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
a96ac4f5
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
a96ac4f5
编写于
1月 30, 2018
作者:
Y
Yang Yu
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
Refine code
上级
0311fd15
变更
1
隐藏空白更改
内联
并排
Showing
1 changed file
with
98 addition
and
70 deletion
+98
-70
python/paddle/v2/fluid/tests/book/test_word2vec.py
python/paddle/v2/fluid/tests/book/test_word2vec.py
+98
-70
未找到文件。
python/paddle/v2/fluid/tests/book/test_word2vec.py
浏览文件 @
a96ac4f5
...
...
@@ -12,76 +12,104 @@
# See the License for the specific language governing permissions and
# limitations under the License.
import
numpy
as
np
import
paddle.v2
as
paddle
import
paddle.v2.fluid
as
fluid
import
unittest
PASS_NUM
=
100
EMBED_SIZE
=
32
HIDDEN_SIZE
=
256
N
=
5
BATCH_SIZE
=
32
IS_SPARSE
=
True
word_dict
=
paddle
.
dataset
.
imikolov
.
build_dict
()
dict_size
=
len
(
word_dict
)
first_word
=
fluid
.
layers
.
data
(
name
=
'firstw'
,
shape
=
[
1
],
dtype
=
'int64'
)
second_word
=
fluid
.
layers
.
data
(
name
=
'secondw'
,
shape
=
[
1
],
dtype
=
'int64'
)
third_word
=
fluid
.
layers
.
data
(
name
=
'thirdw'
,
shape
=
[
1
],
dtype
=
'int64'
)
forth_word
=
fluid
.
layers
.
data
(
name
=
'forthw'
,
shape
=
[
1
],
dtype
=
'int64'
)
next_word
=
fluid
.
layers
.
data
(
name
=
'nextw'
,
shape
=
[
1
],
dtype
=
'int64'
)
embed_first
=
fluid
.
layers
.
embedding
(
input
=
first_word
,
size
=
[
dict_size
,
EMBED_SIZE
],
dtype
=
'float32'
,
is_sparse
=
IS_SPARSE
,
param_attr
=
'shared_w'
)
embed_second
=
fluid
.
layers
.
embedding
(
input
=
second_word
,
size
=
[
dict_size
,
EMBED_SIZE
],
dtype
=
'float32'
,
is_sparse
=
IS_SPARSE
,
param_attr
=
'shared_w'
)
embed_third
=
fluid
.
layers
.
embedding
(
input
=
third_word
,
size
=
[
dict_size
,
EMBED_SIZE
],
dtype
=
'float32'
,
is_sparse
=
IS_SPARSE
,
param_attr
=
'shared_w'
)
embed_forth
=
fluid
.
layers
.
embedding
(
input
=
forth_word
,
size
=
[
dict_size
,
EMBED_SIZE
],
dtype
=
'float32'
,
is_sparse
=
IS_SPARSE
,
param_attr
=
'shared_w'
)
concat_embed
=
fluid
.
layers
.
concat
(
input
=
[
embed_first
,
embed_second
,
embed_third
,
embed_forth
],
axis
=
1
)
hidden1
=
fluid
.
layers
.
fc
(
input
=
concat_embed
,
size
=
HIDDEN_SIZE
,
act
=
'sigmoid'
)
predict_word
=
fluid
.
layers
.
fc
(
input
=
hidden1
,
size
=
dict_size
,
act
=
'softmax'
)
cost
=
fluid
.
layers
.
cross_entropy
(
input
=
predict_word
,
label
=
next_word
)
avg_cost
=
fluid
.
layers
.
mean
(
x
=
cost
)
sgd_optimizer
=
fluid
.
optimizer
.
SGD
(
learning_rate
=
0.001
)
sgd_optimizer
.
minimize
(
avg_cost
)
train_reader
=
paddle
.
batch
(
paddle
.
dataset
.
imikolov
.
train
(
word_dict
,
N
),
BATCH_SIZE
)
place
=
fluid
.
CPUPlace
()
exe
=
fluid
.
Executor
(
place
)
feeder
=
fluid
.
