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
models
提交
5312aaa1
M
models
项目概览
PaddlePaddle
/
models
大约 2 年 前同步成功
通知
232
Star
6828
Fork
2962
代码
文件
提交
分支
Tags
贡献者
分支图
Diff
Issue
602
列表
看板
标记
里程碑
合并请求
255
Wiki
0
Wiki
分析
仓库
DevOps
项目成员
Pages
M
models
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
602
Issue
602
列表
看板
标记
里程碑
合并请求
255
合并请求
255
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
未验证
提交
5312aaa1
编写于
2月 17, 2020
作者:
H
hutuxian
提交者:
GitHub
2月 17, 2020
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
upgrade API for 1.7(din & sr-gnn) (#4301)
Upgrade API for 1.7 * PaddleRec/din * PaddleRec/gnn
上级
68c7b046
变更
8
隐藏空白更改
内联
并排
Showing
8 changed file
with
91 addition
and
103 deletion
+91
-103
PaddleRec/din/infer.py
PaddleRec/din/infer.py
+8
-7
PaddleRec/din/network.py
PaddleRec/din/network.py
+31
-28
PaddleRec/din/reader.py
PaddleRec/din/reader.py
+3
-3
PaddleRec/din/train.py
PaddleRec/din/train.py
+6
-9
PaddleRec/gnn/infer.py
PaddleRec/gnn/infer.py
+2
-2
PaddleRec/gnn/network.py
PaddleRec/gnn/network.py
+28
-44
PaddleRec/gnn/reader.py
PaddleRec/gnn/reader.py
+9
-7
PaddleRec/gnn/train.py
PaddleRec/gnn/train.py
+4
-3
未找到文件。
PaddleRec/din/infer.py
浏览文件 @
5312aaa1
...
@@ -78,20 +78,21 @@ def infer():
...
@@ -78,20 +78,21 @@ def infer():
[
inference_program
,
feed_target_names
,
[
inference_program
,
feed_target_names
,
fetch_targets
]
=
fluid
.
io
.
load_inference_model
(
model_path
,
exe
)
fetch_targets
]
=
fluid
.
io
.
load_inference_model
(
model_path
,
exe
)
feeder
=
fluid
.
DataFeeder
(
loader
=
fluid
.
io
.
DataLoader
.
from_generator
(
feed_list
=
feed_target_names
,
place
=
place
,
program
=
inference_program
)
feed_list
=
[
inference_program
.
block
(
0
).
var
(
e
)
for
e
in
feed_target_names
],
capacity
=
10000
,
iterable
=
True
)
loader
.
set_sample_list_generator
(
data_reader
,
places
=
fluid
.
cuda_places
())
loss_sum
=
0.0
loss_sum
=
0.0
score
=
[]
score
=
[]
count
=
0
count
=
0
for
data
in
data_re
ader
():
for
data
in
lo
ader
():
res
=
exe
.
run
(
inference_program
,
res
=
exe
.
run
(
inference_program
,
feed
=
feeder
.
feed
(
data
)
,
feed
=
data
,
fetch_list
=
fetch_targets
)
fetch_list
=
fetch_targets
)
loss_sum
+=
res
[
0
]
loss_sum
+=
res
[
0
]
label_data
=
list
(
np
.
array
(
data
[
0
][
"label"
]))
for
i
in
range
(
len
(
data
)):
for
i
in
range
(
len
(
label_
data
)):
if
data
[
i
][
4
]
>
0.5
:
if
label_data
[
i
]
>
0.5
:
score
.
append
([
0
,
1
,
res
[
1
][
i
]])
score
.
append
([
0
,
1
,
res
[
1
][
i
]])
else
:
else
:
score
.
append
([
1
,
0
,
res
[
1
][
i
]])
score
.
append
([
1
,
0
,
res
[
1
][
i
]])
...
...
PaddleRec/din/network.py
浏览文件 @
5312aaa1
...
@@ -14,7 +14,7 @@
...
@@ -14,7 +14,7 @@
import
paddle.fluid
as
fluid
import
paddle.fluid
as
fluid
def
din_attention
(
hist
,
target_expand
,
ma
x_len
,
ma
sk
):
def
din_attention
(
hist
,
target_expand
,
mask
):
"""activation weight"""
"""activation weight"""
hidden_size
=
hist
.
shape
[
-
1
]
hidden_size
=
hist
.
shape
[
-
1
]
...
