Fork
1598
代码
文件
提交
分支
Tags
贡献者
分支图
Diff
Issue
245
列表
看板
标记
里程碑
合并请求
3
Wiki
0
Wiki
分析
仓库
DevOps
项目成员
Pages
D
DeepSpeech
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
245
Issue
245
列表
看板
标记
里程碑
合并请求
3
合并请求
3
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
1d163ad1
编写于
8月 31, 2017
作者:
X
Xinghai Sun
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
Fixed a serious mistake of bidirectional simple rnn for DS2.
上级
638fae13
变更
2
隐藏空白更改
内联
并排
Showing
2 changed file
with
12 addition
and
8 deletion
+12
-8
cloud/pcloud_submit.sh
cloud/pcloud_submit.sh
+2
-2
layer.py
layer.py
+10
-6
未找到文件。
cloud/pcloud_submit.sh
浏览文件 @
1d163ad1
TRAIN_MANIFEST
=
"cloud/cloud.manifest.train"
DEV_MANIFEST
=
"cloud/cloud.manifest.dev"
CLOUD_MODEL_DIR
=
"
/pfs/dlnel/home/USERNAME/deepspeech2/model
"
CLOUD_MODEL_DIR
=
"
./checkpoints
"
BATCH_SIZE
=
256
NUM_GPU
=
8
NUM_NODE
=
1
...
...
@@ -11,7 +11,7 @@ DS2_PATH=${PWD%/*}
cp
-f
pcloud_train.sh
${
DS2_PATH
}
paddlecloud submit
\
-image
bootstrapper:5000/
wanghaoshuang
/pcloud_ds2:latest
\
-image
bootstrapper:5000/
paddlepaddle
/pcloud_ds2:latest
\
-jobname
${
JOB_NAME
}
\
-cpu
${
NUM_GPU
}
\
-gpu
${
NUM_GPU
}
\
...
...
layer.py
浏览文件 @
1d163ad1
...
...
@@ -55,16 +55,20 @@ def bidirectional_simple_rnn_bn_layer(name, input, size, act):
:rtype: LayerOutput
"""
# input-hidden weights shared across bi-direcitonal rnn.
input_proj
=
paddle
.
layer
.
fc
(
input_proj
_forward
=
paddle
.
layer
.
fc
(
input
=
input
,
size
=
size
,
act
=
paddle
.
activation
.
Linear
(),
bias_attr
=
False
)
# batch norm is only performed on input-state projection
input_proj_bn
=
paddle
.
layer
.
batch_norm
(
input
=
input_proj
,
act
=
paddle
.
activation
.
Linear
())
input_proj_backward
=
paddle
.
layer
.
fc
(
input
=
input
,
size
=
size
,
act
=
paddle
.
activation
.
Linear
(),
bias_attr
=
False
)
# batch norm is only performed on input-state projection
input_proj_bn_forward
=
paddle
.
layer
.
batch_norm
(
input
=
input_proj_forward
,
act
=
paddle
.
activation
.
Linear
())
input_proj_bn_backward
=
paddle
.
layer
.
batch_norm
(
input
=
input_proj_backward
,
act
=
paddle
.
activation
.
Linear
())
# forward and backward in time
forward_simple_rnn
=
paddle
.
layer
.
recurrent
(
input
=
input_proj_bn
,
act
=
act
,
reverse
=
False
)
input
=
input_proj_bn
_forward
,
act
=
act
,
reverse
=
False
)
backward_simple_rnn
=
paddle
.
layer
.
recurrent
(
input
=
input_proj_bn
,
act
=
act
,
reverse
=
True
)
input
=
input_proj_bn
_backward
,
act
=
act
,
reverse
=
True
)
return
paddle
.
layer
.
concat
(
input
=
[
forward_simple_rnn
,
backward_simple_rnn
])
...
...
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