Skip to content

GitLab

"mmdet3d/models/vscode:/vscode.git/clone" did not exist on "8fb2cf6c3773977a3a1f473c43b065afc0181b48"
Commit 6c7ff9c7 authored by LDOUBLEV's avatar LDOUBLEV
Browse files

fix conflict

parents ac91a9e1 9b8f587e
Hide whitespace changes
Inline Side-by-side
Showing with 12071 additions and 11182 deletions
MANIFEST.in
View file @ 6c7ff9c7
include LICENSE.txt
include LICENSE
include README.md
recursive-include ppocr/utils *.txt utility.py logging.py
recursive-include ppocr/data/ *.py
recursive-include ppocr/utils *.txt utility.py logging.py network.py
recursive-include ppocr/data *.py
recursive-include ppocr/postprocess *.py
recursive-include tools/infer *.py
recursive-include ppocr/utils/e2e_utils/ *.py
\ No newline at end of file
recursive-include ppocr/utils/e2e_utils *.py
recursive-include ppstructure *.py
\ No newline at end of file
PPOCRLabel/PPOCRLabel.py
View file @ 6c7ff9c7
......@@ -92,7 +92,7 @@ class WindowMixin(object):
class MainWindow(QMainWindow, WindowMixin):
FIT_WINDOW, FIT_WIDTH, MANUAL_ZOOM = list(range(3))
def __init__(self, lang="ch", defaultFilename=None, defaultPrefdefClassFile=None, defaultSaveDir=None):
def __init__(self, lang="ch", gpu=False, defaultFilename=None, defaultPrefdefClassFile=None, defaultSaveDir=None):
super(MainWindow, self).__init__()
self.setWindowTitle(__appname__)
......@@ -108,7 +108,7 @@ class MainWindow(QMainWindow, WindowMixin):
getStr = lambda strId: self.stringBundle.getString(strId)
self.defaultSaveDir = defaultSaveDir
self.ocr = PaddleOCR(use_pdserving=False, use_angle_cls=True, det=True, cls=True, use_gpu=False, lang=lang)
self.ocr = PaddleOCR(use_pdserving=False, use_angle_cls=True, det=True, cls=True, use_gpu=gpu, lang=lang)
if os.path.exists('./data/paddle.png'):
result = self.ocr.ocr('./data/paddle.png', cls=True, det=True)
......@@ -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)
......@@ -1239,6 +1244,8 @@ class MainWindow(QMainWindow, WindowMixin):
def loadFile(self, filePath=None):
"""Load the specified file, or the last opened file if None."""
if self.dirty:
self.mayContinue()
self.resetState()
self.canvas.setEnabled(False)
if filePath is None:
......@@ -2037,6 +2044,8 @@ def read(filename, default=None):
except:
return default
def str2bool(v):
return v.lower() in ("true", "t", "1")
def get_main_app(argv=[]):
"""
......@@ -2048,13 +2057,14 @@ def get_main_app(argv=[]):
app.setWindowIcon(newIcon("app"))
# Tzutalin 201705+: Accept extra agruments to change predefined class file
argparser = argparse.ArgumentParser()
argparser.add_argument("--lang", default='en', nargs="?")
argparser.add_argument("--lang", type=str, default='en', nargs="?")
argparser.add_argument("--gpu", type=str2bool, default=False, nargs="?")
argparser.add_argument("--predefined_classes_file",
default=os.path.join(os.path.dirname(__file__), "data", "predefined_classes.txt"),
nargs="?")
args = argparser.parse_args(argv[1:])
# Usage : labelImg.py image predefClassFile saveDir
win = MainWindow(lang=args.lang,
win = MainWindow(lang=args.lang, gpu=args.gpu,
defaultPrefdefClassFile=args.predefined_classes_file)
win.show()
return app, win
......
PPOCRLabel/libs/resources.py
View file @ 6c7ff9c7
This source diff could not be displayed because it is too large. You can view the blob instead.
PPOCRLabel/libs/utils.py
View file @ 6c7ff9c7
......@@ -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
PPOCRLabel/resources/strings/strings-zh-CN.properties
View file @ 6c7ff9c7
......@@ -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
......
PPOCRLabel/resources/strings/strings.properties
View file @ 6c7ff9c7
......@@ -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
......
