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
Paddle
提交
d55cfc60
P
Paddle
项目概览
PaddlePaddle
/
Paddle
12 个月 前同步成功
通知
2292
Star
20931
Fork
5422
代码
文件
提交
分支
Tags
贡献者
分支图
Diff
Issue
1423
列表
看板
标记
里程碑
合并请求
543
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
1,423
Issue
1,423
列表
看板
标记
里程碑
合并请求
543
合并请求
543
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
d55cfc60
编写于
6月 22, 2018
作者:
T
Tao Luo
提交者:
GitHub
6月 22, 2018
浏览文件
操作
浏览文件
下载
差异文件
Merge pull request #11640 from wojtuss/wojtuss/cycle-cifar-flowers
added cycling the cifar and flowers datasets
上级
dda24f18
50e750a2
变更
2
隐藏空白更改
内联
并排
Showing
2 changed file
with
52 addition
and
25 deletion
+52
-25
python/paddle/v2/dataset/cifar.py
python/paddle/v2/dataset/cifar.py
+18
-9
python/paddle/v2/dataset/flowers.py
python/paddle/v2/dataset/flowers.py
+34
-16
未找到文件。
python/paddle/v2/dataset/cifar.py
浏览文件 @
d55cfc60
...
...
@@ -43,7 +43,7 @@ CIFAR100_URL = URL_PREFIX + 'cifar-100-python.tar.gz'
CIFAR100_MD5
=
'eb9058c3a382ffc7106e4002c42a8d85'
def
reader_creator
(
filename
,
sub_name
):
def
reader_creator
(
filename
,
sub_name
,
cycle
=
False
):
def
read_batch
(
batch
):
data
=
batch
[
'data'
]
labels
=
batch
.
get
(
'labels'
,
batch
.
get
(
'fine_labels'
,
None
))
...
...
@@ -56,10 +56,13 @@ def reader_creator(filename, sub_name):
names
=
(
each_item
.
name
for
each_item
in
f
if
sub_name
in
each_item
.
name
)
for
name
in
names
:
batch
=
cPickle
.
load
(
f
.
extractfile
(
name
))
for
item
in
read_batch
(
batch
):
yield
item
while
True
:
for
name
in
names
:
batch
=
cPickle
.
load
(
f
.
extractfile
(
name
))
for
item
in
read_batch
(
batch
):
yield
item
if
not
cycle
:
break
return
reader
...
...
@@ -94,34 +97,40 @@ def test100():
'test'
)
def
train10
():
def
train10
(
cycle
=
False
):
"""
CIFAR-10 training set creator.
It returns a reader creator, each sample in the reader is image pixels in
[0, 1] and label in [0, 9].
:param cycle: whether to cycle through the dataset
:type cycle: bool
:return: Training reader creator
:rtype: callable
"""
return
reader_creator
(
paddle
.
v2
.
dataset
.
common
.
download
(
CIFAR10_URL
,
'cifar'
,
CIFAR10_MD5
),
'data_batch'
)
'data_batch'
,
cycle
=
cycle
)
def
test10
():
def
test10
(
cycle
=
False
):
"""
CIFAR-10 test set creator.
It returns a reader creator, each sample in the reader is image pixels in
[0, 1] and label in [0, 9].
:param cycle: whether to cycle through the dataset
:type cycle: bool
:return: Test reader creator.
:rtype: callable
"""
return
reader_creator
(
paddle
.
v2
.
dataset
.
common
.
download
(
CIFAR10_URL
,
'cifar'
,
CIFAR10_MD5
),
'test_batch'
)
'test_batch'
,
cycle
=
cycle
)
def
fetch
():
...
...
python/paddle/v2/dataset/flowers.py
浏览文件 @
d55cfc60
...
...
@@ -76,7 +76,8 @@ def reader_creator(data_file,
dataset_name
,
mapper
,
buffered_size
=
1024
,
use_xmap
=
True
):
use_xmap
=
True
,
cycle
=
False
):
'''
1. read images from tar file and
merge images into batch files in 102flowers.tgz_batch/
...
...
