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
PaddleDetection
提交
b7a809a1
P
PaddleDetection
项目概览
PaddlePaddle
/
PaddleDetection
大约 1 年 前同步成功
通知
695
Star
11112
Fork
2696
代码
文件
提交
分支
Tags
贡献者
分支图
Diff
Issue
184
列表
看板
标记
里程碑
合并请求
40
Wiki
0
Wiki
分析
仓库
DevOps
项目成员
Pages
P
PaddleDetection
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
184
Issue
184
列表
看板
标记
里程碑
合并请求
40
合并请求
40
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
提交
b7a809a1
编写于
3月 22, 2017
作者:
Y
Yancey1989
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
add download api for dataset
上级
c1feccdc
变更
9
隐藏空白更改
内联
并排
Showing
9 changed file
with
46 addition
and
4 deletion
+46
-4
python/paddle/v2/dataset/cifar.py
python/paddle/v2/dataset/cifar.py
+5
-0
python/paddle/v2/dataset/conll05.py
python/paddle/v2/dataset/conll05.py
+8
-0
python/paddle/v2/dataset/imdb.py
python/paddle/v2/dataset/imdb.py
+4
-0
python/paddle/v2/dataset/imikolov.py
python/paddle/v2/dataset/imikolov.py
+4
-0
python/paddle/v2/dataset/mnist.py
python/paddle/v2/dataset/mnist.py
+5
-0
python/paddle/v2/dataset/movielens.py
python/paddle/v2/dataset/movielens.py
+8
-4
python/paddle/v2/dataset/sentiment.py
python/paddle/v2/dataset/sentiment.py
+4
-0
python/paddle/v2/dataset/uci_housing.py
python/paddle/v2/dataset/uci_housing.py
+4
-0
python/paddle/v2/dataset/wmt14.py
python/paddle/v2/dataset/wmt14.py
+4
-0
未找到文件。
python/paddle/v2/dataset/cifar.py
浏览文件 @
b7a809a1
...
...
@@ -75,3 +75,8 @@ def test10():
return
reader_creator
(
paddle
.
v2
.
dataset
.
common
.
download
(
CIFAR10_URL
,
'cifar'
,
CIFAR10_MD5
),
'test_batch'
)
def
download
():
paddle
.
v2
.
dataset
.
common
.
download
(
CIFAR10_URL
,
'cifar'
,
CIFAR10_MD5
)
paddle
.
v2
.
dataset
.
common
.
download
(
CIFAR100_URL
,
'cifar'
,
CIFAR100_MD5
)
python/paddle/v2/dataset/conll05.py
浏览文件 @
b7a809a1
...
...
@@ -196,3 +196,11 @@ def test():
words_name
=
'conll05st-release/test.wsj/words/test.wsj.words.gz'
,
props_name
=
'conll05st-release/test.wsj/props/test.wsj.props.gz'
)
return
reader_creator
(
reader
,
word_dict
,
verb_dict
,
label_dict
)
def
download
():
paddle
.
v2
.
dataset
.
common
.
download
(
WORDDICT_URL
,
'conll05st'
,
WORDDICT_MD5
)
paddle
.
v2
.
dataset
.
common
.
download
(
VERBDICT_URL
,
'conll05st'
,
VERBDICT_MD5
)
paddle
.
v2
.
dataset
.
common
.
download
(
TRGDICT_URL
,
'conll05st'
,
TRGDICT_MD5
)
paddle
.
v2
.
dataset
.
common
.
download
(
EMB_URL
,
'conll05st'
,
EMB_MD5
)
paddle
.
v2
.
dataset
.
common
.
download
(
DATA_URL
,
'conll05st'
,
DATA_MD5
)
python/paddle/v2/dataset/imdb.py
浏览文件 @
b7a809a1
...
...