StyleText/engine/text_drawers.py
View file @ 6c7ff9c7
......@@ -66,6 +66,7 @@ class StdTextDrawer(object):
corpus_list.append(corpus[0:i])
text_input_list.append(text_input)
corpus = corpus[i:]
i = 0
break
draw.text((char_x, 2), char_i, fill=(0, 0, 0), font=font)
char_x += char_size
......@@ -78,7 +79,6 @@ class StdTextDrawer(object):
corpus_list.append(corpus[0:i])
text_input_list.append(text_input)
corpus = corpus[i:]
break
return corpus_list, text_input_list
__init__.py
View file @ 6c7ff9c7
......@@ -11,7 +11,8 @@
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import paddleocr
from .paddleocr import *
__all__ = ['PaddleOCR', 'draw_ocr']
from .paddleocr import PaddleOCR
from .tools.infer.utility import draw_ocr
__version__ = paddleocr.VERSION
__all__ = ['PaddleOCR', 'PPStructure', 'draw_ocr', 'draw_structure_result', 'save_structure_res','download_with_progressbar']
configs/det/ch_ppocr_v2.1/ch_det_lite_train_cml_v2.1.yml 0 → 100644
View file @ 6c7ff9c7
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
configs/det/ch_ppocr_v2.1/ch_det_lite_train_distill_v2.1.yml 0 → 100644
View file @ 6c7ff9c7
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
configs/det/ch_ppocr_v2.1/ch_det_lite_train_dml_v2.1.yml 0 → 100644
View file @ 6c7ff9c7
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
configs/rec/ch_ppocr_v2.1/rec_chinese_lite_train_distillation_v2.1.yml 0 → 100644
View file @ 6c7ff9c7
Global:
debug: false
use_gpu: true
epoch_num: 800
log_smooth_window: 20
print_batch_step: 10
save_model_dir: ./output/rec_chinese_lite_distillation_v2.1
save_epoch_step: 3
eval_batch_step: [0, 2000]
cal_metric_during_train: true
pretrained_model:
checkpoints:
save_inference_dir:
use_visualdl: false
infer_img: doc/imgs_words/ch/word_1.jpg
character_dict_path: ppocr/utils/ppocr_keys_v1.txt
character_type: ch
max_text_length: 25
infer_mode: false
use_space_char: true
distributed: true
save_res_path: ./output/rec/predicts_chinese_lite_distillation_v2.1.txt
Optimizer:
name: Adam
beta1: 0.9
beta2: 0.999
lr:
name: Piecewise
decay_epochs : [700, 800]
values : [0.001, 0.0001]
warmup_epoch: 5
regularizer:
name: L2
factor: 2.0e-05
Architecture:
model_type: &model_type "rec"
name: DistillationModel
algorithm: Distillation
Models:
Teacher:
pretrained:
freeze_params: false
return_all_feats: true
model_type: *model_type
algorithm: CRNN
Transform:
Backbone:
name: MobileNetV1Enhance
scale: 0.5
Neck:
name: SequenceEncoder
encoder_type: rnn
hidden_size: 64
Head:
name: CTCHead
mid_channels: 96
fc_decay: 0.00002
Student:
pretrained:
freeze_params: false
return_all_feats: true
model_type: *model_type
algorithm: CRNN
Transform:
Backbone:
name: MobileNetV1Enhance
scale: 0.5
Neck:
name: SequenceEncoder
encoder_type: rnn
hidden_size: 64
Head:
name: CTCHead
mid_channels: 96
fc_decay: 0.00002
Loss:
name: CombinedLoss
loss_config_list:
- DistillationCTCLoss:
weight: 1.0
model_name_list: ["Student", "Teacher"]
key: head_out
- DistillationDMLLoss:
weight: 1.0
act: "softmax"
model_name_pairs:
- ["Student", "Teacher"]
key: head_out
- DistillationDistanceLoss:
weight: 1.0
mode: "l2"
model_name_pairs:
- ["Student", "Teacher"]
key: backbone_out
PostProcess:
name: DistillationCTCLabelDecode
model_name: ["Student", "Teacher"]
key: head_out
Metric:
name: DistillationMetric
base_metric_name: RecMetric
main_indicator: acc
key: "Student"
Train:
dataset:
name: SimpleDataSet
data_dir: ./train_data/
label_file_list:
