"...git@developer.sourcefind.cn:chenpangpang/open-webui.git" did not exist on "194564e253ef60086e33b8efcd3656f18e11c151"
Commit a739abab authored by WenmuZhou's avatar WenmuZhou
Browse files

merge dygraph

parents 982926db 75aa6f2f
......@@ -398,6 +398,7 @@ class MainWindow(QMainWindow, WindowMixin):
help = action(getStr('tutorial'), self.showTutorialDialog, None, 'help', getStr('tutorialDetail'))
showInfo = action(getStr('info'), self.showInfoDialog, None, 'help', getStr('info'))
showSteps = action(getStr('steps'), self.showStepsDialog, None, 'help', getStr('steps'))
showKeys = action(getStr('keys'), self.showKeysDialog, None, 'help', getStr('keys'))
zoom = QWidgetAction(self)
zoom.setDefaultWidget(self.zoomWidget)
......@@ -565,7 +566,7 @@ class MainWindow(QMainWindow, WindowMixin):
addActions(self.menus.file,
(opendir, None, saveLabel, saveRec, self.autoSaveOption, None, resetAll, deleteImg, quit))
addActions(self.menus.help, (showSteps, showInfo))
addActions(self.menus.help, (showKeys,showSteps, showInfo))
addActions(self.menus.view, (
self.displayLabelOption, self.labelDialogOption,
None,
......@@ -760,6 +761,10 @@ class MainWindow(QMainWindow, WindowMixin):
msg = stepsInfo(self.lang)
QMessageBox.information(self, u'Information', msg)
def showKeysDialog(self):
msg = keysInfo(self.lang)
QMessageBox.information(self, u'Information', msg)
def createShape(self):
assert self.beginner()
self.canvas.setEditing(False)
......
This diff is collapsed.
......@@ -174,6 +174,7 @@ def stepsInfo(lang='en'):
"10. 标注结果:关闭应用程序或切换文件路径后,手动保存过的标签将会被存放在所打开图片文件夹下的" \
"*Label.txt*中。在菜单栏点击 “PaddleOCR” - 保存识别结果后,会将此类图片的识别训练数据保存在*crop_img*文件夹下," \
"识别标签保存在*rec_gt.txt*中。\n"
else:
msg = "1. Build and launch using the instructions above.\n" \
"2. Click 'Open Dir' in Menu/File to select the folder of the picture.\n"\
......@@ -187,5 +188,57 @@ def stepsInfo(lang='en'):
"8. Click 'Save', the image status will switch to '√',then the program automatically jump to the next.\n"\
"9. Click 'Delete Image' and the image will be deleted to the recycle bin.\n"\
"10. Labeling result: After closing the application or switching the file path, the manually saved label will be stored in *Label.txt* under the opened picture folder.\n"\
" Click PaddleOCR-Save Recognition Results in the menu bar, the recognition training data of such pictures will be saved in the *crop_img* folder, and the recognition label will be saved in *rec_gt.txt*.\n"
" Click PaddleOCR-Save Recognition Results in the menu bar, the recognition training data of such pictures will be saved in the *crop_img* folder, and the recognition label will be saved in *rec_gt.txt*.\n"
return msg
def keysInfo(lang='en'):
if lang == 'ch':
msg = "快捷键\t\t\t说明\n" \
"———————————————————————\n"\
"Ctrl + shift + R\t\t对当前图片的所有标记重新识别\n" \
"W\t\t\t新建矩形框\n" \
"Q\t\t\t新建四点框\n" \
"Ctrl + E\t\t编辑所选框标签\n" \
"Ctrl + R\t\t重新识别所选标记\n" \