DataFeeder
(
feed_list
=
[
first_word
,
second_word
,
third_word
,
forth_word
,
next_word
],
place
=
place
)
exe
.
run
(
fluid
.
default_startup_program
())
for
pass_id
in
range
(
PASS_NUM
):
for
data
in
train_reader
():
avg_cost_np
=
exe
.
run
(
fluid
.
default_main_program
(),
feed
=
feeder
.
feed
(
data
),
fetch_list
=
[
avg_cost
])
if
avg_cost_np
[
0
]
<
5.0
:
exit
(
0
)
# if avg cost less than 10.0, we think our code is good.
exit
(
1
)
def
main_impl
(
use_cuda
):
if
use_cuda
and
not
fluid
.
core
.
is_compiled_with_cuda
():
return
PASS_NUM
=
100
EMBED_SIZE
=
32
HIDDEN_SIZE
=
256
N
=
5
BATCH_SIZE
=
32
IS_SPARSE
=
True
word_dict
=
paddle
.
dataset
.
imikolov
.
build_dict
()
dict_size
=
len
(
word_dict
)
first_word
=
fluid
.
layers
.
data
(
name
=
'firstw'
,
shape
=
[
1
],
dtype
=
'int64'
)
second_word
=
fluid
.
layers
.
data
(
name
=
'secondw'
,
shape
=
[
1
],
dtype
=
'int64'
)
third_word
=
fluid
.
layers
.
data
(
name
=
'thirdw'
,
shape
=
[
1
],
dtype
=
'int64'
)
forth_word
=
fluid
.
layers
.
data
(
name
=
'forthw'
,
shape
=
[
1
],
dtype
=
'int64'
)
next_word
=
fluid
.
layers
.
data
(
name
=
'nextw'
,
shape
=
[
1
],
dtype
=
'int64'
)
embed_first
=
fluid
.
layers
.
embedding
(
input
=
first_word
,
size
=
[
dict_size
,
EMBED_SIZE
],
dtype
=
'float32'
,
is_sparse
=
IS_SPARSE
,
param_attr
=
'shared_w'
)
embed_second
=
fluid
.
layers
.
embedding
(
input
=
second_word
,
size
=
[
dict_size
,
EMBED_SIZE
],
dtype
=
'float32'
,
is_sparse
=
IS_SPARSE
,
param_attr
=
'shared_w'
)
embed_third
=
fluid
.
layers
.
embedding
(
input
=
third_word
,
size
=
[
dict_size
,
EMBED_SIZE
],
dtype
=
'float32'
,
is_sparse
=
IS_SPARSE
,
param_attr
=
'shared_w'
)
embed_forth
=
fluid
.
layers
.
embedding
(
input
=
forth_word
,
size
=
[
dict_size
,
EMBED_SIZE
],
dtype
=
'float32'
,
is_sparse
=
IS_SPARSE
,
param_attr
=
'shared_w'
)
concat_embed
=
fluid
.
layers
.
concat
(
input
=
[
embed_first
,
embed_second
,
embed_third
,
embed_forth
],
axis
=
1
)
hidden1
=
fluid
.
layers
.
fc
(
input
=
concat_embed
,
size
=
HIDDEN_SIZE
,
act
=
'sigmoid'
)
predict_word
=
fluid
.
layers
.
fc
(
input
=
hidden1
,
size
=
dict_size
,
act
=
'softmax'
)
cost
=
fluid
.
layers
.
cross_entropy
(
input
=
predict_word
,
label
=
next_word
)
avg_cost
=
fluid
.
layers
.
mean
(
x
=
cost
)
sgd_optimizer
=
fluid
.
optimizer
.
SGD
(
learning_rate
=
0.001
)
sgd_optimizer
.
minimize
(
avg_cost
)
train_reader
=
paddle
.
batch
(
paddle
.
dataset
.
imikolov
.
train
(
word_dict
,
N
),
BATCH_SIZE
)
place
=
fluid
.
CUDAPlace
(
0
)
if
use_cuda
else
fluid
.
CPUPlace
()
exe
=
fluid
.
Executor
(
place
)
feeder
=
fluid
.
DataFeeder
(
feed_list
=
[
first_word
,
second_word
,
third_word
,
forth_word
,
next_word
],
place
=
place
)
exe
.
run
(
fluid
.
default_startup_program
())
for
pass_id
in
range
(
PASS_NUM
):
for
data
in
train_reader
():
avg_cost_np
=
exe
.
run
(
fluid
.
default_main_program
(),
feed
=
feeder
.
feed
(
data
),
fetch_list
=
[
avg_cost
])
if
avg_cost_np
[
0
]
<
5.0
:
return
raise
AssertionError
(
"Cost is too large {0:2.2}"
.
format
(
avg_cost_np
[
0
]))
def
main
(
*
args
,
**
kwargs
):
prog
=
fluid
.
Program
()
startup_prog
=
fluid
.
Program
()
scope
=
fluid
.
core
.
Scope
()
with
fluid
.
scope_guard
(
scope
):
with
fluid
.
program_guard
(
prog
,
startup_prog
):
main_impl
(
*
args
,
**
kwargs
)
class
W2VTest
(
unittest
.
TestCase
):
def
test_cpu_normal
(
self
):
main
(
use_cuda
=
False
)
def
test_gpu_normal
(
self
):
main
(
use_cuda
=
True
)
if
__name__
==
'__main__'
:
unittest
.
main
()
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