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
20ee36bd
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
20ee36bd
编写于
7月 13, 2020
作者:
K
Kaipeng Deng
提交者:
GitHub
7月 13, 2020
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
make default_collate_fn visible. test=develop (#25244)
* make default_collate_fn visible. test=develop
上级
ee44bcdd
变更
2
隐藏空白更改
内联
并排
Showing
2 changed file
with
24 addition
and
4 deletion
+24
-4
python/paddle/fluid/dataloader/dataloader_iter.py
python/paddle/fluid/dataloader/dataloader_iter.py
+22
-2
python/paddle/fluid/reader.py
python/paddle/fluid/reader.py
+2
-2
未找到文件。
python/paddle/fluid/dataloader/dataloader_iter.py
浏览文件 @
20ee36bd
...
...
@@ -38,7 +38,27 @@ from ..multiprocess_utils import CleanupFuncRegistrar, _cleanup_mmap, _set_SIGCH
MP_INDICES_CHECK_INTERVAL
=
5
def
_default_collate_fn
(
batch
):
def
default_collate_fn
(
batch
):
"""
Default batch collating function for :code:`fluid.io.DataLoader`,
batch should be a list of samples, and each sample should be a list
of fields as follows:
[[filed1, filed2, ...], [filed1, filed2, ...], ...]
This default collate function zipped each filed together and stack
each filed as the batch field as follows:
[batch_filed1, batch_filed2, ...]
Args:
batch(list of list of numpy array): the batch data, each fields
should be a numpy array, each sample should be a list of
fileds, and batch should be a list of sample.
Returns:
a list of numpy array: collated batch
"""
sample
=
batch
[
0
]
# dataset has only 1 field
if
isinstance
(
sample
,
np
.
ndarray
):
...
...
@@ -82,7 +102,7 @@ class _DataLoaderIterBase(object):
self
.
_return_list
=
loader
.
return_list
self
.
_batch_sampler
=
loader
.
batch_sampler
self
.
_sampler_iter
=
iter
(
loader
.
batch_sampler
)
self
.
_collate_fn
=
loader
.
collate_fn
or
_
default_collate_fn
self
.
_collate_fn
=
loader
.
collate_fn
or
default_collate_fn
self
.
_num_workers
=
loader
.
num_workers
self
.
_use_buffer_reader
=
loader
.
use_buffer_reader
self
.
_use_shared_memory
=
loader
.
use_shared_memory
...
...
python/paddle/fluid/reader.py
浏览文件 @
20ee36bd
...
...
@@ -23,7 +23,7 @@ from .executor import global_scope
from
.data_feeder
import
DataFeeder
,
BatchedTensorProvider
from
.multiprocess_utils
import
multiprocess_queue_set
,
CleanupFuncRegistrar
,
_cleanup_mmap
,
_cleanup
,
_set_SIGCHLD_handler
from
.dataloader
import
BatchSampler
,
Dataset
from
.dataloader.dataloader_iter
import
_DataLoaderIterSingleProcess
,
_DataLoaderIterMultiProcess
from
.dataloader.dataloader_iter
import
_DataLoaderIterSingleProcess
,
_DataLoaderIterMultiProcess
,
default_collate_fn
from
.layers.io
import
monkey_patch_reader_methods
,
_copy_reader_var_
,
double_buffer
from
.unique_name
import
UniqueNameGenerator
import
logging
...
...
@@ -44,7 +44,7 @@ else:
# NOTE: [ avoid hanging & failed quickly ] These value is used in getting data from another process
QUEUE_GET_TIMEOUT
=
60
__all__
=
[
'PyReader'
,
'DataLoader'
]
__all__
=
[
'PyReader'
,
'DataLoader'
,
'default_collate_fn'
]
data_loader_unique_name_generator
=
UniqueNameGenerator
()
...
...
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