"Ctrl + C\t\t复制并粘贴选中的标记框\n" \
"Ctrl + 鼠标左键\t\t多选标记框\n" \
"Backspace\t\t删除所选框\n" \
"Ctrl + V\t\t确认本张图片标记\n" \
"Ctrl + Shift + d\t删除本张图片\n" \
"D\t\t\t下一张图片\n" \
"A\t\t\t上一张图片\n" \
"Ctrl++\t\t\t缩小\n" \
"Ctrl--\t\t\t放大\n" \
"↑→↓←\t\t\t移动标记框\n" \
"———————————————————————\n" \
"注:Mac用户Command键替换上述Ctrl键"
else:
msg = "Shortcut Keys\t\tDescription\n" \
"———————————————————————\n" \
"Ctrl + shift + R\t\tRe-recognize all the labels\n" \
"\t\t\tof the current image\n" \
"\n"\
"W\t\t\tCreate a rect box\n" \
"Q\t\t\tCreate a four-points box\n" \
"Ctrl + E\t\tEdit label of the selected box\n" \
"Ctrl + R\t\tRe-recognize the selected box\n" \
"Ctrl + C\t\tCopy and paste the selected\n" \
"\t\t\tbox\n" \
"\n"\
"Ctrl + Left Mouse\tMulti select the label\n" \
"Button\t\t\tbox\n" \
"\n"\
"Backspace\t\tDelete the selected box\n" \
"Ctrl + V\t\tCheck image\n" \
"Ctrl + Shift + d\tDelete image\n" \
"D\t\t\tNext image\n" \
"A\t\t\tPrevious image\n" \
"Ctrl++\t\t\tZoom in\n" \
"Ctrl--\t\t\tZoom out\n" \
"↑→↓←\t\t\tMove selected box" \
"———————————————————————\n" \
"Notice:For Mac users, use the 'Command' key instead of the 'Ctrl' key"
return msg
\ No newline at end of file
......@@ -89,6 +89,7 @@ saveRec=保存识别结果
tempLabel=待识别
nullLabel=无法识别
steps=操作步骤
keys=快捷键
choseModelLg=选择模型语言
cancel=取消
ok=确认
......
......@@ -89,6 +89,7 @@ saveRec=Save Recognition Result
tempLabel=TEMPORARY
nullLabel=NULL
steps=Steps
keys=Shortcut Keys
choseModelLg=Choose Model Language
cancel=Cancel
ok=OK
......
Global:
use_gpu: true
epoch_num: 1200
log_smooth_window: 20
print_batch_step: 2
save_model_dir: ./output/ch_db_mv3/
save_epoch_step: 1200
# evaluation is run every 5000 iterations after the 4000th iteration
eval_batch_step: [3000, 2000]
cal_metric_during_train: False
pretrained_model: ./pretrain_models/MobileNetV3_large_x0_5_pretrained
checkpoints:
save_inference_dir:
use_visualdl: False
infer_img: doc/imgs_en/img_10.jpg
save_res_path: ./output/det_db/predicts_db.txt
Architecture:
name: DistillationModel
algorithm: Distillation
Models:
Student:
pretrained: ./pretrain_models/MobileNetV3_large_x0_5_pretrained
freeze_params: false
return_all_feats: false
model_type: det
algorithm: DB
Backbone:
name: MobileNetV3
scale: 0.5
model_name: large
disable_se: True
Neck:
name: DBFPN
out_channels: 96
Head:
name: DBHead
k: 50
Student2:
pretrained: ./pretrain_models/MobileNetV3_large_x0_5_pretrained
freeze_params: false
return_all_feats: false
model_type: det
algorithm: DB
Transform:
Backbone:
name: MobileNetV3
scale: 0.5
model_name: large
disable_se: True
Neck:
name: DBFPN
out_channels: 96
Head:
name: DBHead
k: 50
Teacher:
pretrained: ./pretrain_models/ch_ppocr_server_v2.0_det_train/best_accuracy
freeze_params: true
return_all_feats: false
model_type: det
algorithm: DB
Transform:
Backbone:
name: ResNet
layers: 18
Neck:
name: DBFPN
out_channels: 256
Head:
name: DBHead
k: 50
Loss:
name: CombinedLoss
loss_config_list:
