Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
Menu
Open sidebar
wangsen
paddle_dbnet
Commits
259f3bb0
".github/vscode:/vscode.git/clone" did not exist on "ae7cd5ad4c3ec9e13b5ad1b8d6f25b31696e78cf"
Commit
259f3bb0
authored
Feb 01, 2021
by
WenmuZhou
Browse files
update
parent
dbef4a1d
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
1 addition
and
1 deletion
+1
-1
doc/doc_ch/FAQ.md
doc/doc_ch/FAQ.md
+1
-1
No files found.
doc/doc_ch/FAQ.md
View file @
259f3bb0
...
@@ -725,7 +725,7 @@ ps -axu | grep train.py | awk '{print $2}' | xargs kill -9
...
@@ -725,7 +725,7 @@ ps -axu | grep train.py | awk '{print $2}' | xargs kill -9
**A**
:1.1和2.0的模型一样,微调时,垂直排列的文字需要逆时针旋转 90°后加入训练,上下颠倒的需要旋转为水平的。
**A**
:1.1和2.0的模型一样,微调时,垂直排列的文字需要逆时针旋转 90°后加入训练,上下颠倒的需要旋转为水平的。
#### Q3.3.30: 模型训练过程中如何得到 best_accuracy 模型?
#### Q3.3.30: 模型训练过程中如何得到 best_accuracy 模型?
**A**
:配置文件里的eval_batch_step字段用来控制多少次iter进行一次eval,在eval完成后会自动生成 best_accuracy 模型,所以如果希望很快就能拿到best_accuracy模型,可以将eval_batch_step改小一点
(例如,10)
。
**A**
:配置文件里的eval_batch_step字段用来控制多少次iter进行一次eval,在eval完成后会自动生成 best_accuracy 模型,所以如果希望很快就能拿到best_accuracy模型,可以将eval_batch_step改小一点
,如改为[10,10],这样表示第10次迭代后,以后没隔10个迭代就进行一次模型的评估
。
<a
name=
"预测部署3"
></a>
<a
name=
"预测部署3"
></a>
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment