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
afeixing77
Paddle
提交
0ce38b77
P
Paddle
项目概览
afeixing77
/
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 >>
未验证
提交
0ce38b77
编写于
11月 16, 2017
作者:
Q
Qiao Longfei
提交者:
GitHub
11月 16, 2017
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
correct optimizer import (#5699)
上级
06d155b5
变更
9
隐藏空白更改
内联
并排
Showing
9 changed file
with
101 addition
and
270 deletion
+101
-270
python/paddle/v2/fluid/tests/book/test_fit_a_line.py
python/paddle/v2/fluid/tests/book/test_fit_a_line.py
+9
-20
python/paddle/v2/fluid/tests/book/test_image_classification_train.py
...le/v2/fluid/tests/book/test_image_classification_train.py
+20
-80
python/paddle/v2/fluid/tests/book/test_recognize_digits_conv.py
.../paddle/v2/fluid/tests/book/test_recognize_digits_conv.py
+9
-20
python/paddle/v2/fluid/tests/book/test_recognize_digits_mlp.py
...n/paddle/v2/fluid/tests/book/test_recognize_digits_mlp.py
+10
-25
python/paddle/v2/fluid/tests/book/test_recommender_system.py
python/paddle/v2/fluid/tests/book/test_recommender_system.py
+27
-72
python/paddle/v2/fluid/tests/book/test_understand_sentiment_conv.py
...dle/v2/fluid/tests/book/test_understand_sentiment_conv.py
+5
-6
python/paddle/v2/fluid/tests/book/test_understand_sentiment_dynamic_lstm.py
...luid/tests/book/test_understand_sentiment_dynamic_lstm.py
+4
-6
python/paddle/v2/fluid/tests/book/test_understand_sentiment_lstm.py
...dle/v2/fluid/tests/book/test_understand_sentiment_lstm.py
+4
-5
python/paddle/v2/fluid/tests/book/test_word2vec.py
python/paddle/v2/fluid/tests/book/test_word2vec.py
+13
-36
未找到文件。
python/paddle/v2/fluid/tests/book/test_fit_a_line.py
浏览文件 @
0ce38b77
import
numpy
as
np
import
paddle.v2
as
paddle
import
paddle.v2.fluid.layers
as
layers
import
paddle.v2.fluid.core
as
core
import
paddle.v2.fluid.optimizer
as
optimizer
import
paddle.v2.fluid.framework
as
framework
from
paddle.v2.fluid.io
import
save_persistables
,
load_persistable
s
import
paddle.v2.fluid.layers
as
layer
s
from
paddle.v2.fluid.executor
import
Executor
from
paddle.v2.fluid.io
import
save_persistables
,
load_persistables
from
paddle.v2.fluid.optimizer
import
SGDOptimizer
import
numpy
as
np
x
=
layers
.
data
(
name
=
'x'
,
shape
=
[
13
],
data_type
=
'float32'
)
x
=
layers
.
data
(
name
=
'x'
,
shape
=
[
13
],
data_type
=
'float32'
)
y_predict
=
layers
.
fc
(
input
=
x
,
size
=
1
,
act
=
None
)
y_predict
=
layers
.
fc
(
input
=
x
,
size
=
1
,
act
=
None
)
y
=
layers
.
data
(
name
=
'y'
,
shape
=
[
1
],
data_type
=
'float32'
)
y
=
layers
.
data
(
name
=
'y'
,
shape
=
[
1
],
data_type
=
'float32'
)
cost
=
layers
.
square_error_cost
(
input
=
y_predict
,
label
=
y
)
cost
=
layers
.
square_error_cost
(
input
=
y_predict
,
label
=
y
)
avg_cost
=
layers
.
mean
(
x
=
cost
)
sgd_optimizer
=
optimizer
.
SGDOptimizer
(
learning_rate
=
0.001
)
sgd_optimizer
=
SGDOptimizer
(
learning_rate
=
0.001
)
opts
=
sgd_optimizer
.
minimize
(
avg_cost
)
BATCH_SIZE
=
20
...
...
python/paddle/v2/fluid/tests/book/test_image_classification_train.py
浏览文件 @
0ce38b77
import
numpy
as
np
import
paddle.v2
as
paddle
import
paddle.v2.fluid.core
as
core
import
paddle.v2.fluid.framework
as
framework
import
paddle.v2.fluid.layers
as
layers
import
paddle.v2.fluid.nets
as
nets
import
paddle.v2.fluid.optimizer
as
optimizer
from
paddle.v2.fluid.executor
import
Executor
import
paddle.v2.fluid.framework
as
framework
from
paddle.v2.fluid.initializer
import
XavierInitializer
from
paddle.v2.fluid.optimizer
import
AdamOptimizer
def
resnet_cifar10
(
input
,
depth
=
32
):
def
conv_bn_layer
(
input
,
ch_out
,
filter_size
,
stride
,
padding
,
act
=
'relu'
):
def
conv_bn_layer
(
input
,
ch_out
,
filter_size
,
stride
,
padding
,
act
=
'relu'
):
tmp
=
layers
.
conv2d
(
input
=
input
,
filter_size
=
filter_size
,
...
...
@@ -24,9 +19,7 @@ def resnet_cifar10(input, depth=32):
padding
=
padding
,
act
=
None
,
bias_attr
=
False
)
return
layers
.
batch_norm
(
input
=
tmp
,
act
=
act
)
return
layers
.
batch_norm
(
input
=
tmp
,
act
=
act
)
def
shortcut
(
input
,
ch_in
,
ch_out
,
stride
,
program
,
init_program
):
if
ch_in
!=
ch_out
:
...
...
@@ -35,28 +28,11 @@ def resnet_cifar10(input, depth=32):
else
:
return
input
def
basicblock
(
input
,
ch_in
,
ch_out
,
stride
):
tmp
=
conv_bn_layer
(
input
,
ch_out
,
3
,
stride
,
1
)
tmp
=
conv_bn_layer
(
tmp
,
ch_out
,
3
,
1
,
1
,
act
=
None
)
def
basicblock
(
input
,
ch_in
,
ch_out
,
stride
):
tmp
=
conv_bn_layer
(
input
,
ch_out
,
3
,
stride
,
1
)
tmp
=
conv_bn_layer
(
tmp
,
ch_out
,
3
,
1
,
1
,
act
=
None
)
short
=
shortcut
(
input
,
ch_in
,
ch_out
,
stride
)
return
layers
.
elementwise_add
(
x
=
tmp
,
y
=
short
,
act
=
'relu'
)
return
layers
.
elementwise_add
(
x
=
tmp
,
y
=
short
,
act
=
'relu'
)
def
layer_warp
(
block_func
,
input
,
ch_in
,
ch_out
,
count
,
stride
):
tmp
=
block_func
(
input
,
ch_in
,
ch_out
,
stride
)
...
...
@@ -67,45 +43,17 @@ def resnet_cifar10(input, depth=32):
assert
(
depth
-
2
)
%
6
==
0
n
=
(
depth
-
2
)
/
6
conv1
=
conv_bn_layer
(
input
=
input
,
ch_out
=
16
,
filter_size
=
3
,
stride
=
1
,
padding
=
1
)
res1
=
layer_warp
(
basicblock
,
conv1
,
16
,
16
,
n
,
1
)
res2
=
layer_warp
(
basicblock
,
res1
,
16
,
32
,
n
,
2
)
res3
=
layer_warp
(
basicblock
,
res2
,
32
,
64
,
n
,
2
)
input
=
input
,
ch_out
=
16
,
filter_size
=
3
,
stride
=
1
,
padding
=
1
)
res1
=
layer_warp
(
basicblock
,
conv1
,
16
,
16
,
n
,
1
)
res2
=
layer_warp
(
basicblock
,
res1
,
16
,
32
,
n
,
2
)
res3
=
layer_warp
(
basicblock
,
res2
,
32
,
64
,
n
,
2
)
pool
=
layers
.
pool2d
(
input
=
res3
,
pool_size
=
8
,
pool_type
=
'avg'
,
pool_stride
=
1
)
input
=
res3
,
pool_size
=
8
,
pool_type
=
'avg'
,
pool_stride
=
1
)
return
pool
def
vgg16_bn_drop
(
input
):
def
conv_block
(
input
,
num_filter
,
groups
,
dropouts
):
def
conv_block
(
input
,
num_filter
,
groups
,
dropouts
):
return
nets
.
img_conv_group
(
input
=
input
,
pool_size
=
2
,
...