@@ -45,9 +45,10 @@ def din_attention(hist, target_expand, max_len, mask):
...
@@ -45,9 +45,10 @@ def din_attention(hist, target_expand, max_len, mask):
return
out
return
out
def
network
(
item_count
,
cat_count
,
max_len
):
def
network
(
item_count
,
cat_count
):
"""network definition"""
"""network definition"""
seq_len
=
-
1
item_emb_size
=
64
item_emb_size
=
64
cat_emb_size
=
64
cat_emb_size
=
64
is_sparse
=
False
is_sparse
=
False
...
@@ -56,60 +57,60 @@ def network(item_count, cat_count, max_len):
...
@@ -56,60 +57,60 @@ def network(item_count, cat_count, max_len):
item_emb_attr
=
fluid
.
ParamAttr
(
name
=
"item_emb"
)
item_emb_attr
=
fluid
.
ParamAttr
(
name
=
"item_emb"
)
cat_emb_attr
=
fluid
.
ParamAttr
(
name
=
"cat_emb"
)
cat_emb_attr
=
fluid
.
ParamAttr
(
name
=
"cat_emb"
)
hist_item_seq
=
fluid
.
layers
.
data
(
hist_item_seq
=
fluid
.
data
(
name
=
"hist_item_seq"
,
shape
=
[
max_len
,
1
],
dtype
=
"int64"
)
name
=
"hist_item_seq"
,
shape
=
[
None
,
seq_len
],
dtype
=
"int64"
)
hist_cat_seq
=
fluid
.
layers
.
data
(
hist_cat_seq
=
fluid
.
data
(
name
=
"hist_cat_seq"
,
shape
=
[
max_len
,
1
],
dtype
=
"int64"
)
name
=
"hist_cat_seq"
,
shape
=
[
None
,
seq_len
],
dtype
=
"int64"
)
target_item
=
fluid
.
layers
.
data
(
target_item
=
fluid
.
data
(
name
=
"target_item"
,
shape
=
[
1
],
dtype
=
"int64"
)
name
=
"target_item"
,
shape
=
[
None
],
dtype
=
"int64"
)
target_cat
=
fluid
.
layers
.
data
(
target_cat
=
fluid
.
data
(
name
=
"target_cat"
,
shape
=
[
1
],
dtype
=
"int64"
)
name
=
"target_cat"
,
shape
=
[
None
],
dtype
=
"int64"
)
label
=
fluid
.
layers
.
data
(
label
=
fluid
.
data
(
name
=
"label"
,
shape
=
[
1
],
dtype
=
"float32"
)
name
=
"label"
,
shape
=
[
None
,
1
],
dtype
=
"float32"
)
mask
=
fluid
.
layers
.
data
(
mask
=
fluid
.
data
(
name
=
"mask"
,
shape
=
[
max
_len
,
1
],
dtype
=
"float32"
)
name
=
"mask"
,
shape
=
[
None
,
seq
_len
,
1
],
dtype
=
"float32"
)
target_item_seq
=
fluid
.
layers
.
data
(
target_item_seq
=
fluid
.
data
(
name
=
"target_item_seq"
,
shape
=
[
max_len
,
1
],
dtype
=
"int64"
)
name
=
"target_item_seq"
,
shape
=
[
None
,
seq_len
],
dtype
=
"int64"
)
target_cat_seq
=
fluid
.
layers
.
data
(
target_cat_seq
=
fluid
.
data
(
name
=
"target_cat_seq"
,
shape
=
[
max_len
,
1
],
dtype
=
"int64"
,
lod_level
=
0
)
name
=
"target_cat_seq"
,
shape
=
[
None
,
seq_len
],
dtype
=
"int64"
)
hist_item_emb
=
fluid
.
layers
.
embedding
(
hist_item_emb
=
fluid
.
embedding
(
input
=
hist_item_seq
,
input
=
hist_item_seq
,
size
=
[
item_count
,
item_emb_size
],
size
=
[
item_count
,
item_emb_size
],
param_attr
=
item_emb_attr
,
param_attr
=
item_emb_attr
,
is_sparse
=
is_sparse
)
is_sparse
=
is_sparse
)
hist_cat_emb
=
fluid
.
layers
.
embedding
(
hist_cat_emb
=
fluid
.
embedding
(
input
=
hist_cat_seq
,
input
=
hist_cat_seq
,
size
=
[
cat_count
,
cat_emb_size
],
size
=
[
cat_count
,
cat_emb_size
],
param_attr
=
cat_emb_attr
,
param_attr
=
cat_emb_attr
,
is_sparse
=
is_sparse
)
is_sparse
=
is_sparse
)
target_item_emb
=
fluid
.
