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
爱学习的小尤
PaddleOCR
提交
da5d7ee3
P
PaddleOCR
项目概览
爱学习的小尤
/
PaddleOCR
与 Fork 源项目一致
Fork自
PaddlePaddle / PaddleOCR
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
PaddleOCR
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
da5d7ee3
编写于
8月 03, 2021
作者:
D
Double_V
提交者:
GitHub
8月 03, 2021
浏览文件
操作
浏览文件
下载
差异文件
Merge pull request #3496 from fengxiaoshuai/dynameic_shape_change
change dynameic shape
上级
1664aa98
ef103a59
变更
1
显示空白变更内容
内联
并排
Showing
1 changed file
with
25 addition
and
25 deletion
+25
-25
tools/infer/utility.py
tools/infer/utility.py
+25
-25
未找到文件。
tools/infer/utility.py
浏览文件 @
da5d7ee3
...
...
@@ -169,45 +169,45 @@ def create_predictor(args, mode, logger):
if
mode
==
"det"
:
min_input_shape
=
{
"x"
:
[
1
,
3
,
50
,
50
],
"conv2d_92.tmp_0"
:
[
1
,
96
,
20
,
20
],
"conv2d_91.tmp_0"
:
[
1
,
96
,
10
,
10
],
"conv2d_92.tmp_0"
:
[
1
,
120
,
20
,
20
],
"conv2d_91.tmp_0"
:
[
1
,
24
,
10
,
10
],
"conv2d_59.tmp_0"
:
[
1
,
96
,
20
,
20
],
"nearest_interp_v2_1.tmp_0"
:
[
1
,
9
6
,
10
,
10
],
"nearest_interp_v2_2.tmp_0"
:
[
1
,
9
6
,
20
,
20
],
"conv2d_124.tmp_0"
:
[
1
,
9
6
,
20
,
20
],
"nearest_interp_v2_3.tmp_0"
:
[
1
,
2
4
,
20
,
20
],
"nearest_interp_v2_4.tmp_0"
:
[
1
,
2
4
,
20
,
20
],
"nearest_interp_v2_5.tmp_0"
:
[
1
,
2
4
,
20
,
20
],
"nearest_interp_v2_1.tmp_0"
:
[
1
,
25
6
,
10
,
10
],
"nearest_interp_v2_2.tmp_0"
:
[
1
,
25
6
,
20
,
20
],
"conv2d_124.tmp_0"
:
[
1
,
25
6
,
20
,
20
],
"nearest_interp_v2_3.tmp_0"
:
[
1
,
6
4
,
20
,
20
],
"nearest_interp_v2_4.tmp_0"
:
[
1
,
6
4
,
20
,
20
],
"nearest_interp_v2_5.tmp_0"
:
[
1
,
6
4
,
20
,
20
],
"elementwise_add_7"
:
[
1
,
56
,
2
,
2
],
"nearest_interp_v2_0.tmp_0"
:
[
1
,
9
6
,
2
,
2
]
"nearest_interp_v2_0.tmp_0"
:
[
1
,
25
6
,
2
,
2
]
}
max_input_shape
=
{
"x"
:
[
1
,
3
,
2000
,
2000
],
"conv2d_92.tmp_0"
:
[
1
,
96
,
400
,
400
],
"conv2d_91.tmp_0"
:
[
1
,
96
,
200
,
200
],
"conv2d_92.tmp_0"
:
[
1
,
120
,
400
,
400
],
"conv2d_91.tmp_0"
:
[
1
,
24
,
200
,
200
],
"conv2d_59.tmp_0"
:
[
1
,
96
,
400
,
400
],
"nearest_interp_v2_1.tmp_0"
:
[
1
,
9
6
,
200
,
200
],
"nearest_interp_v2_1.tmp_0"
:
[
1
,
25
6
,
200
,
200
],
"conv2d_124.tmp_0"
:
[
1
,
256
,
400
,
400
],
"nearest_interp_v2_2.tmp_0"
:
[
1
,
9
6
,
400
,
400
],
"nearest_interp_v2_3.tmp_0"
:
[
1
,
2
4
,
400
,
400
],
"nearest_interp_v2_4.tmp_0"
:
[
1
,
2
4
,
400
,
400
],
"nearest_interp_v2_5.tmp_0"
:
[
1
,
2
4
,
400
,
400
],
"nearest_interp_v2_2.tmp_0"
:
[
1
,
25
6
,
400
,
400
],
"nearest_interp_v2_3.tmp_0"
:
[
1
,
6
4
,
400
,
400
],
"nearest_interp_v2_4.tmp_0"
:
[
1
,
6
4
,
400
,
400
],
"nearest_interp_v2_5.tmp_0"
:
[
1
,
6
4
,
400
,
400
],
"elementwise_add_7"
:
[
1
,
56
,
400
,
400
],
"nearest_interp_v2_0.tmp_0"
:
[
1
,
9
6
,
400
,
400
]
"nearest_interp_v2_0.tmp_0"
:
[
1
,
25
6
,
400
,
400
]
}
opt_input_shape
=
{
"x"
:
[
1
,
3
,
640
,
640
],
"conv2d_92.tmp_0"
:
[
1
,
96
,
160
,
160
],
"conv2d_91.tmp_0"
:
[
1
,
96
,
80
,
80
],
"conv2d_92.tmp_0"
:
[
1
,
120
,
160
,
160
],
"conv2d_91.tmp_0"
:
[
1
,
24
,
80
,
80
],
"conv2d_59.tmp_0"
:
[
1
,
96
,
160
,
160
],
"nearest_interp_v2_1.tmp_0"
:
[
1
,
9
6
,
80
,
80
],
"nearest_interp_v2_2.tmp_0"
:
[
1
,
9
6
,
160
,
160
],
"nearest_interp_v2_1.tmp_0"
:
[
1
,
25
6
,
80
,
80
],
"nearest_interp_v2_2.tmp_0"
:
[
1
,
25
6
,
160
,
160
],
"conv2d_124.tmp_0"
:
[
1
,
256
,
160
,
160
],
"nearest_interp_v2_3.tmp_0"
:
[
1
,
2
4
,
160
,
160
],
"nearest_interp_v2_4.tmp_0"
:
[
1
,
2
4
,
160
,
160
],
"nearest_interp_v2_5.tmp_0"
:
[
1
,
2
4
,
160
,
160
],
"nearest_interp_v2_3.tmp_0"
:
[
1
,
6
4
,
160
,
160
],
"nearest_interp_v2_4.tmp_0"
:
[
1
,
6
4
,
160
,
160
],
"nearest_interp_v2_5.tmp_0"
:
[
1
,
6
4
,
160
,
160
],
"elementwise_add_7"
:
[
1
,
56
,
40
,
40
],
"nearest_interp_v2_0.tmp_0"
:
[
1
,
9
6
,
40
,
40
]
"nearest_interp_v2_0.tmp_0"
:
[
1
,
25
6
,
40
,
40
]
}
elif
mode
==
"rec"
:
min_input_shape
=
{
"x"
:
[
args
.
rec_batch_num
,
3
,
32
,
10
]}
...
...
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