...
@@ -123,22 +71,14 @@ def vgg16_bn_drop(input):
conv4
=
conv_block
(
conv3
,
512
,
3
,
[
0.4
,
0.4
,
0
])
conv5
=
conv_block
(
conv4
,
512
,
3
,
[
0.4
,
0.4
,
0
])
drop
=
layers
.
dropout
(
x
=
conv5
,
dropout_prob
=
0.5
)
drop
=
layers
.
dropout
(
x
=
conv5
,
dropout_prob
=
0.5
)
fc1
=
layers
.
fc
(
input
=
drop
,
size
=
512
,
act
=
None
,
param_attr
=
{
"initializer"
:
XavierInitializer
()})
reshape1
=
layers
.
reshape
(
x
=
fc1
,
shape
=
list
(
fc1
.
shape
+
(
1
,
1
)))
bn
=
layers
.
batch_norm
(
input
=
reshape1
,
act
=
'relu'
)
drop2
=
layers
.
dropout
(
x
=
bn
,
dropout_prob
=
0.5
)
reshape1
=
layers
.
reshape
(
x
=
fc1
,
shape
=
list
(
fc1
.
shape
+
(
1
,
1
)))
bn
=
layers
.
batch_norm
(
input
=
reshape1
,
act
=
'relu'
)
drop2
=
layers
.
dropout
(
x
=
bn
,
dropout_prob
=
0.5
)
fc2
=
layers
.
fc
(
input
=
drop2
,
size
=
512
,
act
=
None
,
...
...
@@ -165,8 +105,8 @@ cost = layers.cross_entropy(input=predict, label=label)
avg_cost
=
layers
.
mean
(
x
=
cost
)
accuracy
=
layers
.
accuracy
(
input
=
predict
,
label
=
label
)
# optimizer =
optimizer.
SGDOptimizer(learning_rate=0.001)
optimizer
=
optimizer
.
AdamOptimizer
(
learning_rate
=
0.001
)
# optimizer = SGDOptimizer(learning_rate=0.001)
optimizer
=
AdamOptimizer
(
learning_rate
=
0.001
)
opts
=
optimizer
.
minimize
(
avg_cost
)
BATCH_SIZE
=
128
...
...
python/paddle/v2/fluid/tests/book/test_recognize_digits_conv.py
浏览文件 @
0ce38b77
import
numpy
as
np
import
paddle.v2
as
paddle
import
paddle.v2.fluid.layers
as
layers
import
paddle.v2.fluid.nets
as
nets
import
paddle.v2.fluid.core
as
core
import
paddle.v2.fluid.optimizer
as
optimizer
import
paddle.v2.fluid.evaluator
as
evaluator
import
paddle.v2.fluid.framework
as
framework
import
paddle.v2.fluid.layers
as
layers
import
paddle.v2.fluid.nets
as
nets
from
paddle.v2.fluid.executor
import
Executor
from
paddle.v2.fluid.optimizer
import
AdamOptimizer
import
numpy
as
np
images
=
layers
.
data
(
name
=
'pixel'
,
shape
=
[
1
,
28
,
28
],
data_type
=
'float32'
)
label
=
layers
.
data
(
name
=
'label'
,
shape
=
[
1
],
data_type
=
'int64'
)
images
=
layers
.
data
(
name
=
'pixel'
,
shape
=
[
1
,
28
,
28
],
data_type
=
'float32'
)
label
=
layers
.
data
(
name
=
'label'
,
shape
=
[
1
],
data_type
=
'int64'
)
conv_pool_1
=
nets
.
simple_img_conv_pool
(
input
=
images
,
filter_size
=
5
,
...
...
@@ -32,17 +25,13 @@ conv_pool_2 = nets.simple_img_conv_pool(
pool_stride
=
2
,
act
=
"relu"
)
predict
=
layers
.
fc
(
input
=
conv_pool_2
,
size
=
10
,
act
=
"softmax"
)
predict
=
layers
.
fc
(
input
=
conv_pool_2
,
size
=
10
,
act
=
"softmax"
)
cost
=
layers
.
cross_entropy
(
input
=
predict
,
label
=
label
)
avg_cost
=
layers
.
mean
(
x
=
cost
)
optimizer
=
optimizer
.