layers
.
embedding
(
target_item_emb
=
fluid
.
embedding
(
input
=
target_item
,
input
=
target_item
,
size
=
[
item_count
,
item_emb_size
],
size
=
[
item_count
,
item_emb_size
],
param_attr
=
item_emb_attr
,
param_attr
=
item_emb_attr
,
is_sparse
=
is_sparse
)
is_sparse
=
is_sparse
)
target_cat_emb
=
fluid
.
layers
.
embedding
(
target_cat_emb
=
fluid
.
embedding
(
input
=
target_cat
,
input
=
target_cat
,
size
=
[
cat_count
,
cat_emb_size
],
size
=
[
cat_count
,
cat_emb_size
],
param_attr
=
cat_emb_attr
,
param_attr
=
cat_emb_attr
,
is_sparse
=
is_sparse
)
is_sparse
=
is_sparse
)
target_item_seq_emb
=
fluid
.
layers
.
embedding
(
target_item_seq_emb
=
fluid
.
embedding
(
input
=
target_item_seq
,
input
=
target_item_seq
,
size
=
[
item_count
,
item_emb_size
],
size
=
[
item_count
,
item_emb_size
],
param_attr
=
item_emb_attr
,
param_attr
=
item_emb_attr
,
is_sparse
=
is_sparse
)
is_sparse
=
is_sparse
)
target_cat_seq_emb
=
fluid
.
layers
.
embedding
(
target_cat_seq_emb
=
fluid
.
embedding
(
input
=
target_cat_seq
,
input
=
target_cat_seq
,
size
=
[
cat_count
,
cat_emb_size
],
size
=
[
cat_count
,
cat_emb_size
],
param_attr
=
cat_emb_attr
,
param_attr
=
cat_emb_attr
,
is_sparse
=
is_sparse
)
is_sparse
=
is_sparse
)
item_b
=
fluid
.
layers
.
embedding
(
item_b
=
fluid
.
embedding
(
input
=
target_item
,
input
=
target_item
,
size
=
[
item_count
,
1
],
size
=
[
item_count
,
1
],
param_attr
=
fluid
.
initializer
.
Constant
(
value
=
0.0
))
param_attr
=
fluid
.
initializer
.
Constant
(
value
=
0.0
))
...
@@ -120,7 +121,7 @@ def network(item_count, cat_count, max_len):
...
@@ -120,7 +121,7 @@ def network(item_count, cat_count, max_len):
target_concat
=
fluid
.
layers
.
concat
(
target_concat
=
fluid
.
layers
.
concat
(
[
target_item_emb
,
target_cat_emb
],
axis
=
1
)
[
target_item_emb
,
target_cat_emb
],
axis
=
1
)
out
=
din_attention
(
hist_seq_concat
,
target_seq_concat
,
ma
x_len
,
ma
sk
)
out
=
din_attention
(
hist_seq_concat
,
target_seq_concat
,
mask
)
out_fc
=
fluid
.
layers
.
fc
(
name
=
"out_fc"
,
out_fc
=
fluid
.
layers
.
fc
(
name
=
"out_fc"
,
input
=
out
,
input
=
out
,
size
=
item_emb_size
+
cat_emb_size
,
size
=
item_emb_size
+
cat_emb_size
,
...
@@ -137,4 +138,6 @@ def network(item_count, cat_count, max_len):
...
@@ -137,4 +138,6 @@ def network(item_count, cat_count, max_len):
loss
=
fluid
.
layers
.
sigmoid_cross_entropy_with_logits
(
x
=
logit
,
label
=
label
)
loss
=
fluid
.
layers
.
sigmoid_cross_entropy_with_logits
(
x
=
logit
,
label
=
label
)
avg_loss
=
fluid
.
layers
.
mean
(
loss
)
avg_loss
=
fluid
.
layers
.
mean
(
loss
)
return
avg_loss
,
fluid
.
layers
.
sigmoid
(
logit
)
return
avg_loss
,
fluid
.
layers
.
sigmoid
(
logit
),
\
[
hist_item_seq
,
hist_cat_seq
,
target_item
,
\
target_cat
,
label
,
mask
,
target_item_seq
,
target_cat_seq
]
PaddleRec/din/reader.py
浏览文件 @
5312aaa1
...