- ./train_data/train_list.txt
transforms:
- DecodeImage:
img_mode: BGR
channel_first: false
- RecAug:
- CTCLabelEncode:
- RecResizeImg:
image_shape: [3, 32, 320]
- KeepKeys:
keep_keys:
- image
- label
- length
loader:
shuffle: true
batch_size_per_card: 128
drop_last: true
num_sections: 1
num_workers: 8
Eval:
dataset:
name: SimpleDataSet
data_dir: ./train_data
label_file_list:
- ./train_data/val_list.txt
transforms:
- DecodeImage:
img_mode: BGR
channel_first: false
- CTCLabelEncode:
- RecResizeImg:
image_shape: [3, 32, 320]
- KeepKeys:
keep_keys:
- image
- label
- length
loader:
shuffle: false
drop_last: false
batch_size_per_card: 128
num_workers: 8
configs/table/table_mv3.yml 0 → 100755
View file @ 6c7ff9c7
Global:
use_gpu: true
epoch_num: 50
log_smooth_window: 20
print_batch_step: 5
save_model_dir: ./output/table_mv3/
save_epoch_step: 5
# evaluation is run every 400 iterations after the 0th iteration
eval_batch_step: [0, 400]
cal_metric_during_train: True
pretrained_model:
checkpoints:
save_inference_dir:
use_visualdl: False
infer_img: doc/imgs_words/ch/word_1.jpg
# for data or label process
character_dict_path: ppocr/utils/dict/table_structure_dict.txt
character_type: en
max_text_length: 100
max_elem_length: 500
max_cell_num: 500
infer_mode: False
process_total_num: 0
process_cut_num: 0
Optimizer:
name: Adam
beta1: 0.9
beta2: 0.999
clip_norm: 5.0
lr:
learning_rate: 0.001
regularizer:
name: 'L2'
factor: 0.00000
Architecture:
model_type: table
algorithm: TableAttn
Backbone:
name: MobileNetV3
scale: 1.0
model_name: small
disable_se: True
Head:
name: TableAttentionHead
hidden_size: 256
l2_decay: 0.00001
loc_type: 2
Loss:
name: TableAttentionLoss
structure_weight: 100.0
loc_weight: 10000.0
PostProcess:
name: TableLabelDecode
Metric:
name: TableMetric
main_indicator: acc
Train:
dataset:
name: PubTabDataSet
data_dir: train_data/table/pubtabnet/train/
label_file_path: train_data/table/pubtabnet/PubTabNet_2.0.0_train.jsonl
transforms:
- DecodeImage: # load image
img_mode: BGR
channel_first: False
- ResizeTableImage:
max_len: 488
- TableLabelEncode:
- NormalizeImage:
scale: 1./255.
mean: [0.485, 0.456, 0.406]
std: [0.229, 0.224, 0.225]
order: 'hwc'
- PaddingTableImage:
- ToCHWImage:
- KeepKeys:
keep_keys: ['image', 'structure', 'bbox_list', 'sp_tokens', 'bbox_list_mask']
loader:
shuffle: True
batch_size_per_card: 32
drop_last: True
num_workers: 1
Eval:
dataset:
name: PubTabDataSet
data_dir: train_data/table/pubtabnet/val/
label_file_path: train_data/table/pubtabnet/PubTabNet_2.0.0_val.jsonl
transforms:
- DecodeImage: # load image
img_mode: BGR
channel_first: False
- ResizeTableImage:
max_len: 488
- TableLabelEncode:
- NormalizeImage:
scale: 1./255.
mean: [0.485, 0.456, 0.406]
std: [0.229, 0.224, 0.225]
order: 'hwc'
- PaddingTableImage:
- ToCHWImage:
- KeepKeys:
keep_keys: ['image', 'structure', 'bbox_list', 'sp_tokens', 'bbox_list_mask']
loader:
shuffle: False
drop_last: False
batch_size_per_card: 16
num_workers: 1
deploy/android_demo/app/src/main/java/com/baidu/paddle/lite/demo/ocr/MainActivity.java
View file @ 6c7ff9c7
......@@ -465,8 +465,12 @@ public class MainActivity extends AppCompatActivity {
}
public void btn_load_model_click(View view) {
tvStatus.setText("STATUS: load model ......");
loadModel();
if (predictor.isLoaded()){
tvStatus.setText("STATUS: model has been loaded");
}else{
tvStatus.setText("STATUS: load model ......");
loadModel();
}
}
public void btn_run_model_click(View view) {
......
