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
znstj
PaddleOCR
提交
bb1a54ef
P
PaddleOCR
项目概览
znstj
/
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
1
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
1
Issue
1
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
bb1a54ef
编写于
5月 19, 2020
作者:
X
xiaoting
提交者:
GitHub
5月 19, 2020
浏览文件
操作
浏览文件
下载
差异文件
Merge pull request #65 from tink2123/save_epoch_0
Save weights at epoch 0
上级
838e8069
f806d8d8
变更
6
隐藏空白更改
内联
并排
Showing
6 changed file
with
16 addition
and
12 deletion
+16
-12
configs/det/det_mv3_east.yml
configs/det/det_mv3_east.yml
+2
-2
configs/det/det_r50_vd_db.yml
configs/det/det_r50_vd_db.yml
+2
-2
configs/det/det_r50_vd_east.yml
configs/det/det_r50_vd_east.yml
+2
-2
doc/detection.md
doc/detection.md
+3
-3
doc/installation.md
doc/installation.md
+1
-1
tools/program.py
tools/program.py
+6
-2
未找到文件。
configs/det/det_mv3_east.yml
浏览文件 @
bb1a54ef
...
...
@@ -11,7 +11,7 @@ Global:
test_batch_size_per_card
:
16
image_shape
:
[
3
,
512
,
512
]
reader_yml
:
./configs/det/det_east_icdar15_reader.yml
pretrain_weights
:
./pretrain_models/MobileNetV3_
pretrained/MobileNetV3_
large_x0_5_pretrained/
pretrain_weights
:
./pretrain_models/MobileNetV3_large_x0_5_pretrained/
checkpoints
:
save_res_path
:
./output/det_east/predicts_east.txt
save_inference_dir
:
...
...
@@ -42,4 +42,4 @@ PostProcess:
score_thresh
:
0.8
cover_thresh
:
0.1
nms_thresh
:
0.2
\ No newline at end of file
configs/det/det_r50_vd_db.yml
浏览文件 @
bb1a54ef
...
...
@@ -11,7 +11,7 @@ Global:
test_batch_size_per_card
:
16
image_shape
:
[
3
,
640
,
640
]
reader_yml
:
./configs/det/det_db_icdar15_reader.yml
pretrain_weights
:
./pretrain_models/ResNet50_vd_pretrained/
pretrain_weights
:
./pretrain_models/ResNet50_vd_
ssld_
pretrained/
save_res_path
:
./output/det_db/predicts_db.txt
checkpoints
:
save_inference_dir
:
...
...
@@ -50,4 +50,4 @@ PostProcess:
box_thresh
:
0.7
max_candidates
:
1000
unclip_ratio
:
1.5
\ No newline at end of file
configs/det/det_r50_vd_east.yml
浏览文件 @
bb1a54ef
...
...
@@ -11,7 +11,7 @@ Global:
test_batch_size_per_card
:
16
image_shape
:
[
3
,
512
,
512
]
reader_yml
:
./configs/det/det_east_icdar15_reader.yml
pretrain_weights
:
./pretrain_models/ResNet50_vd_pretrained/
pretrain_weights
:
./pretrain_models/ResNet50_vd_
ssld_
pretrained/
save_res_path
:
./output/det_east/predicts_east.txt
checkpoints
:
save_inference_dir
:
...
...
@@ -41,4 +41,4 @@ PostProcess:
score_thresh
:
0.8
cover_thresh
:
0.1
nms_thresh
:
0.2
\ No newline at end of file
doc/detection.md
浏览文件 @
bb1a54ef
...
...
@@ -16,7 +16,7 @@ wget -P ./train_data/ https://paddleocr.bj.bcebos.com/dataset/test_icdar2015_la
解压数据集和下载标注文件后,PaddleOCR/train_data/ 有两个文件夹和两个文件,分别是:
```
/PaddleOCR/train_data/
/PaddleOCR/train_data/
icdar2015/text_localization/
└─ icdar_c4_train_imgs/ icdar数据集的训练数据
└─ ch4_test_images/ icdar数据集的测试数据
└─ train_icdar2015_label.txt icdar数据集的训练标注
...
...
@@ -79,10 +79,10 @@ python3 tools/eval.py -c configs/det/det_mv3_db.yml -o Global.checkpoints="./ou
测试单张图像的检测效果
```
python3 tools/infer_det.py -c config/det/det_mv3_db.yml -o TestReader.single_img_path="./doc/imgs_en/img_10.jpg" Global.checkpoints="./output/det_db/best_accuracy"
python3 tools/infer_det.py -c config
s
/det/det_mv3_db.yml -o TestReader.single_img_path="./doc/imgs_en/img_10.jpg" Global.checkpoints="./output/det_db/best_accuracy"
```
测试文件夹下所有图像的检测效果
```
python3 tools/infer_det.py -c config/det/det_mv3_db.yml -o TestReader.single_img_path="./doc/imgs_en/" Global.checkpoints="./output/det_db/best_accuracy"
python3 tools/infer_det.py -c config
s
/det/det_mv3_db.yml -o TestReader.single_img_path="./doc/imgs_en/" Global.checkpoints="./output/det_db/best_accuracy"
```
doc/installation.md
浏览文件 @
bb1a54ef
...
...
@@ -20,7 +20,7 @@ sudo nvidia-docker run --name ppocr -v $PWD:/paddle --network=host -it hub.baidu
sudo nvidia-docker container exec -it ppocr /bin/bash
```
2.
安装PaddlePaddle Fluid v1.7
或更高版本
2.
安装PaddlePaddle Fluid v1.7
(暂不支持更高版本,适配工作进行中)
```
pip3 install --upgrade pip
...
...
tools/program.py
浏览文件 @
bb1a54ef
...
...
@@ -269,7 +269,9 @@ def train_eval_det_run(config, exe, train_info_dict, eval_info_dict):
except
fluid
.
core
.
EOFException
:
train_loader
.
reset
()
if
epoch
==
0
and
save_epoch_step
==
1
:
save_path
=
save_model_dir
+
"/iter_epoch_0"
save_model
(
train_info_dict
[
'train_program'
],
save_path
)
if
epoch
>
0
and
epoch
%
save_epoch_step
==
0
:
save_path
=
save_model_dir
+
"/iter_epoch_%d"
%
(
epoch
)
save_model
(
train_info_dict
[
'train_program'
],
save_path
)
...
...
@@ -346,7 +348,9 @@ def train_eval_rec_run(config, exe, train_info_dict, eval_info_dict):
except
fluid
.
core
.
EOFException
:
train_loader
.
reset
()
if
epoch
==
0
and
save_epoch_step
==
1
:
save_path
=
save_model_dir
+
"/iter_epoch_0"
save_model
(
train_info_dict
[
'train_program'
],
save_path
)
if
epoch
>
0
and
epoch
%
save_epoch_step
==
0
:
save_path
=
save_model_dir
+
"/iter_epoch_%d"
%
(
epoch
)
save_model
(
train_info_dict
[
'train_program'
],
save_path
)
...
...
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