@@ -20,7 +20,7 @@ import pickle
...
@@ -20,7 +20,7 @@ import pickle
def
pad_batch_data
(
input
,
max_len
):
def
pad_batch_data
(
input
,
max_len
):
res
=
np
.
array
([
x
+
[
0
]
*
(
max_len
-
len
(
x
))
for
x
in
input
])
res
=
np
.
array
([
x
+
[
0
]
*
(
max_len
-
len
(
x
))
for
x
in
input
])
res
=
res
.
astype
(
"int64"
).
reshape
([
-
1
,
max_len
,
1
])
res
=
res
.
astype
(
"int64"
).
reshape
([
-
1
,
max_len
])
return
res
return
res
...
@@ -34,10 +34,10 @@ def make_data(b):
...
@@ -34,10 +34,10 @@ def make_data(b):
[
-
1
,
max_len
,
1
])
[
-
1
,
max_len
,
1
])
target_item_seq
=
np
.
array
(
target_item_seq
=
np
.
array
(
[[
x
[
2
]]
*
max_len
for
x
in
b
]).
astype
(
"int64"
).
reshape
(
[[
x
[
2
]]
*
max_len
for
x
in
b
]).
astype
(
"int64"
).
reshape
(
[
-
1
,
max_len
,
1
])
[
-
1
,
max_len
])
target_cat_seq
=
np
.
array
(
target_cat_seq
=
np
.
array
(
[[
x
[
3
]]
*
max_len
for
x
in
b
]).
astype
(
"int64"
).
reshape
(
[[
x
[
3
]]
*
max_len
for
x
in
b
]).
astype
(
"int64"
).
reshape
(
[
-
1
,
max_len
,
1
])
[
-
1
,
max_len
])
res
=
[]
res
=
[]
for
i
in
range
(
len
(
b
)):
for
i
in
range
(
len
(
b
)):
res
.
append
([
res
.
append
([
...
...
PaddleRec/din/train.py
浏览文件 @
5312aaa1
...
@@ -78,7 +78,7 @@ def train():
...
@@ -78,7 +78,7 @@ def train():
args
.
num_devices
)
args
.
num_devices
)
logger
.
info
(
"reading data completes"
)
logger
.
info
(
"reading data completes"
)
avg_cost
,
pred
=
network
.
network
(
item_count
,
cat_count
,
max_len
)
avg_cost
,
pred
,
feed_list
=
network
.
network
(
item_count
,
cat_count
)
fluid
.
clip
.
set_gradient_clip
(
clip
=
fluid
.
clip
.
GradientClipByGlobalNorm
(
fluid
.
clip
.
set_gradient_clip
(
clip
=
fluid
.
clip
.
GradientClipByGlobalNorm
(
clip_norm
=
5.0
))
clip_norm
=
5.0
))
base_lr
=
args
.
base_lr
base_lr
=
args
.
base_lr
...
@@ -94,12 +94,9 @@ def train():
...
@@ -94,12 +94,9 @@ def train():
exe
=
fluid
.
Executor
(
place
)
exe
=
fluid
.
Executor
(
place
)
exe
.
run
(
fluid
.
default_startup_program
())
exe
.
run
(
fluid
.
default_startup_program
())
feeder
=
fluid
.
DataFeeder
(
loader
=
fluid
.
io
.
DataLoader
.
from_generator
(
feed_list
=
[
feed_list
=
feed_list
,
capacity
=
10000
,
iterable
=
True
)
"hist_item_seq"
,
"hist_cat_seq"
,
"target_item"
,
"target_cat"
,
loader
.
set_sample_list_generator
(
data_reader
,
places
=
fluid
.
cuda_places
())
"label"
,
"mask"
,
"target_item_seq"
,
"target_cat_seq"
],
place
=
place
)
if
use_parallel
:
if
use_parallel
:
train_exe
=
fluid
.
ParallelExecutor
(
train_exe
=
fluid
.
ParallelExecutor
(
use_cuda
=
use_cuda
,
loss_name
=
avg_cost
.
name
)
use_cuda
=
use_cuda
,
loss_name
=
avg_cost
.
name
)
...
@@ -117,9 +114,9 @@ def train():
...
