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
weixin_41840029
PaddleOCR
提交
1a06bff0
P
PaddleOCR
项目概览
weixin_41840029
/
PaddleOCR
与 Fork 源项目一致
Fork自
PaddlePaddle / PaddleOCR
通知
1
Star
1
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
提交
1a06bff0
编写于
6月 08, 2021
作者:
L
LDOUBLEV
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
delete epoch from params.txt
上级
83149576
变更
2
隐藏空白更改
内联
并排
Showing
2 changed file
with
7 addition
and
5 deletion
+7
-5
test/params.txt
test/params.txt
+0
-2
test/test.sh
test/test.sh
+7
-3
未找到文件。
test/params.txt
浏览文件 @
1a06bff0
...
...
@@ -12,6 +12,4 @@ rec_batch_size_list: 1|6
gpu_trt_list: True|False
gpu_precision_list: fp32|fp16|int8
epoch: 10
checkpoints: None
test/test.sh
浏览文件 @
1a06bff0
...
...
@@ -15,10 +15,14 @@ if [ ${MODE} = "lite_train_infer" ];then
cd
./train_data/
&&
tar
xf icdar2015_lite.tar
&&
ln
-s
./icdar2015_lite ./icdar2015
cd
../
epoch
=
10
eval_batch_step
=
10
elif
[
${
MODE
}
=
"whole_train_infer"
]
;
then
rm
-rf
./train_data/icdar2015
wget
-nc
-P
./train_data/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/icdar2015.tar
cd
./train_data/
&&
tar
xf icdar2015.tar
&&
cd
../
epoch
=
300
eval_batch_step
=
200
else
echo
"Do Nothing"
fi
...
...
@@ -52,8 +56,8 @@ gpu_trt_list=$(func_parser "${lines[10]}")
gpu_precision_list
=
$(
func_parser
"
${
lines
[11]
}
"
)
img_dir
=
"./train_data/icdar2015/text_localization/ch4_test_images/"
# train superparameters
epoch
=
$(
func_parser
"
${
lines
[12]
}
"
)
checkpoints
=
$(
func_parser
"
${
lines
[13]
}
"
)
#
epoch=$(func_parser "${lines[12]}")
#
checkpoints=$(func_parser "${lines[13]}")
for
train_model
in
${
train_model_list
[*]
}
;
do
...
...
@@ -99,7 +103,7 @@ for train_model in ${train_model_list[*]}; do
fi
# dataset="Train.dataset.data_dir=${train_dir} Train.dataset.label_file_list=${train_label_file} Eval.dataset.data_dir=${eval_dir} Eval.dataset.label_file_list=${eval_label_file}"
save_log
=
${
log_path
}
/
${
model_name
}
_
${
slim_trainer
}
_autocast_
${
auto_cast
}
_gpuid_
${
gpu
}
echo
${
python
}
${
launch
}
${
trainer
}
-c
${
yml_file
}
-o
Global.auto_cast
=
${
auto_cast
}
Global.save_model_dir
=
${
save_log
}
Global.use_gpu
=
${
use_gpu
}
Global.epoch
=
${
epoch
}
${
python
}
${
launch
}
${
trainer
}
-c
${
yml_file
}
-o
Global.epoch_num
=
${
epoch
}
Global.eval_batch_step
=
${
eval_batch_step
}
Global.auto_cast
=
${
auto_cast
}
Global.save_model_dir
=
${
save_log
}
Global.use_gpu
=
${
use_gpu
}
${
python
}
${
export_model
}
-c
${
yml_file
}
-o
Global.pretrained_model
=
${
save_log
}
/best_accuracy Global.save_inference_dir
=
${
save_log
}
/export_inference/
if
[
"
${
model_name
}
"
=
"det"
]
;
then
export
rec_batch_size_list
=(
"1"
)
...
...
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