- DistillationDilaDBLoss:
weight: 1.0
model_name_pairs:
- ["Student", "Teacher"]
- ["Student2", "Teacher"]
key: maps
balance_loss: true
main_loss_type: DiceLoss
alpha: 5
beta: 10
ohem_ratio: 3
- DistillationDMLLoss:
model_name_pairs:
- ["Student", "Student2"]
maps_name: "thrink_maps"
weight: 1.0
# act: None
model_name_pairs: ["Student", "Student2"]
key: maps
- DistillationDBLoss:
weight: 1.0
model_name_list: ["Student", "Student2"]
# key: maps
# name: DBLoss
balance_loss: true
main_loss_type: DiceLoss
alpha: 5
beta: 10
ohem_ratio: 3
Optimizer:
name: Adam
beta1: 0.9
beta2: 0.999
lr:
name: Cosine
learning_rate: 0.001
warmup_epoch: 2
regularizer:
name: 'L2'
factor: 0
PostProcess:
name: DistillationDBPostProcess
model_name: ["Student", "Student2", "Teacher"]
# key: maps
thresh: 0.3
box_thresh: 0.6
max_candidates: 1000
unclip_ratio: 1.5
Metric:
name: DistillationMetric
base_metric_name: DetMetric
main_indicator: hmean
key: "Student"
Train:
dataset:
name: SimpleDataSet
data_dir: ./train_data/icdar2015/text_localization/
label_file_list:
- ./train_data/icdar2015/text_localization/train_icdar2015_label.txt
ratio_list: [1.0]
transforms:
- DecodeImage: # load image
img_mode: BGR
channel_first: False
- DetLabelEncode: # Class handling label
- IaaAugment:
augmenter_args:
- { 'type': Fliplr, 'args': { 'p': 0.5 } }
- { 'type': Affine, 'args': { 'rotate': [-10, 10] } }
- { 'type': Resize, 'args': { 'size': [0.5, 3] } }
- EastRandomCropData:
size: [960, 960]
max_tries: 50
keep_ratio: true
- MakeBorderMap:
shrink_ratio: 0.4
thresh_min: 0.3
thresh_max: 0.7
- MakeShrinkMap:
shrink_ratio: 0.4
min_text_size: 8
- NormalizeImage:
scale: 1./255.
mean: [0.485, 0.456, 0.406]
std: [0.229, 0.224, 0.225]
order: 'hwc'
- ToCHWImage:
- KeepKeys:
keep_keys: ['image', 'threshold_map', 'threshold_mask', 'shrink_map', 'shrink_mask'] # the order of the dataloader list
loader:
shuffle: True
drop_last: False
batch_size_per_card: 8
num_workers: 4
Eval:
dataset:
name: SimpleDataSet
data_dir: ./train_data/icdar2015/text_localization/
label_file_list:
- ./train_data/icdar2015/text_localization/test_icdar2015_label.txt
transforms:
- DecodeImage: # load image
img_mode: BGR
channel_first: False
- DetLabelEncode: # Class handling label
- DetResizeForTest:
# image_shape: [736, 1280]
- NormalizeImage:
scale: 1./255.
mean: [0.485, 0.456, 0.406]
std: [0.229, 0.224, 0.225]
order: 'hwc'
- ToCHWImage:
- KeepKeys:
keep_keys: ['image', 'shape', 'polys', 'ignore_tags']
loader:
shuffle: False
drop_last: False
batch_size_per_card: 1 # must be 1
num_workers: 2
Global:
use_gpu: true
epoch_num: 1200
log_smooth_window: 20
print_batch_step: 2
save_model_dir: ./output/ch_db_mv3/
save_epoch_step: 1200
# evaluation is run every 5000 iterations after the 4000th iteration
eval_batch_step: [3000, 2000]
cal_metric_during_train: False
pretrained_model: ./pretrain_models/MobileNetV3_large_x0_5_pretrained