@@ -117,9 +114,9 @@ def train():
loss_sum
=
0.0
loss_sum
=
0.0
for
id
in
range
(
epoch_num
):
for
id
in
range
(
epoch_num
):
epoch
=
id
+
1
epoch
=
id
+
1
for
data
in
data_re
ader
():
for
data
in
lo
ader
():
global_step
+=
1
global_step
+=
1
results
=
train_exe
.
run
(
feed
=
feeder
.
feed
(
data
)
,
results
=
train_exe
.
run
(
feed
=
data
,
fetch_list
=
[
avg_cost
.
name
,
pred
.
name
],
fetch_list
=
[
avg_cost
.
name
,
pred
.
name
],
return_numpy
=
True
)
return_numpy
=
True
)
loss_sum
+=
results
[
0
].
mean
()
loss_sum
+=
results
[
0
].
mean
()
...
...
PaddleRec/gnn/infer.py
浏览文件 @
5312aaa1
...
@@ -55,7 +55,7 @@ def infer(args):
...
@@ -55,7 +55,7 @@ def infer(args):
test_data
=
reader
.
Data
(
args
.
test_path
,
False
)
test_data
=
reader
.
Data
(
args
.
test_path
,
False
)
place
=
fluid
.
CUDAPlace
(
0
)
if
args
.
use_cuda
else
fluid
.
CPUPlace
()
place
=
fluid
.
CUDAPlace
(
0
)
if
args
.
use_cuda
else
fluid
.
CPUPlace
()
exe
=
fluid
.
Executor
(
place
)
exe
=
fluid
.
Executor
(
place
)
loss
,
acc
,
py_reader
,
feed_datas
=
network
.
network
(
items_num
,
args
.
hidden_size
,
args
.
step
)
loss
,
acc
,
py_reader
,
feed_datas
=
network
.
network
(
items_num
,
args
.
hidden_size
,
args
.
step
,
batch_size
)
exe
.
run
(
fluid
.
default_startup_program
())
exe
.
run
(
fluid
.
default_startup_program
())
infer_program
=
fluid
.
default_main_program
().
clone
(
for_test
=
True
)
infer_program
=
fluid
.
default_main_program
().
clone
(
for_test
=
True
)
...
@@ -70,7 +70,7 @@ def infer(args):
...
@@ -70,7 +70,7 @@ def infer(args):
loss_sum
=
0.0
loss_sum
=
0.0
acc_sum
=
0.0
acc_sum
=
0.0
count
=
0
count
=
0
py_reader
.
decorate_paddle_reade
r
(
test_data
.
reader
(
batch_size
,
batch_size
*
20
,
False
))
py_reader
.
set_sample_list_generato
r
(
test_data
.
reader
(
batch_size
,
batch_size
*
20
,
False
))
py_reader
.
start
()
py_reader
.
start
()
try
:
try
:
while
True
:
while
True
:
...
...
PaddleRec/gnn/network.py
浏览文件 @
5312aaa1
...
@@ -19,57 +19,53 @@ import paddle.fluid as fluid
...
@@ -19,57 +19,53 @@ import paddle.fluid as fluid
import
paddle.fluid.layers
as
layers
import
paddle.fluid.layers
as
layers
def
network
(
items_num
,
hidden_size
,
step
):
def
network
(
items_num
,
hidden_size
,
step
,
bs
):
stdv
=
1.0
/
math
.
sqrt
(
hidden_size
)
stdv
=
1.0
/
math
.
sqrt
(
hidden_size
)
items
=
layers
.
data
(
items
=
fluid
.
data
(
name
=
"items"
,
name
=
"items"
,
shape
=
[
1
,
1
],
shape
=
[
bs
,
-
1
],
dtype
=
"int64"
)
#[batch_size, uniq_max
, 1
]
dtype
=
"int64"
)
#[batch_size, uniq_max]
seq_index
=
layers
.
data
(
seq_index
=
fluid
.
data
(
name
=
"seq_index"
,
name
=
"seq_index"
,
shape
=
[
1
],
shape
=
[
bs
,
-
1
,
2
],
dtype
=
"int32"
)
#[batch_size, seq_max]
dtype
=
"int32"
)
#[batch_size, seq_max
, 2
]
last_index
=
layers
.
data
(
last_index
=
fluid
.
data
(
name
=
"last_index"
,
name
=
"last_index"
,
shape
=
[
1
],
shape
=
[
bs
,
2
],
dtype
=
"int32"
)
#[batch_size,
1
]
dtype
=
"int32"
)
#[batch_size,
2
]
adj_in
=
layers
.
data
(
adj_in
=
fluid
.