AdamOptimizer
(
learning_rate
=
0.01
,
beta1
=
0.9
,
beta2
=
0.999
)
optimizer
=
AdamOptimizer
(
learning_rate
=
0.01
,
beta1
=
0.9
,
beta2
=
0.999
)
opts
=
optimizer
.
minimize
(
avg_cost
)
accuracy
,
acc_out
=
evaluator
.
accuracy
(
input
=
predict
,
label
=
label
)
accuracy
,
acc_out
=
evaluator
.
accuracy
(
input
=
predict
,
label
=
label
)
BATCH_SIZE
=
50
PASS_NUM
=
3
...
...
python/paddle/v2/fluid/tests/book/test_recognize_digits_mlp.py
浏览文件 @
0ce38b77
import
numpy
as
np
import
paddle.v2
as
paddle
import
paddle.v2.fluid.layers
as
layers
import
paddle.v2.fluid.core
as
core
import
paddle.v2.fluid.optimizer
as
optimizer
import
paddle.v2.fluid.framework
as
framework
import
paddle.v2.fluid.layers
as
layers
from
paddle.v2.fluid.executor
import
Executor
from
paddle.v2.fluid.regularizer
import
L2DecayRegularizer
from
paddle.v2.fluid.initializer
import
UniformInitializer
import
numpy
as
np
from
paddle.v2.fluid.optimizer
import
MomentumOptimizer
from
paddle.v2.fluid.regularizer
import
L2DecayRegularizer
BATCH_SIZE
=
128
image
=
layers
.
data
(
name
=
'x'
,
shape
=
[
784
],
data_type
=
'float32'
)
image
=
layers
.
data
(
name
=
'x'
,
shape
=
[
784
],
data_type
=
'float32'
)
param_attr
=
{
'name'
:
None
,
...
...
@@ -22,32 +18,21 @@ param_attr = {
'regularization'
:
L2DecayRegularizer
(
0.0005
*
BATCH_SIZE
)
}
hidden1
=
layers
.
fc
(
input
=
image
,
size
=
128
,
act
=
'relu'
,
param_attr
=
param_attr
)
hidden2
=
layers
.
fc
(
input
=
hidden1
,
size
=
64
,
act
=
'relu'
,
param_attr
=
param_attr
)
hidden1
=
layers
.
fc
(
input
=
image
,
size
=
128
,
act
=
'relu'
,
param_attr
=
param_attr
)
hidden2
=
layers
.
fc
(
input
=
hidden1
,
size
=
64
,
act
=
'relu'
,
param_attr
=
param_attr
)
predict
=
layers
.
fc
(
input
=
hidden2
,
size
=
10
,
act
=
'softmax'
,
param_attr
=
param_attr
)
label
=
layers
.
data
(
name
=
'y'
,
shape
=
[
1
],
data_type
=
'int64'
)
label
=
layers
.
data
(
name
=
'y'
,
shape
=
[
1
],
data_type
=
'int64'
)
cost
=
layers
.
cross_entropy
(
input
=
predict
,
label
=
label
)
avg_cost
=
layers
.
mean
(
x
=
cost
)
accuracy
=
layers
.
accuracy
(
input
=
predict
,
label
=
label
)
accuracy
=
layers
.
accuracy
(
input
=
predict
,
label
=
label
)
optimizer
=
optimizer
.
MomentumOptimizer
(
learning_rate
=
0.001
,
momentum
=
0.9
)
optimizer
=
MomentumOptimizer
(
learning_rate
=
0.001
,
momentum
=
0.9
)
opts
=
optimizer
.
minimize
(
avg_cost
)
train_reader
=
paddle
.
batch
(
...
...
python/paddle/v2/fluid/tests/book/test_recommender_system.py
浏览文件 @
0ce38b77
import
numpy
as
np
import
paddle.v2
as
paddle
import
paddle.v2.fluid.layers
as
layers
import
paddle.v2.fluid.nets
as
nets
import
paddle.v2.fluid.core
as
core
import
paddle.v2.fluid.optimizer
as
optimizer
import
paddle.v2.fluid.framework
as
framework
import
paddle.v2.fluid.layers
as
layers
import
paddle.v2.fluid.nets
as
nets
from
paddle.v2.fluid.executor
import
Executor
import
numpy
as
np
from
paddle.v2.fluid.optimizer
import
SGDOptimizer
IS_SPARSE
=
True
USE_GPU
=
False
...