checkpoints:
save_inference_dir:
use_visualdl: False
infer_img: doc/imgs_en/img_10.jpg
save_res_path: ./output/det_db/predicts_db.txt
Architecture:
name: DistillationModel
algorithm: Distillation
Models:
Student:
pretrained: ./pretrain_models/MobileNetV3_large_x0_5_pretrained
freeze_params: false
return_all_feats: false
model_type: det
algorithm: DB
Backbone:
name: MobileNetV3
scale: 0.5
model_name: large
disable_se: True
Neck:
name: DBFPN
out_channels: 96
Head:
name: DBHead
k: 50
Teacher:
pretrained: ./pretrain_models/ch_ppocr_server_v2.0_det_train/best_accuracy
freeze_params: true
return_all_feats: false
model_type: det
algorithm: DB
Transform:
Backbone:
name: ResNet
layers: 18
Neck:
name: DBFPN
out_channels: 256
Head:
name: DBHead
k: 50
Loss:
name: CombinedLoss
loss_config_list:
- DistillationDilaDBLoss:
weight: 1.0
model_name_pairs:
- ["Student", "Teacher"]
key: maps
balance_loss: true
main_loss_type: DiceLoss
alpha: 5
beta: 10
ohem_ratio: 3
- DistillationDBLoss:
weight: 1.0
model_name_list: ["Student", "Teacher"]
# key: maps
name: DBLoss
balance_loss: true
main_loss_type: DiceLoss
alpha: 5
beta: 10
ohem_ratio: 3
Optimizer:
name: Adam
beta1: 0.9
beta2: 0.999
lr:
name: Cosine
learning_rate: 0.001
warmup_epoch: 2
regularizer:
name: 'L2'
factor: 0
PostProcess:
name: DistillationDBPostProcess
model_name: ["Student", "Student2"]
key: head_out
thresh: 0.3
box_thresh: 0.6
max_candidates: 1000
unclip_ratio: 1.5
Metric:
name: DistillationMetric
base_metric_name: DetMetric
main_indicator: hmean
key: "Student"
Train:
dataset:
name: SimpleDataSet
data_dir: ./train_data/icdar2015/text_localization/
label_file_list:
- ./train_data/icdar2015/text_localization/train_icdar2015_label.txt
ratio_list: [1.0]
transforms:
- DecodeImage: # load image
img_mode: BGR
channel_first: False
- DetLabelEncode: # Class handling label
- IaaAugment:
augmenter_args:
- { 'type': Fliplr, 'args': { 'p': 0.5 } }
- { 'type': Affine, 'args': { 'rotate': [-10, 10] } }
- { 'type': Resize, 'args': { 'size': [0.5, 3] } }
- EastRandomCropData:
size: [960, 960]
max_tries: 50
keep_ratio: true
- MakeBorderMap:
shrink_ratio: 0.4
thresh_min: 0.3
thresh_max: 0.7
- MakeShrinkMap:
shrink_ratio: 0.4
min_text_size: 8
- NormalizeImage:
scale: 1./255.
mean: [0.485, 0.456, 0.406]
std: [0.229, 0.224, 0.225]
order: 'hwc'
- ToCHWImage:
- KeepKeys:
keep_keys: ['image', 'threshold_map', 'threshold_mask', 'shrink_map', 'shrink_mask'] # the order of the dataloader list
loader:
shuffle: True
drop_last: False
batch_size_per_card: 8
num_workers: 4
Eval:
dataset:
name: SimpleDataSet
data_dir: ./train_data/icdar2015/text_localization/
label_file_list:
- ./train_data/icdar2015/text_localization/test_icdar2015_label.txt
transforms:
- DecodeImage: # load image
img_mode: BGR
channel_first: False
- DetLabelEncode: # Class handling label
- DetResizeForTest:
# image_shape: [736, 1280]
- NormalizeImage:
scale: 1./255.