data
(
name
=
"adj_in"
,
name
=
"adj_in"
,
shape
=
[
1
,
1
],
shape
=
[
bs
,
-
1
,
-
1
],
dtype
=
"float32"
)
#[batch_size, seq_max, seq_max]
dtype
=
"float32"
)
#[batch_size, seq_max, seq_max]
adj_out
=
layers
.
data
(
adj_out
=
fluid
.
data
(
name
=
"adj_out"
,
name
=
"adj_out"
,
shape
=
[
1
,
1
],
shape
=
[
bs
,
-
1
,
-
1
],
dtype
=
"float32"
)
#[batch_size, seq_max, seq_max]
dtype
=
"float32"
)
#[batch_size, seq_max, seq_max]
mask
=
layers
.
data
(
mask
=
fluid
.
data
(
name
=
"mask"
,
name
=
"mask"
,
shape
=
[
1
,
1
],
shape
=
[
bs
,
-
1
,
1
],
dtype
=
"float32"
)
#[batch_size, seq_max, 1]
dtype
=
"float32"
)
#[batch_size, seq_max, 1]
label
=
layers
.
data
(
label
=
fluid
.
data
(
name
=
"label"
,
name
=
"label"
,
shape
=
[
1
],
shape
=
[
bs
,
1
],
dtype
=
"int64"
)
#[batch_size, 1]
dtype
=
"int64"
)
#[batch_size, 1]
datas
=
[
items
,
seq_index
,
last_index
,
adj_in
,
adj_out
,
mask
,
label
]
datas
=
[
items
,
seq_index
,
last_index
,
adj_in
,
adj_out
,
mask
,
label
]
py_reader
=
fluid
.
layers
.
create_py_reader_by_data
(
py_reader
=
fluid
.
io
.
DataLoader
.
from_generator
(
capacity
=
256
,
feed_list
=
datas
,
iterable
=
False
)
capacity
=
256
,
feed_list
=
datas
,
name
=
'py_reader'
,
use_double_buffer
=
True
)
feed_datas
=
datas
feed_datas
=
fluid
.
layers
.
read_file
(
py_reader
)
items
,
seq_index
,
last_index
,
adj_in
,
adj_out
,
mask
,
label
=
feed_datas
items_emb
=
layers
.
embedding
(
items_emb
=
fluid
.
embedding
(
input
=
items
,
input
=
items
,
param_attr
=
fluid
.
ParamAttr
(
param_attr
=
fluid
.
ParamAttr
(
name
=
"emb"
,
name
=
"emb"
,
initializer
=
fluid
.
initializer
.
Uniform
(
initializer
=
fluid
.
initializer
.
Uniform
(
low
=-
stdv
,
high
=
stdv
)),
low
=-
stdv
,
high
=
stdv
)),
size
=
[
items_num
,
hidden_size
])
#[batch_size, uniq_max, h]
size
=
[
items_num
,
hidden_size
])
#[batch_size, uniq_max, h]
items_emb_shape
=
layers
.
shape
(
items_emb
)
pre_state
=
items_emb
pre_state
=
items_emb
for
i
in
range
(
step
):
for
i
in
range
(
step
):
pre_state
=
layers
.
reshape
(
pre_state
=
layers
.
reshape
(
x
=
pre_state
,
shape
=
[
bs
,
-
1
,
hidden_size
])
x
=
pre_state
,
shape
=
[
-
1
,
1
,
hidden_size
],
actual_shape
=
items_emb_shape
)
state_in
=
layers
.
fc
(
state_in
=
layers
.
fc
(
input
=
pre_state
,
input
=
pre_state
,
name
=
"state_in"
,
name
=
"state_in"
,
...
@@ -104,24 +100,12 @@ def network(items_num, hidden_size, step):
...
@@ -104,24 +100,12 @@ def network(items_num, hidden_size, step):
bias_attr
=
False
)
bias_attr
=
False
)
pre_state
,
_
,
_
=
fluid
.
layers
.
gru_unit
(
pre_state
,
_
,
_
=
fluid
.
layers
.
gru_unit
(
input
=
gru_fc
,
input
=
gru_fc
,
hidden
=
layers
.
reshape
(
hidden
=
layers
.
reshape
(
x
=
pre_state
,
shape
=
[
-
1
,
hidden_size
]),
x
=
pre_state
,
shape
=
[
-
1
,
hidden_size
]),
size
=
3
*
hidden_size
)
size
=
3
*
hidden_size
)
final_state
=
pre_state
#[batch_size * uniq_max, h]
final_state
=
layers
.