...
@@ -19,10 +18,7 @@ def get_usr_combined_features():
USR_DICT_SIZE
=
paddle
.
dataset
.
movielens
.
max_user_id
()
+
1
uid
=
layers
.
data
(
name
=
'user_id'
,
shape
=
[
1
],
data_type
=
'int64'
)
uid
=
layers
.
data
(
name
=
'user_id'
,
shape
=
[
1
],
data_type
=
'int64'
)
usr_emb
=
layers
.
embedding
(
input
=
uid
,
...
...
@@ -31,15 +27,11 @@ def get_usr_combined_features():
param_attr
=
{
'name'
:
'user_table'
},
is_sparse
=
IS_SPARSE
)
usr_fc
=
layers
.
fc
(
input
=
usr_emb
,
size
=
32
)
usr_fc
=
layers
.
fc
(
input
=
usr_emb
,
size
=
32
)
USR_GENDER_DICT_SIZE
=
2
usr_gender_id
=
layers
.
data
(
name
=
'gender_id'
,
shape
=
[
1
],
data_type
=
'int64'
)
usr_gender_id
=
layers
.
data
(
name
=
'gender_id'
,
shape
=
[
1
],
data_type
=
'int64'
)
usr_gender_emb
=
layers
.
embedding
(
input
=
usr_gender_id
,
...
...
@@ -47,14 +39,10 @@ def get_usr_combined_features():
param_attr
=
{
'name'
:
'gender_table'
},
is_sparse
=
IS_SPARSE
)
usr_gender_fc
=
layers
.
fc
(
input
=
usr_gender_emb
,
size
=
16
)
usr_gender_fc
=
layers
.
fc
(
input
=
usr_gender_emb
,
size
=
16
)
USR_AGE_DICT_SIZE
=
len
(
paddle
.
dataset
.
movielens
.
age_table
)
usr_age_id
=
layers
.
data
(
name
=
'age_id'
,
shape
=
[
1
],
data_type
=
"int64"
)
usr_age_id
=
layers
.
data
(
name
=
'age_id'
,
shape
=
[
1
],
data_type
=
"int64"
)
usr_age_emb
=
layers
.
embedding
(
input
=
usr_age_id
,
...
...
@@ -62,14 +50,10 @@ def get_usr_combined_features():
is_sparse
=
IS_SPARSE
,
param_attr
=
{
'name'
:
'age_table'
})
usr_age_fc
=
layers
.
fc
(
input
=
usr_age_emb
,
size
=
16
)
usr_age_fc
=
layers
.
fc
(
input
=
usr_age_emb
,
size
=
16
)
USR_JOB_DICT_SIZE
=
paddle
.
dataset
.
movielens
.
max_job_id
()
+
1
usr_job_id
=
layers
.
data
(
name
=
'job_id'
,
shape
=
[
1
],
data_type
=
"int64"
)
usr_job_id
=
layers
.
data
(
name
=
'job_id'
,
shape
=
[
1
],
data_type
=
"int64"
)
usr_job_emb
=
layers
.
embedding
(
input
=
usr_job_id
,
...
...
@@ -77,16 +61,12 @@ def get_usr_combined_features():
param_attr
=
{
'name'
:
'job_table'
},
is_sparse
=
IS_SPARSE
)
usr_job_fc
=
layers
.
fc
(
input
=
usr_job_emb
,
size
=
16
)
usr_job_fc
=
layers
.
fc
(
input
=
usr_job_emb
,
size
=
16
)
concat_embed
=
layers
.
concat
(
input
=
[
usr_fc
,
usr_gender_fc
,
usr_age_fc
,
usr_job_fc
],
axis
=
1
)
input
=
[
usr_fc
,
usr_gender_fc
,
usr_age_fc
,
usr_job_fc
],
axis
=
1
)
usr_combined_features
=
layers
.
fc
(
input
=
concat_embed
,
size
=
200
,
act
=
"tanh"
)
usr_combined_features
=
layers
.
fc
(
input
=
concat_embed
,
size
=
200
,
act
=
"tanh"
)
return
usr_combined_features
...
...