mean: [0.485, 0.456, 0.406]
std: [0.229, 0.224, 0.225]
order: 'hwc'
- ToCHWImage:
- KeepKeys:
keep_keys: ['image', 'shape', 'polys', 'ignore_tags']
loader:
shuffle: False
drop_last: False
batch_size_per_card: 1 # must be 1
num_workers: 2
Global:
use_gpu: true
epoch_num: 1200
log_smooth_window: 20
print_batch_step: 2
save_model_dir: ./output/ch_db_mv3/
save_epoch_step: 1200
# evaluation is run every 5000 iterations after the 4000th iteration
eval_batch_step: [3000, 2000]
cal_metric_during_train: False
pretrained_model: ./pretrain_models/MobileNetV3_large_x0_5_pretrained
checkpoints:
save_inference_dir:
use_visualdl: False
infer_img: doc/imgs_en/img_10.jpg
save_res_path: ./output/det_db/predicts_db.txt
Architecture:
name: DistillationModel
algorithm: Distillation
Models:
Student:
pretrained: ./pretrain_models/MobileNetV3_large_x0_5_pretrained
freeze_params: false
return_all_feats: false
model_type: det
algorithm: DB
Backbone:
name: MobileNetV3
scale: 0.5
model_name: large
disable_se: True
Neck:
name: DBFPN
out_channels: 96
Head:
name: DBHead
k: 50
Student2:
pretrained: ./pretrain_models/MobileNetV3_large_x0_5_pretrained
freeze_params: false
return_all_feats: false
model_type: det
algorithm: DB
Transform:
Backbone:
name: MobileNetV3
scale: 0.5
model_name: large
disable_se: True
Neck:
name: DBFPN
out_channels: 96
Head:
name: DBHead
k: 50
Loss:
name: CombinedLoss
loss_config_list:
- DistillationDMLLoss:
model_name_pairs:
- ["Student", "Student2"]
maps_name: "thrink_maps"
weight: 1.0
act: "softmax"
model_name_pairs: ["Student", "Student2"]
key: maps
- DistillationDBLoss:
weight: 1.0
model_name_list: ["Student", "Student2"]
# key: maps
name: DBLoss
balance_loss: true
main_loss_type: DiceLoss
alpha: 5
beta: 10
ohem_ratio: 3
Optimizer:
name: Adam
beta1: 0.9
beta2: 0.999
lr:
name: Cosine
learning_rate: 0.001
warmup_epoch: 2
regularizer:
name: 'L2'
factor: 0
PostProcess:
name: DistillationDBPostProcess
model_name: ["Student", "Student2"]
key: head_out
thresh: 0.3
box_thresh: 0.6
max_candidates: 1000
unclip_ratio: 1.5
Metric:
name: DistillationMetric
base_metric_name: DetMetric
main_indicator: hmean
key: "Student"
Train:
dataset:
name: SimpleDataSet
data_dir: ./train_data/icdar2015/text_localization/
label_file_list:
- ./train_data/icdar2015/text_localization/train_icdar2015_label.txt
ratio_list: [1.0]
transforms:
- DecodeImage: # load image
img_mode: BGR
channel_first: False
- DetLabelEncode: # Class handling label
- IaaAugment:
augmenter_args:
- { 'type': Fliplr, 'args': { 'p': 0.5 } }
- { 'type': Affine, 'args': { 'rotate': [-10, 10] } }
- { 'type': Resize, 'args': { 'size': [0.5, 3] } }
- EastRandomCropData:
size: [960, 960]
max_tries: 50
keep_ratio: true
- MakeBorderMap:
shrink_ratio: 0.4
thresh_min: 0.3
thresh_max: 0.7
- MakeShrinkMap:
shrink_ratio: 0.4
min_text_size: 8
- NormalizeImage:
scale: 1./255.
mean: [0.485, 0.456, 0.406]
std: [0.229, 0.224, 0.225]
order: 'hwc'
- ToCHWImage:
- KeepKeys:
keep_keys: ['image', 'threshold_map', 'threshold_mask', 'shrink_map', 'shrink_mask'] # the order of the dataloader list
loader:
shuffle: True
drop_last: False
batch_size_per_card: 8
num_workers: 4
Eval:
dataset:
name: SimpleDataSet
data_dir: ./train_data/icdar2015/text_localization/
label_file_list:
- ./train_data/icdar2015/text_localization/test_icdar2015_label.txt
transforms:
- DecodeImage: # load image
img_mode: BGR
channel_first: False
- DetLabelEncode: # Class handling label
- DetResizeForTest:
# image_shape: [736, 1280]
- NormalizeImage:
scale: 1./255.
mean: [0.485, 0.456, 0.406]
std: [0.229, 0.224, 0.225]
order: 'hwc'
- ToCHWImage:
- KeepKeys:
keep_keys: ['image', 'shape', 'polys', 'ignore_tags']
loader:
shuffle: False
drop_last: False
batch_size_per_card: 1 # must be 1
num_workers: 2
......@@ -13,7 +13,6 @@ SET(TENSORRT_DIR "" CACHE PATH "Compile demo with TensorRT")
set(DEMO_NAME "ocr_system")
macro(safe_set_static_flag)
foreach(flag_var
CMAKE_CXX_FLAGS CMAKE_CXX_FLAGS_DEBUG CMAKE_CXX_FLAGS_RELEASE
......
