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
fd8ed6c4
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
fd8ed6c4
编写于
10月 26, 2020
作者:
W
wangxinxin08
提交者:
GitHub
10月 26, 2020
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
fix argument mismatch when using roi_ops (#1601)
上级
ab3fb4ae
变更
2
隐藏空白更改
内联
并排
Showing
2 changed file
with
5 addition
and
4 deletion
+5
-4
ppdet/modeling/layers.py
ppdet/modeling/layers.py
+0
-2
ppdet/modeling/ops.py
ppdet/modeling/ops.py
+5
-2
未找到文件。
ppdet/modeling/layers.py
浏览文件 @
fd8ed6c4
...
...
@@ -302,7 +302,6 @@ class RoIExtractor(object):
feats
[
self
.
start_level
],
roi
,
self
.
resolution
,
self
.
resolution
,
spatial_scale
,
rois_num
=
rois_num
)
return
rois_feat
...
...
@@ -323,7 +322,6 @@ class RoIExtractor(object):
feats
[
lvl
],
rois_dist
[
lvl
],
self
.
resolution
,
self
.
resolution
,
spatial_scale
[
lvl
],
sampling_ratio
=
self
.
sampling_ratio
,
rois_num
=
rois_num_dist
[
lvl
])
...
...
ppdet/modeling/ops.py
浏览文件 @
fd8ed6c4
...
...
@@ -168,8 +168,10 @@ def roi_align(input,
The data type is float32 or float64. Given as [[x1, y1, x2, y2], ...],
(x1, y1) is the top left coordinates, and (x2, y2) is the bottom right coordinates.
output_size (int or tuple[int, int]): The pooled output size(h, w), data type is int32. If int, h and w are both equal to output_size.
spatial_scale (float32, optional): ${spatial_scale_comment} Default: 1.0
sampling_ratio(int32, optional): ${sampling_ratio_comment} Default: -1
spatial_scale (float32, optional): Multiplicative spatial scale factor to translate ROI coords
from their input scale to the scale used when pooling. Default: 1.0
sampling_ratio(int32, optional): number of sampling points in the interpolation grid.
If <=0, then grid points are adaptive to roi_width and pooled_w, likewise for height. Default: -1
rois_num (Tensor): The number of RoIs in each image. Default: None
name(str, optional): For detailed information, please refer
to :ref:`api_guide_Name`. Usually name is no need to set and
...
...
@@ -199,6 +201,7 @@ def roi_align(input,
sampling_ratio=-1,
rois_num=rois_num)
"""
check_type
(
output_size
,
'output_size'
,
(
int
,
tuple
),
'roi_align'
)
if
isinstance
(
output_size
,
int
):
output_size
=
(
output_size
,
output_size
)
...
...
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