@@ -95,10 +75,7 @@ def get_mov_combined_features():
MOV_DICT_SIZE
=
paddle
.
dataset
.
movielens
.
max_movie_id
()
+
1
mov_id
=
layers
.
data
(
name
=
'movie_id'
,
shape
=
[
1
],
data_type
=
'int64'
)
mov_id
=
layers
.
data
(
name
=
'movie_id'
,
shape
=
[
1
],
data_type
=
'int64'
)
mov_emb
=
layers
.
embedding
(
input
=
mov_id
,
...
...
@@ -107,36 +84,24 @@ def get_mov_combined_features():
param_attr
=
{
'name'
:
'movie_table'
},
is_sparse
=
IS_SPARSE
)
mov_fc
=
layers
.
fc
(
input
=
mov_emb
,
size
=
32
)
mov_fc
=
layers
.
fc
(
input
=
mov_emb
,
size
=
32
)
CATEGORY_DICT_SIZE
=
len
(
paddle
.
dataset
.
movielens
.
movie_categories
())
category_id
=
layers
.
data
(
name
=
'category_id'
,
shape
=
[
1
],
data_type
=
'int64'
)
category_id
=
layers
.
data
(
name
=
'category_id'
,
shape
=
[
1
],
data_type
=
'int64'
)
mov_categories_emb
=
layers
.
embedding
(
input
=
category_id
,
size
=
[
CATEGORY_DICT_SIZE
,
32
],
is_sparse
=
IS_SPARSE
)
input
=
category_id
,
size
=
[
CATEGORY_DICT_SIZE
,
32
],
is_sparse
=
IS_SPARSE
)
mov_categories_hidden
=
layers
.
sequence_pool
(
input
=
mov_categories_emb
,
pool_type
=
"sum"
)
input
=
mov_categories_emb
,
pool_type
=
"sum"
)
MOV_TITLE_DICT_SIZE
=
len
(
paddle
.
dataset
.
movielens
.
get_movie_title_dict
())
mov_title_id
=
layers
.
data
(
name
=
'movie_title'
,
shape
=
[
1
],
data_type
=
'int64'
)
mov_title_id
=
layers
.
data
(
name
=
'movie_title'
,
shape
=
[
1
],
data_type
=
'int64'
)
mov_title_emb
=
layers
.
embedding
(
input
=
mov_title_id
,
size
=
[
MOV_TITLE_DICT_SIZE
,
32
],
is_sparse
=
IS_SPARSE
)
input
=
mov_title_id
,
size
=
[
MOV_TITLE_DICT_SIZE
,
32
],
is_sparse
=
IS_SPARSE
)
mov_title_conv
=
nets
.
sequence_conv_pool
(
input
=
mov_title_emb
,
...
...
@@ -146,13 +111,10 @@ def get_mov_combined_features():
pool_type
=
"sum"
)
concat_embed
=
layers
.
concat
(
input
=
[
mov_fc
,
mov_categories_hidden
,
mov_title_conv
],
axis
=
1
)
input
=
[
mov_fc
,
mov_categories_hidden
,
mov_title_conv
],
axis
=
1
)
# FIXME(dzh) : need tanh operator
mov_combined_features
=
layers
.
fc
(
input
=
concat_embed
,
size
=
200
,
act
=
"tanh"
)
mov_combined_features
=
layers
.
fc
(
input
=
concat_embed
,
size
=
200
,
act
=
"tanh"
)
return
mov_combined_features
...
...
@@ -162,18 +124,11 @@ def model():
mov_combined_features
=
get_mov_combined_features
()
# need cos sim
inference
=
layers
.
cos_sim
(
X
=
usr_combined_features
,
Y
=
mov_combined_features
)
inference
=
layers
.
cos_sim
(
X
=
usr_combined_features
,
Y
=
mov_combined_features
)
label
=
layers
.
data
(
name
=
'score'
,
shape
=
[
1
],
data_type
=
'float32'
)
label
=
layers
.
data
(
name
=
'score'
,
shape
=
[
1
],
data_type
=
'float32'
)
square_cost
=
layers
.
square_error_cost
(
input
=
inference
,
label
=
label
)
square_cost
=
layers
.
square_error_cost
(
input
=
inference
,
label
=
label
)
avg_cost
=
layers
.
mean
(
x
=
square_cost
)
...
...
@@ -182,7 +137,7 @@ def model():
def
main
():
cost
=
model
()
sgd_optimizer
=
optimizer
.
SGDOptimizer
(
learning_rate
=
0.2
)
sgd_optimizer
=
SGDOptimizer
(
learning_rate
=
0.2
)
opts
=
sgd_optimizer
.
minimize
(
cost
)
if
USE_GPU
:
...
...
python/paddle/v2/fluid/tests/book/test_understand_sentiment_conv.py
浏览文件 @
0ce38b77
import
numpy
as
np
import
paddle.v2
as
paddle
import
paddle.v2.fluid.layers
as
layers
import
paddle.v2.fluid.nets
as
nets
import
paddle.v2.fluid.core
as
core
import
paddle.v2.fluid.optimizer
as
optimizer
import
paddle.v2.fluid.framework
as
framework
import
paddle.v2.fluid.layers
as
layers
import
paddle.v2.fluid.nets
as
nets
from
paddle.v2.fluid.executor
import
Executor
import
numpy
as
np
from
paddle.v2.fluid.optimizer
import
AdamOptimizer
def
convolution_net
(
input_dim
,
class_dim
=
2
,
emb_dim
=
32
,
hid_dim
=
32
):
...
...
@@ -31,7 +30,7 @@ def convolution_net(input_dim, class_dim=2, emb_dim=32, hid_dim=32):
act
=
"softmax"
)
cost
=
layers
.
cross_entropy
(
input
=
prediction
,
label
=
label
)
avg_cost
=
layers
.
mean
(
x
=
cost
)
adam_optimizer
=
optimizer
.
AdamOptimizer
(
learning_rate
=
0.002
)
adam_optimizer
=
AdamOptimizer
(
learning_rate
=
0.002
)
opts
=
adam_optimizer
.
minimize
(
avg_cost
)
acc
=
layers
.
accuracy
(
input
=
prediction
,
label
=
label
)
return
avg_cost
,
acc
...
...
python/paddle/v2/fluid/tests/book/test_understand_sentiment_dynamic_lstm.py
浏览文件 @
0ce38b77
import
numpy
as
np
import
paddle.v2
as
paddle
import
paddle.v2.fluid.layers
as
layers
import
paddle.v2.fluid.nets
as
nets
import
paddle.v2.fluid.core
as
core
import
paddle.v2.fluid.optimizer
as
optimizer
import
paddle.v2.fluid.framework
as
framework
import
paddle.v2.fluid.layers
as
layers
from
paddle.v2.fluid.executor
import
Executor
import
numpy
as
np
from
paddle.v2.fluid.optimizer
import
AdamOptimizer
def
stacked_lstm_net
(
input_dim
,
...
...
@@ -41,7 +39,7 @@ def stacked_lstm_net(input_dim,
act
=
'softmax'
)
cost
=
layers
.
cross_entropy
(
input
=
prediction
,
label
=
label
)
avg_cost
=
layers
.
mean
(
x
=
cost
)
adam_optimizer
=
optimizer
.
AdamOptimizer
(
learning_rate
=
0.002
)
adam_optimizer
=
AdamOptimizer
(
learning_rate
=
0.002
)
opts
=
adam_optimizer
.
minimize
(
avg_cost
)
acc
=
layers
.
accuracy
(
input
=
prediction
,
label
=
label
)
return
avg_cost
,
acc
...
...
python/paddle/v2/fluid/tests/book/test_understand_sentiment_lstm.py
浏览文件 @
0ce38b77
import
numpy
as
np
import
paddle.v2
as
paddle
import
paddle.v2.fluid.layers
as
layers
import
paddle.v2.fluid.core
as
core
import
paddle.v2.fluid.optimizer
as
optimizer
import
paddle.v2.fluid.framework
as
framework
import
paddle.v2.fluid.layers
as
layers
from
paddle.v2.fluid.executor
import
Executor
import
numpy
as
np
from
paddle.v2.fluid.optimizer
import
AdamOptimizer
def
lstm_net
(
dict_dim
,
class_dim
=
2
,
emb_dim
=
32
,
seq_len
=
80
,
batch_size
=
50
):
...
...
@@ -33,7 +32,7 @@ def lstm_net(dict_dim, class_dim=2, emb_dim=32, seq_len=80, batch_size=50):
cost
=
layers
.
cross_entropy
(
input
=
prediction
,
label
=
label
)
avg_cost
=
layers
.
mean
(
x
=
cost
)
adam_optimizer
=
optimizer
.
AdamOptimizer
(
learning_rate
=
0.002
)
adam_optimizer
=
AdamOptimizer
(
learning_rate
=
0.002
)
opts
=
adam_optimizer
.
minimize
(
avg_cost
)
acc
=
layers
.
accuracy
(
input
=
prediction
,
label
=
label
)
...
...
python/paddle/v2/fluid/tests/book/test_word2vec.py
浏览文件 @
0ce38b77
import
numpy
as
np
import
paddle.v2
as
paddle
import
paddle.v2.fluid.layers
as
layers
import
paddle.v2.fluid.core
as
core
import
paddle.v2.fluid.optimizer
as
optimizer
import
paddle.v2.fluid.framework
as
framework
import
paddle.v2.fluid.layers
as
layers
from
paddle.v2.fluid.executor
import
Executor
import
numpy
as
np
from
paddle.v2.fluid.optimizer
import
SGDOptimizer
PASS_NUM
=
100
EMBED_SIZE
=
32
...
...
@@ -17,26 +16,11 @@ IS_SPARSE = True
word_dict
=
paddle
.
dataset
.
imikolov
.
build_dict
()
dict_size
=
len
(
word_dict
)
first_word
=
layers
.
data
(
name
=
'firstw'
,
shape
=
[
1
],
data_type
=
'int64'
)
second_word
=
layers
.
data
(
name
=
'secondw'
,
shape
=
[
1
],
data_type
=
'int64'
)
third_word
=
layers
.
data
(
name
=
'thirdw'
,
shape
=
[
1
],
data_type
=
'int64'
)
forth_word
=
layers
.
data
(
name
=
'forthw'
,
shape
=
[
1
],
data_type
=
'int64'
)
next_word
=
layers
.
data
(
name
=
'nextw'
,
shape
=
[
1
],
data_type
=
'int64'
)
first_word
=
layers
.
data
(
name
=
'firstw'
,
shape
=
[
1
],
data_type
=
'int64'
)
second_word
=
layers
.
data
(
name
=
'secondw'
,
shape
=
[
1
],
data_type
=
'int64'
)
third_word
=
layers
.
data
(
name
=
'thirdw'
,
shape
=
[
1
],
data_type
=
'int64'
)
forth_word
=
layers
.
data
(
name
=
'forthw'
,
shape
=
[
1
],
data_type
=
'int64'
)
next_word
=
layers
.
data
(
name
=
'nextw'
,
shape
=
[
1
],
data_type
=
'int64'
)
embed_first
=
layers
.
embedding
(
input
=
first_word
,
...
...
@@ -64,19 +48,12 @@ embed_forth = layers.embedding(
param_attr
=
{
'name'
:
'shared_w'
})
concat_embed
=
layers
.
concat
(
input
=
[
embed_first
,
embed_second
,
embed_third
,
embed_forth
],
axis
=
1
)
hidden1
=
layers
.
fc
(
input
=
concat_embed
,
size
=
HIDDEN_SIZE
,
act
=
'sigmoid'
)
predict_word
=
layers
.
fc
(
input
=
hidden1
,
size
=
dict_size
,
act
=
'softmax'
)
cost
=
layers
.
cross_entropy
(
input
=
predict_word
,
label
=
next_word
)
input
=
[
embed_first
,
embed_second
,
embed_third
,
embed_forth
],
axis
=
1
)
hidden1
=
layers
.
fc
(
input
=
concat_embed
,
size
=
HIDDEN_SIZE
,
act
=
'sigmoid'
)
predict_word
=
layers
.
fc
(
input
=
hidden1
,
size
=
dict_size
,
act
=
'softmax'
)
cost
=
layers
.
cross_entropy
(
input
=
predict_word
,
label
=
next_word
)
avg_cost
=
layers
.
mean
(
x
=
cost
)
sgd_optimizer
=
optimizer
.
SGDOptimizer
(
learning_rate
=
0.001
)
sgd_optimizer
=
SGDOptimizer
(
learning_rate
=
0.001
)
opts
=
sgd_optimizer
.
minimize
(
avg_cost
)
train_reader
=
paddle
.
batch
(
...
...
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