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
PaddleDetection
提交
a13180fc
P
PaddleDetection
项目概览
PaddlePaddle
/
PaddleDetection
大约 1 年 前同步成功
通知
692
Star
11112
Fork
2696
代码
文件
提交
分支
Tags
贡献者
分支图
Diff
Issue
184
列表
看板
标记
里程碑
合并请求
40
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
184
Issue
184
列表
看板
标记
里程碑
合并请求
40
合并请求
40
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
a13180fc
编写于
7月 08, 2021
作者:
W
Wenyu
提交者:
GitHub
7月 08, 2021
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
fix import problem of _convert_attention_mask (#3631)
上级
c8f8a3b0
变更
2
显示空白变更内容
内联
并排
Showing
2 changed file
with
22 addition
and
4 deletion
+22
-4
ppdet/modeling/layers.py
ppdet/modeling/layers.py
+21
-2
ppdet/modeling/transformers/detr_transformer.py
ppdet/modeling/transformers/detr_transformer.py
+1
-2
未找到文件。
ppdet/modeling/layers.py
浏览文件 @
a13180fc
...
...
@@ -31,8 +31,6 @@ from . import ops
from
.initializer
import
xavier_uniform_
,
constant_
from
paddle.vision.ops
import
DeformConv2D
from
paddle.nn.layer
import
transformer
_convert_attention_mask
=
transformer
.
_convert_attention_mask
def
_to_list
(
l
):
...
...
@@ -1195,6 +1193,27 @@ class Concat(nn.Layer):
return
'dim={}'
.
format
(
self
.
dim
)
def
_convert_attention_mask
(
attn_mask
,
dtype
):
"""
Convert the attention mask to the target dtype we expect.
Parameters:
attn_mask (Tensor, optional): A tensor used in multi-head attention
to prevents attention to some unwanted positions, usually the
paddings or the subsequent positions. It is a tensor with shape
broadcasted to `[batch_size, n_head, sequence_length, sequence_length]`.
When the data type is bool, the unwanted positions have `False`
values and the others have `True` values. When the data type is
int, the unwanted positions have 0 values and the others have 1
values. When the data type is float, the unwanted positions have
`-INF` values and the others have 0 values. It can be None when
nothing wanted or needed to be prevented attention to. Default None.
dtype (VarType): The target type of `attn_mask` we expect.
Returns:
Tensor: A Tensor with shape same as input `attn_mask`, with data type `dtype`.
"""
return
nn
.
layer
.
transformer
.
_convert_attention_mask
(
attn_mask
,
dtype
)
class
MultiHeadAttention
(
nn
.
Layer
):
"""
Attention mapps queries and a set of key-value pairs to outputs, and
...
...
ppdet/modeling/transformers/detr_transformer.py
浏览文件 @
a13180fc
...
...
@@ -18,11 +18,10 @@ from __future__ import print_function
import
paddle
import
paddle.nn
as
nn
from
paddle.nn.layer.transformer
import
_convert_attention_mask
import
paddle.nn.functional
as
F
from
ppdet.core.workspace
import
register
from
..layers
import
MultiHeadAttention
from
..layers
import
MultiHeadAttention
,
_convert_attention_mask
from
.position_encoding
import
PositionEmbedding
from
.utils
import
*
from
..initializer
import
*
...
...
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