......@@ -93,3 +93,5 @@ cd D:\projects\PaddleOCR\deploy\cpp_infer\out\build\x64-Release
### 注意
* 在Windows下的终端中执行文件exe时,可能会发生乱码的现象,此时需要在终端中输入`CHCP 65001`,将终端的编码方式由GBK编码(默认)改为UTF-8编码,更加具体的解释可以参考这篇博客:[https://blog.csdn.net/qq_35038153/article/details/78430359](https://blog.csdn.net/qq_35038153/article/details/78430359)
* 编译时,如果报错`错误:C1083 无法打开包括文件:"dirent.h":No such file or directory`,可以参考该[文档](https://blog.csdn.net/Dora_blank/article/details/117740837#41_C1083_direnthNo_such_file_or_directory_54),新建`dirent.h`文件,并添加到`VC++`的包含目录中。
......@@ -18,6 +18,7 @@ PaddleOCR模型部署。
* 首先需要从opencv官网上下载在Linux环境下源码编译的包,以opencv3.4.7为例,下载命令如下。
```
cd deploy/cpp_infer
wget https://github.com/opencv/opencv/archive/3.4.7.tar.gz
tar -xf 3.4.7.tar.gz
```
......@@ -184,7 +185,7 @@ cmake .. \
make -j
```
`OPENCV_DIR`为opencv编译安装的地址;`LIB_DIR`为下载(`paddle_inference`文件夹)或者编译生成的Paddle预测库地址(`build/paddle_inference_install_dir`文件夹);`CUDA_LIB_DIR`为cuda库文件地址,在docker中为`/usr/local/cuda/lib64``CUDNN_LIB_DIR`为cudnn库文件地址,在docker中为`/usr/lib/x86_64-linux-gnu/`
`OPENCV_DIR`为opencv编译安装的地址;`LIB_DIR`为下载(`paddle_inference`文件夹)或者编译生成的Paddle预测库地址(`build/paddle_inference_install_dir`文件夹);`CUDA_LIB_DIR`为cuda库文件地址,在docker中为`/usr/local/cuda/lib64``CUDNN_LIB_DIR`为cudnn库文件地址,在docker中为`/usr/lib/x86_64-linux-gnu/`**注意**:以上路径都写绝对路径,不要写相对路径。
* 编译完成之后,会在`build`文件夹下生成一个名为`ocr_system`的可执行文件。
......
......@@ -18,6 +18,7 @@ PaddleOCR model deployment.
* First of all, you need to download the source code compiled package in the Linux environment from the opencv official website. Taking opencv3.4.7 as an example, the download command is as follows.
```
cd deploy/cpp_infer
wget https://github.com/opencv/opencv/archive/3.4.7.tar.gz
tar -xf 3.4.7.tar.gz
```
......
