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
s920243400
PaddleDetection
提交
1a30667d
P
PaddleDetection
项目概览
s920243400
/
PaddleDetection
与 Fork 源项目一致
Fork自
PaddlePaddle / PaddleDetection
通知
2
Star
0
Fork
0
代码
文件
提交
分支
Tags
贡献者
分支图
Diff
Issue
0
列表
看板
标记
里程碑
合并请求
0
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
0
Issue
0
列表
看板
标记
里程碑
合并请求
0
合并请求
0
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
1a30667d
编写于
2月 13, 2020
作者:
Y
Yang Zhang
提交者:
GitHub
2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
Clean up pyreader vestiges (#228)
上级
2835d5ad
变更
7
隐藏空白更改
内联
并排
Showing
7 changed file
with
7 addition
and
7 deletion
+7
-7
demo/mask_rcnn_demo.ipynb
demo/mask_rcnn_demo.ipynb
+1
-1
ppdet/modeling/architectures/cascade_mask_rcnn.py
ppdet/modeling/architectures/cascade_mask_rcnn.py
+1
-1
ppdet/modeling/architectures/cascade_rcnn.py
ppdet/modeling/architectures/cascade_rcnn.py
+1
-1
ppdet/modeling/architectures/cascade_rcnn_cls_aware.py
ppdet/modeling/architectures/cascade_rcnn_cls_aware.py
+1
-1
ppdet/modeling/architectures/faster_rcnn.py
ppdet/modeling/architectures/faster_rcnn.py
+1
-1
ppdet/modeling/architectures/mask_rcnn.py
ppdet/modeling/architectures/mask_rcnn.py
+1
-1
ppdet/modeling/architectures/retinanet.py
ppdet/modeling/architectures/retinanet.py
+1
-1
未找到文件。
demo/mask_rcnn_demo.ipynb
浏览文件 @
1a30667d
...
...
@@ -216,7 +216,7 @@
"with fluid.program_guard(infer_prog, startup_prog):\n",
" with fluid.unique_name.guard():\n",
" feed_vars = {\n",
" var['name']: fluid.
layers.
data(\n",
" var['name']: fluid.data(\n",
" name=var['name'],\n",
" shape=var['shape'],\n",
" dtype='float32',\n",
ppdet/modeling/architectures/cascade_mask_rcnn.py
浏览文件 @
1a30667d
...
...
@@ -411,7 +411,7 @@ class CascadeMaskRCNN(object):
'lod_level'
:
1
}
fields
+=
box_fields
feed_vars
=
OrderedDict
([(
key
,
fluid
.
layers
.
data
(
feed_vars
=
OrderedDict
([(
key
,
fluid
.
data
(
name
=
key
,
shape
=
inputs_def
[
key
][
'shape'
],
dtype
=
inputs_def
[
key
][
'dtype'
],
...
...
ppdet/modeling/architectures/cascade_rcnn.py
浏览文件 @
1a30667d
...
...
@@ -312,7 +312,7 @@ class CascadeRCNN(object):
fields
+=
ms_fields
self
.
im_info_names
=
[
'image'
,
'im_info'
]
+
ms_fields
feed_vars
=
OrderedDict
([(
key
,
fluid
.
layers
.
data
(
feed_vars
=
OrderedDict
([(
key
,
fluid
.
data
(
name
=
key
,
shape
=
inputs_def
[
key
][
'shape'
],
dtype
=
inputs_def
[
key
][
'dtype'
],
...
...
ppdet/modeling/architectures/cascade_rcnn_cls_aware.py
浏览文件 @
1a30667d
...
...
@@ -195,7 +195,7 @@ class CascadeRCNNClsAware(object):
use_dataloader
=
True
,
iterable
=
False
):
inputs_def
=
self
.
_inputs_def
(
image_shape
)
feed_vars
=
OrderedDict
([(
key
,
fluid
.
layers
.
data
(
feed_vars
=
OrderedDict
([(
key
,
fluid
.
data
(
name
=
key
,
shape
=
inputs_def
[
key
][
'shape'
],
dtype
=
inputs_def
[
key
][
'dtype'
],
...
...
ppdet/modeling/architectures/faster_rcnn.py
浏览文件 @
1a30667d
...
...
@@ -224,7 +224,7 @@ class FasterRCNN(object):
fields
+=
ms_fields
self
.
im_info_names
=
[
'image'
,
'im_info'
]
+
ms_fields
feed_vars
=
OrderedDict
([(
key
,
fluid
.
layers
.
data
(
feed_vars
=
OrderedDict
([(
key
,
fluid
.
data
(
name
=
key
,
shape
=
inputs_def
[
key
][
'shape'
],
dtype
=
inputs_def
[
key
][
'dtype'
],
...
...
ppdet/modeling/architectures/mask_rcnn.py
浏览文件 @
1a30667d
...
...
@@ -314,7 +314,7 @@ class MaskRCNN(object):
'lod_level'
:
1
}
fields
+=
box_fields
feed_vars
=
OrderedDict
([(
key
,
fluid
.
layers
.
data
(
feed_vars
=
OrderedDict
([(
key
,
fluid
.
data
(
name
=
key
,
shape
=
inputs_def
[
key
][
'shape'
],
dtype
=
inputs_def
[
key
][
'dtype'
],
...
...
ppdet/modeling/architectures/retinanet.py
浏览文件 @
1a30667d
...
...
@@ -107,7 +107,7 @@ class RetinaNet(object):
use_dataloader
=
True
,
iterable
=
False
):
inputs_def
=
self
.
_inputs_def
(
image_shape
)
feed_vars
=
OrderedDict
([(
key
,
fluid
.
layers
.
data
(
feed_vars
=
OrderedDict
([(
key
,
fluid
.
data
(
name
=
key
,
shape
=
inputs_def
[
key
][
'shape'
],
dtype
=
inputs_def
[
key
][
'dtype'
],
...
...
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