reshape
(
pre_state
,
shape
=
[
bs
,
-
1
,
hidden_size
])
seq
=
layers
.
gather_nd
(
final_state
,
seq_index
)
seq_origin_shape
=
layers
.
assign
(
np
.
array
([
0
,
0
,
hidden_size
-
1
]).
astype
(
"int32"
))
last
=
layers
.
gather_nd
(
final_state
,
last_index
)
seq_origin_shape
+=
layers
.
shape
(
layers
.
unsqueeze
(
seq_index
,[
2
]))
#value: [batch_size, seq_max, h]
seq_origin_shape
.
stop_gradient
=
True
seq_index
=
layers
.
reshape
(
seq_index
,
shape
=
[
-
1
])
seq
=
layers
.
gather
(
final_state
,
seq_index
)
#[batch_size * seq_max, h]
last
=
layers
.
gather
(
final_state
,
last_index
)
#[batch_size, h]
seq
=
layers
.
reshape
(
seq
,
shape
=
[
-
1
,
1
,
hidden_size
],
actual_shape
=
seq_origin_shape
)
#[batch_size, seq_max, h]
last
=
layers
.
reshape
(
last
,
shape
=
[
-
1
,
hidden_size
])
#[batch_size, h]
seq_fc
=
layers
.
fc
(
seq_fc
=
layers
.
fc
(
input
=
seq
,
input
=
seq
,
...
@@ -184,13 +168,13 @@ def network(items_num, hidden_size, step):
...
@@ -184,13 +168,13 @@ def network(items_num, hidden_size, step):
low
=-
stdv
,
high
=
stdv
)))
#[batch_size, h]
low
=-
stdv
,
high
=
stdv
)))
#[batch_size, h]
all_vocab
=
layers
.
create_global_var
(
all_vocab
=
layers
.
create_global_var
(
shape
=
[
items_num
-
1
,
1
],
shape
=
[
items_num
-
1
],
value
=
0
,
value
=
0
,
dtype
=
"int64"
,
dtype
=
"int64"
,
persistable
=
True
,
persistable
=
True
,
name
=
"all_vocab"
)
name
=
"all_vocab"
)
all_emb
=
layers
.
embedding
(
all_emb
=
fluid
.
embedding
(
input
=
all_vocab
,
input
=
all_vocab
,
param_attr
=
fluid
.
ParamAttr
(
param_attr
=
fluid
.
ParamAttr
(
name
=
"emb"
,
name
=
"emb"
,
...
...
PaddleRec/gnn/reader.py
浏览文件 @
5312aaa1
...
@@ -64,19 +64,19 @@ class Data():
...
@@ -64,19 +64,19 @@ class Data():
adj_out
.
append
(
np
.
divide
(
adj
.
transpose
(),
u_deg_out
).
transpose
())
adj_out
.
append
(
np
.
divide
(
adj
.
transpose
(),
u_deg_out
).
transpose
())
seq_index
.
append
(
seq_index
.
append
(
[
np
.
where
(
node
==
i
)[
0
][
0
]
+
id
*
max_uniq_len
for
i
in
e
[
0
]])
[
[
id
,
np
.
where
(
node
==
i
)[
0
][
0
]]
for
i
in
e
[
0
]])
last_index
.
append
(
last_index
.
append
(
np
.
where
(
node
==
e
[
0
][
last_id
[
id
]])[
0
][
0
]
+
id
*
max_uniq_len
)
[
id
,
np
.
where
(
node
==
e
[
0
][
last_id
[
id
]])[
0
][
0
]]
)
label
.
append
(
e
[
1
]
-
1
)
label
.
append
(
e
[
1
]
-
1
)
mask
.
append
([[
1
]
*
(
last_id
[
id
]
+
1
)
+
[
0
]
*
mask
.
append
([[
1
]
*
(
last_id
[
id
]
+
1
)
+
[
0
]
*
(
max_seq_len
-
last_id
[
id
]
-
1
)])
(
max_seq_len
-
last_id
[
id
]
-
1
)])
id
+=
1
id
+=
1
items
=
np
.
array
(
items
).
astype
(
"int64"
).
reshape
((
batch_size
,
-
1
,
1
))
items
=
np
.
array
(
items
).
astype
(
"int64"
).
reshape
((
batch_size
,
-
1
))
seq_index
=
np
.
array
(
seq_index
).
astype
(
"int32"
).
reshape
(
seq_index
=
np
.
array
(
seq_index
).
astype
(
"int32"
).
reshape
(
(
batch_size
,
-
1
))
(
batch_size
,
-
1
,
2
))
last_index
=
np
.
array
(
last_index
).
astype
(
"int32"
).
reshape
(
last_index
=
np
.
array
(
last_index
).
astype
(
"int32"
).
reshape
(
(
batch_size
))
(
batch_size
,
2
))
adj_in
=
np
.
array
(
adj_in
).
astype
(
"float32"
).
reshape
(
adj_in
=
np
.
array
(
adj_in
).
astype
(
"float32"
).
reshape
(
(
batch_size
,
max_uniq_len
,
max_uniq_len
))
(
batch_size
,
max_uniq_len
,
max_uniq_len
))
adj_out
=
np
.
array
(
adj_out
).
astype
(
"float32"
).
reshape
(
adj_out
=
np
.
array
(
adj_out
).
astype
(
"float32"
).
reshape
(
...
@@ -110,8 +110,10 @@ class Data():
...
@@ -110,8 +110,10 @@ class Data():
cur_batch
=
remain_data
[
i
:
i
+
batch_size
]
cur_batch
=
remain_data
[
i
:
i
+
batch_size
]
yield
self
.
make_data
(
cur_batch
,
batch_size
)
yield
self
.
make_data
(
cur_batch
,
batch_size
)
else
:
else
:
cur_batch
=
remain_data
[
i
:]
# Due to fixed batch_size, discard the remaining ins
yield
self
.
make_data
(
cur_batch
,
group_remain
%
batch_size
)
return
#cur_batch = remain_data[i:]
#yield self.make_data(cur_batch, group_remain % batch_size)
return
_reader
return
_reader
...
...
PaddleRec/gnn/train.py
浏览文件 @
5312aaa1
...
@@ -72,7 +72,7 @@ def train():
...
@@ -72,7 +72,7 @@ def train():
batch_size
=
args
.
batch_size
batch_size
=
args
.
batch_size
items_num
=
reader
.
read_config
(
args
.
config_path
)
items_num
=
reader
.
read_config
(
args
.
config_path
)
loss
,
acc
,
py_reader
,
feed_datas
=
network
.
network
(
items_num
,
args
.
hidden_size
,
loss
,
acc
,
py_reader
,
feed_datas
=
network
.
network
(
items_num
,
args
.
hidden_size
,
args
.
step
)
args
.
step
,
batch_size
)
data_reader
=
reader
.
Data
(
args
.
train_path
,
True
)
data_reader
=
reader
.
Data
(
args
.
train_path
,
True
)
logger
.
info
(
"load data complete"
)
logger
.
info
(
"load data complete"
)
...
@@ -96,7 +96,7 @@ def train():
...
@@ -96,7 +96,7 @@ def train():
all_vocab
=
fluid
.
global_scope
().
var
(
"all_vocab"
).
get_tensor
()
all_vocab
=
fluid
.
global_scope
().
var
(
"all_vocab"
).
get_tensor
()
all_vocab
.
set
(
all_vocab
.
set
(
np
.
arange
(
1
,
items_num
).
astype
(
"int64"
).
reshape
((
-
1
,
1
)),
place
)
np
.
arange
(
1
,
items_num
).
astype
(
"int64"
).
reshape
((
-
1
)),
place
)
feed_list
=
[
e
.
name
for
e
in
feed_datas
]
feed_list
=
[
e
.
name
for
e
in
feed_datas
]
...
@@ -115,7 +115,8 @@ def train():
...
@@ -115,7 +115,8 @@ def train():
acc_sum
=
0.0
acc_sum
=
0.0
global_step
=
0
global_step
=
0
PRINT_STEP
=
500
PRINT_STEP
=
500
py_reader
.
decorate_paddle_reader
(
data_reader
.
reader
(
batch_size
,
batch_size
*
20
,
True
))
#py_reader.decorate_paddle_reader(data_reader.reader(batch_size, batch_size * 20, True))
py_reader
.
set_sample_list_generator
(
data_reader
.
reader
(
batch_size
,
batch_size
*
20
,
True
))
for
i
in
range
(
args
.
epoch_num
):
for
i
in
range
(
args
.
epoch_num
):
epoch_sum
=
[]
epoch_sum
=
[]
py_reader
.
start
()
py_reader
.
start
()
...
...
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