......@@ -668,7 +668,7 @@ void DisposeOutPts(OutPt *&pp) {
//------------------------------------------------------------------------------
inline void InitEdge(TEdge *e, TEdge *eNext, TEdge *ePrev, const IntPoint &Pt) {
std::memset(e, 0, sizeof(TEdge));
std::memset(e, int(0), sizeof(TEdge));
e->Next = eNext;
e->Prev = ePrev;
e->Curr = Pt;
......@@ -1895,17 +1895,17 @@ void Clipper::InsertLocalMinimaIntoAEL(const cInt botY) {
TEdge *rb = lm->RightBound;
OutPt *Op1 = 0;
if (!lb) {
if (!lb || !rb) {
// nb: don't insert LB into either AEL or SEL
InsertEdgeIntoAEL(rb, 0);
SetWindingCount(*rb);
if (IsContributing(*rb))
Op1 = AddOutPt(rb, rb->Bot);
} else if (!rb) {
InsertEdgeIntoAEL(lb, 0);
SetWindingCount(*lb);
if (IsContributing(*lb))
Op1 = AddOutPt(lb, lb->Bot);
//} else if (!rb) {
// InsertEdgeIntoAEL(lb, 0);
// SetWindingCount(*lb);
// if (IsContributing(*lb))
// Op1 = AddOutPt(lb, lb->Bot);
InsertScanbeam(lb->Top.Y);
} else {
InsertEdgeIntoAEL(lb, 0);
......@@ -2547,13 +2547,13 @@ void Clipper::ProcessHorizontal(TEdge *horzEdge) {
if (dir == dLeftToRight) {
maxIt = m_Maxima.begin();
while (maxIt != m_Maxima.end() && *maxIt <= horzEdge->Bot.X)
maxIt++;
++maxIt;
if (maxIt != m_Maxima.end() && *maxIt >= eLastHorz->Top.X)
maxIt = m_Maxima.end();
} else {
maxRit = m_Maxima.rbegin();
while (maxRit != m_Maxima.rend() && *maxRit > horzEdge->Bot.X)
maxRit++;
++maxRit;
if (maxRit != m_Maxima.rend() && *maxRit <= eLastHorz->Top.X)
maxRit = m_Maxima.rend();
}
......@@ -2576,13 +2576,13 @@ void Clipper::ProcessHorizontal(TEdge *horzEdge) {
while (maxIt != m_Maxima.end() && *maxIt < e->Curr.X) {
if (horzEdge->OutIdx >= 0 && !IsOpen)
AddOutPt(horzEdge, IntPoint(*maxIt, horzEdge->Bot.Y));
maxIt++;
++maxIt;
}
} else {
while (maxRit != m_Maxima.rend() && *maxRit > e->Curr.X) {
if (horzEdge->OutIdx >= 0 && !IsOpen)
AddOutPt(horzEdge, IntPoint(*maxRit, horzEdge->Bot.Y));
maxRit++;
++maxRit;
}
}
};
......
......@@ -21,10 +21,10 @@ std::vector<std::string> OCRConfig::split(const std::string &str,
std::vector<std::string> res;
if ("" == str)
return res;
char *strs = new char[str.length() + 1];
char strs[str.length() + 1];
std::strcpy(strs, str.c_str());
char *d = new char[delim.length() + 1];
char d[delim.length() + 1];
std::strcpy(d, delim.c_str());
char *p = std::strtok(strs, d);
......@@ -61,4 +61,4 @@ void OCRConfig::PrintConfigInfo() {
std::cout << "=======End of Paddle OCR inference config======" << std::endl;
}
} // namespace PaddleOCR
\ No newline at end of file
} // namespace PaddleOCR
......@@ -29,7 +29,8 @@ deploy/hubserving/ocr_system/
### 1. 准备环境
```shell
# 安装paddlehub
pip3 install paddlehub==1.8.3 --upgrade -i https://pypi.tuna.tsinghua.edu.cn/simple
# paddlehub 需要 python>3.6.2
pip3 install paddlehub==2.1.0 --upgrade -i https://pypi.tuna.tsinghua.edu.cn/simple
```
### 2. 下载推理模型
......
......@@ -30,7 +30,8 @@ The following steps take the 2-stage series service as an example. If only the d
### 1. Prepare the environment
```shell
# Install paddlehub
pip3 install paddlehub==1.8.3 --upgrade -i https://pypi.tuna.tsinghua.edu.cn/simple
# python>3.6.2 is required bt paddlehub
pip3 install paddlehub==2.1.0 --upgrade -i https://pypi.tuna.tsinghua.edu.cn/simple
```
### 2. Download inference model
......
......@@ -101,7 +101,7 @@ def main():
quanter = QAT(config=quant_config)
quanter.quantize(model)
init_model(config, model, logger)
init_model(config, model)
model.eval()
# build metric
......@@ -113,7 +113,7 @@ def main():
use_srn = config['Architecture']['algorithm'] == "SRN"
model_type = config['Architecture']['model_type']
# start eval
metirc = program.eval(model, valid_dataloader, post_process_class,
metric = program.eval(model, valid_dataloader, post_process_class,
eval_class, model_type, use_srn)
logger.info('metric eval ***************')
......
