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
wmsofts
Paddle
提交
65efebb8
P
Paddle
项目概览
wmsofts
/
Paddle
与 Fork 源项目一致
Fork自
PaddlePaddle / Paddle
通知
1
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
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
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
体验新版 GitCode,发现更多精彩内容 >>
未验证
提交
65efebb8
编写于
9月 19, 2018
作者:
Q
qingqing01
提交者:
GitHub
9月 19, 2018
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
Fix detection.py after merge slice_op. (#13435)
上级
289acfa2
变更
1
隐藏空白更改
内联
并排
Showing
1 changed file
with
4 addition
and
9 deletion
+4
-9
python/paddle/fluid/layers/detection.py
python/paddle/fluid/layers/detection.py
+4
-9
未找到文件。
python/paddle/fluid/layers/detection.py
浏览文件 @
65efebb8
...
...
@@ -723,11 +723,10 @@ def ssd_loss(location,
target_label
.
stop_gradient
=
True
conf_loss
=
nn
.
softmax_with_cross_entropy
(
confidence
,
target_label
)
# 3. Mining hard examples
actual_shape
=
ops
.
slice
(
conf_shape
,
axes
=
[
0
],
starts
=
[
0
],
ends
=
[
2
])
actual_shape
.
stop_gradient
=
True
conf_loss
=
nn
.
reshape
(
x
=
conf_loss
,
shape
=
(
num
,
num_prior
),
actual_shape
=
ops
.
slice
(
conf_shape
,
axes
=
[
0
],
starts
=
[
0
],
ends
=
[
2
]))
x
=
conf_loss
,
shape
=
(
num
,
num_prior
),
actual_shape
=
actual_shape
)
conf_loss
.
stop_gradient
=
True
neg_indices
=
helper
.
create_tmp_variable
(
dtype
=
'int32'
)
dtype
=
matched_indices
.
dtype
...
...
@@ -796,11 +795,7 @@ def ssd_loss(location,
# 5.3 Compute overall weighted loss.
loss
=
conf_loss_weight
*
conf_loss
+
loc_loss_weight
*
loc_loss
# reshape to [N, Np], N is the batch size and Np is the prior box number.
loss
=
nn
.
reshape
(
x
=
loss
,
shape
=
(
num
,
num_prior
),
actual_shape
=
ops
.
slice
(
conf_shape
,
axes
=
[
0
],
starts
=
[
0
],
ends
=
[
2
]))
loss
=
nn
.
reshape
(
x
=
loss
,
shape
=
(
num
,
num_prior
),
actual_shape
=
actual_shape
)
loss
=
nn
.
reduce_sum
(
loss
,
dim
=
1
,
keep_dim
=
True
)
if
normalize
:
normalizer
=
nn
.
reduce_sum
(
target_loc_weight
)
...
...
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