@@ -123,3 +123,7 @@ def test(word_idx):
def
word_dict
():
return
build_dict
(
re
.
compile
(
"aclImdb/((train)|(test))/((pos)|(neg))/.*\.txt$"
),
150
)
def
download
():
paddle
.
v2
.
dataset
.
common
.
download
(
URL
,
'imdb'
,
MD5
)
python/paddle/v2/dataset/imikolov.py
浏览文件 @
b7a809a1
...
...
@@ -89,3 +89,7 @@ def train(word_idx, n):
def
test
(
word_idx
,
n
):
return
reader_creator
(
'./simple-examples/data/ptb.valid.txt'
,
word_idx
,
n
)
def
download
():
paddle
.
v2
.
dataset
.
common
.
download
(
URL
,
"imikolov"
,
MD5
)
python/paddle/v2/dataset/mnist.py
浏览文件 @
b7a809a1
...
...
@@ -106,3 +106,8 @@ def test():
TEST_IMAGE_MD5
),
paddle
.
v2
.
dataset
.
common
.
download
(
TEST_LABEL_URL
,
'mnist'
,
TEST_LABEL_MD5
),
100
)
def
download
():
paddle
.
v2
.
dataset
.
common
.
download
(
TRAIN_IMAGE_URL
,
'mnist'
,
TRAIN_IMAGE_MD5
)
paddle
.
v2
.
dataset
.
common
.
download
(
TRAIN_LABEL_URL
,
'mnist'
,
TRAIN_LABEL_MD5
)
python/paddle/v2/dataset/movielens.py
浏览文件 @
b7a809a1
...
...
@@ -30,6 +30,9 @@ __all__ = [
age_table
=
[
1
,
18
,
25
,
35
,
45
,
50
,
56
]
URL
=
'http://files.grouplens.org/datasets/movielens/ml-1m.zip'
MD5
=
'c4d9eecfca2ab87c1945afe126590906'
class
MovieInfo
(
object
):
def
__init__
(
self
,
index
,
categories
,
title
):
...
...
@@ -77,10 +80,7 @@ USER_INFO = None
def
__initialize_meta_info__
():
fn
=
download
(
url
=
'http://files.grouplens.org/datasets/movielens/ml-1m.zip'
,
module_name
=
'movielens'
,
md5sum
=
'c4d9eecfca2ab87c1945afe126590906'
)
fn
=
download
(
URL
,
"movielens"
,
MD5
)
global
MOVIE_INFO
if
MOVIE_INFO
is
None
:
pattern
=
re
.
compile
(
r
'^(.*)\((\d+)\)$'
)
...
...
@@ -205,5 +205,9 @@ def unittest():
print
train_count
,
test_count
def
download
():
paddle
.
v2
.
dataset
.
common
.
download
(
URL
,
"movielens"
,
MD5
)
if
__name__
==
'__main__'
:
unittest
()
python/paddle/v2/dataset/sentiment.py
浏览文件 @
b7a809a1
...
...
@@ -125,3 +125,7 @@ def test():
"""
data_set
=
load_sentiment_data
()
return
reader_creator
(
data_set
[
NUM_TRAINING_INSTANCES
:])
def
download
():
nltk
.
download
(
'movie_reviews'
,
download_dir
=
common
.
DATA_HOME
)
python/paddle/v2/dataset/uci_housing.py
浏览文件 @
b7a809a1
...
...
@@ -89,3 +89,7 @@ def test():
yield
d
[:
-
1
],
d
[
-
1
:]
return
reader
def
download
():
paddle
.
v2
.
dataset
.
common
.
download
(
URL
,
'uci_housing'
,
MD5
)
python/paddle/v2/dataset/wmt14.py
浏览文件 @
b7a809a1
...
...
@@ -103,3 +103,7 @@ def test(dict_size):
return
reader_creator
(
paddle
.
v2
.
dataset
.
common
.
download
(
URL_TRAIN
,
'wmt14'
,
MD5_TRAIN
),
'test/test'
,
dict_size
)
def
download
():
paddle
.
v2
.
dataset
.
common
.
download
(
URL_TRAIN
,
'wmt14'
,
MD5_TRAIN
)
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