......@@ -18,9 +18,9 @@ PaddleOCR 也提供了数据格式转换脚本,可以将官网 label 转换支
```
# 将官网下载的标签文件转换为 train_icdar2015_label.txt
python gen_label.py --mode="det" --root_path="icdar_c4_train_imgs/" \
--input_path="ch4_training_localization_transcription_gt" \
--output_label="train_icdar2015_label.txt"
python gen_label.py --mode="det" --root_path="/path/to/icdar_c4_train_imgs/" \
--input_path="/path/to/ch4_training_localization_transcription_gt" \
--output_label="/path/to/train_icdar2015_label.txt"
```
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:
......
......@@ -147,12 +147,12 @@ python3 tools/infer/predict_det.py --image_dir="./doc/imgs/00018069.jpg" --det_m
如果输入图片的分辨率比较大,而且想使用更大的分辨率预测,可以设置det_limit_side_len 为想要的值,比如1216:
```
python3 tools/infer/predict_det.py --image_dir="./doc/imgs/2.jpg" --det_model_dir="./inference/det_db/" --det_limit_type=max --det_limit_side_len=1216
python3 tools/infer/predict_det.py --image_dir="./doc/imgs/1.jpg" --det_model_dir="./inference/det_db/" --det_limit_type=max --det_limit_side_len=1216
```
如果想使用CPU进行预测,执行命令如下
```
python3 tools/infer/predict_det.py --image_dir="./doc/imgs/2.jpg" --det_model_dir="./inference/det_db/" --use_gpu=False
python3 tools/infer/predict_det.py --image_dir="./doc/imgs/1.jpg" --det_model_dir="./inference/det_db/" --use_gpu=False
```
<a name="DB文本检测模型推理"></a>
......@@ -221,7 +221,7 @@ python3 tools/export_model.py -c configs/det/det_r50_vd_sast_totaltext.yml -o Gl
```
**SAST文本检测模型推理,需要设置参数`--det_algorithm="SAST"`,同时,还需要增加参数`--det_sast_polygon=True`,**可以执行如下命令:
SAST文本检测模型推理,需要设置参数`--det_algorithm="SAST"`,同时,还需要增加参数`--det_sast_polygon=True`,可以执行如下命令:
```
python3 tools/infer/predict_det.py --det_algorithm="SAST" --image_dir="./doc/imgs_en/img623.jpg" --det_model_dir="./inference/det_sast_tt/" --det_sast_polygon=True
```
......
......@@ -330,6 +330,8 @@ PaddleOCR目前已支持80种(除中文外)语种识别,`configs/rec/multi
```
意大利文由拉丁字母组成,因此执行完命令后会得到名为 rec_latin_lite_train.yml 的配置文件。
2. 手动修改配置文件
您也可以手动修改模版中的以下几个字段:
......@@ -375,7 +377,9 @@ PaddleOCR目前已支持80种(除中文外)语种识别,`configs/rec/multi
更多支持语种请参考: [多语言模型](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.1/doc/doc_ch/multi_languages.md#%E8%AF%AD%E7%A7%8D%E7%BC%A9%E5%86%99)
多语言模型训练方式与中文模型一致,训练数据集均为100w的合成数据,少量的字体可以在 [百度网盘](https://pan.baidu.com/s/1bS_u207Rm7YbY33wOECKDA) 上下载,提取码:frgi。
多语言模型训练方式与中文模型一致,训练数据集均为100w的合成数据,少量的字体可以通过下面两种方式下载。
* [百度网盘](https://pan.baidu.com/s/1bS_u207Rm7YbY33wOECKDA)。提取码:frgi。
* [google drive](https://drive.google.com/file/d/18cSWX7wXSy4G0tbKJ0d9PuIaiwRLHpjA/view)
如您希望在现有模型效果的基础上调优,请参考下列说明修改配置文件:
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment