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
80283e6d
M
models
项目概览
PaddlePaddle
/
models
12 个月 前同步成功
通知
222
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
体验新版 GitCode,发现更多精彩内容 >>
未验证
提交
80283e6d
编写于
8月 06, 2019
作者:
Q
qingqing01
提交者:
GitHub
8月 06, 2019
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
Change data shape in data_feed.py (#3026)
上级
f1f5353a
变更
1
隐藏空白更改
内联
并排
Showing
1 changed file
with
14 addition
and
13 deletion
+14
-13
PaddleCV/PaddleDetection/ppdet/data/data_feed.py
PaddleCV/PaddleDetection/ppdet/data/data_feed.py
+14
-13
未找到文件。
PaddleCV/PaddleDetection/ppdet/data/data_feed.py
浏览文件 @
80283e6d
...
...
@@ -28,10 +28,9 @@ from ppdet.data.transform.operators import (
DecodeImage
,
MixupImage
,
NormalizeBox
,
NormalizeImage
,
RandomDistort
,
RandomFlipImage
,
RandomInterpImage
,
ResizeImage
,
ExpandImage
,
CropImage
,
Permute
)
from
ppdet.data.transform.arrange_sample
import
(
ArrangeRCNN
,
ArrangeTestRCNN
,
ArrangeSSD
,
ArrangeTestSSD
,
ArrangeYOLO
,
ArrangeEvalYOLO
,
ArrangeTestYOLO
)
from
ppdet.data.transform.arrange_sample
import
(
ArrangeRCNN
,
ArrangeTestRCNN
,
ArrangeSSD
,
ArrangeTestSSD
,
ArrangeYOLO
,
ArrangeEvalYOLO
,
ArrangeTestYOLO
)
__all__
=
[
'PadBatch'
,
'MultiScale'
,
'RandomShape'
,
'DataSet'
,
'CocoDataSet'
,
...
...
@@ -138,8 +137,8 @@ def create_reader(feed, max_iter=0, args_path=None, my_source=None):
ops
.
append
(
op_dict
)
transform_config
[
'OPS'
]
=
ops
return
Reader
.
create
(
feed
.
mode
,
data_config
,
transform_config
,
max_iter
,
my_source
)
return
Reader
.
create
(
feed
.
mode
,
data_config
,
transform_config
,
max_iter
,
my_source
)
# XXX batch transforms are only stubs for now, actually handled by `post_map`
...
...
@@ -412,6 +411,7 @@ class TestFeed(DataFeed):
num_workers
=
num_workers
)
# yapf: disable
@
register
class
FasterRCNNTrainFeed
(
DataFeed
):
__doc__
=
DataFeed
.
__doc__
...
...
@@ -422,7 +422,7 @@ class FasterRCNNTrainFeed(DataFeed):
'image'
,
'im_info'
,
'im_id'
,
'gt_box'
,
'gt_label'
,
'is_crowd'
],
image_shape
=
[
3
,
1333
,
800
],
image_shape
=
[
3
,
800
,
1333
],
sample_transforms
=
[
DecodeImage
(
to_rgb
=
True
),
RandomFlipImage
(
prob
=
0.5
),
...
...
@@ -467,7 +467,7 @@ class FasterRCNNEvalFeed(DataFeed):
dataset
=
CocoDataSet
(
COCO_VAL_ANNOTATION
,
COCO_VAL_IMAGE_DIR
).
__dict__
,
fields
=
[
'image'
,
'im_info'
,
'im_id'
,
'im_shape'
],
image_shape
=
[
3
,
1333
,
800
],
image_shape
=
[
3
,
800
,
1333
],
sample_transforms
=
[
DecodeImage
(
to_rgb
=
True
),
NormalizeImage
(
mean
=
[
0.485
,
0.456
,
0.406
],
...
...
@@ -508,7 +508,7 @@ class FasterRCNNTestFeed(DataFeed):
dataset
=
SimpleDataSet
(
COCO_VAL_ANNOTATION
,
COCO_VAL_IMAGE_DIR
).
__dict__
,
fields
=
[
'image'
,
'im_info'
,
'im_id'
,
'im_shape'
],
image_shape
=
[
3
,
1333
,
800
],
image_shape
=
[
3
,
800
,
1333
],
sample_transforms
=
[
DecodeImage
(
to_rgb
=
True
),
NormalizeImage
(
mean
=
[
0.485
,
0.456
,
0.406
],
...
...
@@ -555,7 +555,7 @@ class MaskRCNNTrainFeed(DataFeed):
'image'
,
'im_info'
,
'im_id'
,
'gt_box'
,
'gt_label'
,
'is_crowd'
,
'gt_mask'
],
image_shape
=
[
3
,
1333
,
800
],
image_shape
=
[
3
,
800
,
1333
],
sample_transforms
=
[
DecodeImage
(
to_rgb
=
True
),
RandomFlipImage
(
prob
=
0.5
,
is_mask_flip
=
True
),
...
...
@@ -601,7 +601,7 @@ class MaskRCNNEvalFeed(DataFeed):
dataset
=
CocoDataSet
(
COCO_VAL_ANNOTATION
,
COCO_VAL_IMAGE_DIR
).
__dict__
,
fields
=
[
'image'
,
'im_info'
,
'im_id'
,
'im_shape'
],
image_shape
=
[
3
,
1333
,
800
],
image_shape
=
[
3
,
800
,
1333
],
sample_transforms
=
[
DecodeImage
(
to_rgb
=
True
),
NormalizeImage
(
mean
=
[
0.485
,
0.456
,
0.406
],
...
...
@@ -647,7 +647,7 @@ class MaskRCNNTestFeed(DataFeed):
dataset
=
SimpleDataSet
(
COCO_VAL_ANNOTATION
,
COCO_VAL_IMAGE_DIR
).
__dict__
,
fields
=
[
'image'
,
'im_info'
,
'im_id'
,
'im_shape'
],
image_shape
=
[
3
,
1333
,
800
],
image_shape
=
[
3
,
800
,
1333
],
sample_transforms
=
[
DecodeImage
(
to_rgb
=
True
),
NormalizeImage
(
...
...
@@ -900,7 +900,7 @@ class YoloEvalFeed(DataFeed):
def
__init__
(
self
,
dataset
=
CocoDataSet
(
COCO_VAL_ANNOTATION
,
COCO_VAL_IMAGE_DIR
).
__dict__
,
fields
=
[
'image'
,
'im_size'
,
'im_id'
,
'gt_box'
,
fields
=
[
'image'
,
'im_size'
,
'im_id'
,
'gt_box'
,
'gt_label'
,
'is_difficult'
],
image_shape
=
[
3
,
608
,
608
],
sample_transforms
=
[
...
...
@@ -985,3 +985,4 @@ class YoloTestFeed(DataFeed):
use_process
=
use_process
)
self
.
mode
=
'TEST'
self
.
bufsize
=
128
# yapf: enable
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