deploy/android_demo/app/src/main/java/com/baidu/paddle/lite/demo/ocr/Predictor.java
View file @ 6c7ff9c7
......@@ -194,26 +194,25 @@ public class Predictor {
"supported!");
return false;
}
int[] channelStride = new int[]{width * height, width * height * 2};
int p = scaleImage.getPixel(scaleImage.getWidth() - 1, scaleImage.getHeight() - 1);
for (int y = 0; y < height; y++) {
for (int x = 0; x < width; x++) {
int color = scaleImage.getPixel(x, y);
float[] rgb = new float[]{(float) red(color) / 255.0f, (float) green(color) / 255.0f,
(float) blue(color) / 255.0f};
inputData[y * width + x] = (rgb[channelIdx[0]] - inputMean[0]) / inputStd[0];
inputData[y * width + x + channelStride[0]] = (rgb[channelIdx[1]] - inputMean[1]) / inputStd[1];
inputData[y * width + x + channelStride[1]] = (rgb[channelIdx[2]] - inputMean[2]) / inputStd[2];
}
int[] channelStride = new int[]{width * height, width * height * 2};
int[] pixels=new int[width*height];
scaleImage.getPixels(pixels,0,scaleImage.getWidth(),0,0,scaleImage.getWidth(),scaleImage.getHeight());
for (int i = 0; i < pixels.length; i++) {
int color = pixels[i];
float[] rgb = new float[]{(float) red(color) / 255.0f, (float) green(color) / 255.0f,
(float) blue(color) / 255.0f};
inputData[i] = (rgb[channelIdx[0]] - inputMean[0]) / inputStd[0];
inputData[i + channelStride[0]] = (rgb[channelIdx[1]] - inputMean[1]) / inputStd[1];
inputData[i+ channelStride[1]] = (rgb[channelIdx[2]] - inputMean[2]) / inputStd[2];
}
} else if (channels == 1) {
for (int y = 0; y < height; y++) {
for (int x = 0; x < width; x++) {
int color = inputImage.getPixel(x, y);
float gray = (float) (red(color) + green(color) + blue(color)) / 3.0f / 255.0f;
inputData[y * width + x] = (gray - inputMean[0]) / inputStd[0];
}
int[] pixels=new int[width*height];
scaleImage.getPixels(pixels,0,scaleImage.getWidth(),0,0,scaleImage.getWidth(),scaleImage.getHeight());
for (int i = 0; i < pixels.length; i++) {
int color = pixels[i];
float gray = (float) (red(color) + green(color) + blue(color)) / 3.0f / 255.0f;
inputData[i] = (gray - inputMean[0]) / inputStd[0];
}
} else {
Log.i(TAG, "Unsupported channel size " + Integer.toString(channels) + ", only channel 1 and 3 is " +
......
deploy/cpp_infer/CMakeLists.txt
View file @ 6c7ff9c7
......@@ -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
......
deploy/cpp_infer/docs/windows_vs2019_build.md
View file @ 6c7ff9c7
......@@ -14,7 +14,7 @@ PaddleOCR在Windows 平台下基于`Visual Studio 2019 Community` 进行了测
### Step1: 下载PaddlePaddle C++ 预测库 fluid_inference
PaddlePaddle C++ 预测库针对不同的`CPU`和`CUDA`版本提供了不同的预编译版本，请根据实际情况下载: [C++预测库下载列表](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/guides/05_inference_deployment/inference/windows_cpp_inference.html)
PaddlePaddle C++ 预测库针对不同的`CPU`和`CUDA`版本提供了不同的预编译版本，请根据实际情况下载: [C++预测库下载列表](https://paddleinference.paddlepaddle.org.cn/user_guides/download_lib.html#windows)
解压后`D:\projects\fluid_inference`目录包含内容为：
```
......@@ -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。
deploy/cpp_infer/readme.md
View file @ 6c7ff9c7
......@@ -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
```
......@@ -141,11 +142,11 @@ build/paddle_inference_install_dir/
```
inference/
|-- det_db
| |--inference.pdparams
| |--inference.pdimodel
| |--inference.pdiparams
| |--inference.pdmodel
|-- rec_rcnn
| |--inference.pdparams
| |--inference.pdparams
| |--inference.pdiparams
| |--inference.pdmodel
```
......@@ -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。
......
deploy/cpp_infer/readme_en.md
View file @ 6c7ff9c7
......@@ -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
```
......@@ -144,11 +145,11 @@ Among them, `paddle` is the Paddle library required for C++ prediction later, an
```
inference/
|-- det_db
| |--inference.pdparams
| |--inference.pdimodel
| |--inference.pdiparams
| |--inference.pdmodel
|-- rec_rcnn
| |--inference.pdparams
| |--inference.pdparams
| |--inference.pdiparams
| |--inference.pdmodel
```
......
deploy/cpp_infer/src/clipper.cpp
View file @ 6c7ff9c7
......@@ -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;
}
}
};
......
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