@@ -96,6 +97,8 @@ def reader_creator(data_file,
:type mapper: callable
:param buffered_size: the size of buffer used to process images
:type buffered_size: int
:param cycle: whether to cycle through the dataset
:type cycle: bool
:return: data reader
:rtype: callable
'''
...
...
@@ -108,15 +111,18 @@ def reader_creator(data_file,
file_list
=
batch_images_from_tar
(
data_file
,
dataset_name
,
img2label
)
def
reader
():
for
file
in
open
(
file_list
):
file
=
file
.
strip
()
batch
=
None
with
open
(
file
,
'r'
)
as
f
:
batch
=
cPickle
.
load
(
f
)
data
=
batch
[
'data'
]
labels
=
batch
[
'label'
]
for
sample
,
label
in
itertools
.
izip
(
data
,
batch
[
'label'
]):
yield
sample
,
int
(
label
)
-
1
while
True
:
for
file
in
open
(
file_list
):
file
=
file
.
strip
()
batch
=
None
with
open
(
file
,
'r'
)
as
f
:
batch
=
cPickle
.
load
(
f
)
data
=
batch
[
'data'
]
labels
=
batch
[
'label'
]
for
sample
,
label
in
itertools
.
izip
(
data
,
batch
[
'label'
]):
yield
sample
,
int
(
label
)
-
1
if
not
cycle
:
break
if
use_xmap
:
cpu_num
=
int
(
os
.
environ
.
get
(
'CPU_NUM'
,
cpu_count
()))
...
...
@@ -125,7 +131,7 @@ def reader_creator(data_file,
return
map_readers
(
mapper
,
reader
)
def
train
(
mapper
=
train_mapper
,
buffered_size
=
1024
,
use_xmap
=
True
):
def
train
(
mapper
=
train_mapper
,
buffered_size
=
1024
,
use_xmap
=
True
,
cycle
=
False
):
'''
Create flowers training set reader.
It returns a reader, each sample in the reader is
...
...
@@ -138,17 +144,23 @@ def train(mapper=train_mapper, buffered_size=1024, use_xmap=True):
:type mapper: callable
:param buffered_size: the size of buffer used to process images
:type buffered_size: int
:param cycle: whether to cycle through the dataset
:type cycle: bool
:return: train data reader
:rtype: callable
'''
return
reader_creator
(
download
(
DATA_URL
,
'flowers'
,
DATA_MD5
),
download
(
LABEL_URL
,
'flowers'
,
LABEL_MD5
),
download
(
SETID_URL
,
'flowers'
,
SETID_MD5
),
TRAIN_FLAG
,
mapper
,
buffered_size
,
use_xmap
)
download
(
SETID_URL
,
'flowers'
,
SETID_MD5
),
TRAIN_FLAG
,
mapper
,
buffered_size
,
use_xmap
,
cycle
=
cycle
)
def
test
(
mapper
=
test_mapper
,
buffered_size
=
1024
,
use_xmap
=
True
):
def
test
(
mapper
=
test_mapper
,
buffered_size
=
1024
,
use_xmap
=
True
,
cycle
=
False
):
'''
Create flowers test set reader.
It returns a reader, each sample in the reader is
...
...
@@ -161,14 +173,20 @@ def test(mapper=test_mapper, buffered_size=1024, use_xmap=True):
:type mapper: callable
:param buffered_size: the size of buffer used to process images
:type buffered_size: int
:param cycle: whether to cycle through the dataset
:type cycle: bool
:return: test data reader
:rtype: callable
'''
return
reader_creator
(
download
(
DATA_URL
,
'flowers'
,
DATA_MD5
),
download
(
LABEL_URL
,
'flowers'
,
LABEL_MD5
),
download
(
SETID_URL
,
'flowers'
,
SETID_MD5
),
TEST_FLAG
,
mapper
,
buffered_size
,
use_xmap
)
download
(
SETID_URL
,
'flowers'
,
SETID_MD5
),
TEST_FLAG
,
mapper
,
buffered_size
,
use_xmap
,
cycle
=
cycle
)
def
valid
(
mapper
=
test_mapper
,
buffered_size
=
1024
,
use_xmap
=
True
):
...
...
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