mirrors
/
PaddleOCR
mirror of https://github.com/PaddlePaddle/PaddleOCR.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Merge remote-tracking branch 'origin/dygraph' into dygraph

pull/3488/head
Leif 2021-07-28 20:14:34 +08:00
parent 45391ef080 75aa6f2f10
commit cb2195e319
27 changed files with 11310 additions and 11193 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
PPOCRLabel/PPOCRLabel.py
View File

@ -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)

22243
PPOCRLabel/libs/resources.py
View File

File diff suppressed because it is too large Load Diff

55
PPOCRLabel/libs/utils.py
View File

@ -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

1
PPOCRLabel/resources/strings/strings-zh-CN.properties
View 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

1
PPOCRLabel/resources/strings/strings.properties
View File

@ -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

1
deploy/cpp_infer/CMakeLists.txt
View File

@ -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

2
deploy/cpp_infer/docs/windows_vs2019_build.md
View File

@ -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。

3
deploy/cpp_infer/readme.md
View File

@ -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。

1
deploy/cpp_infer/readme_en.md
View File

@ -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
```

22
deploy/cpp_infer/src/clipper.cpp
View File

@ -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;
}
}
};

6
deploy/cpp_infer/src/config.cpp
View File

@ -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
} // namespace PaddleOCR

1
deploy/hubserving/readme.md
View File

@ -29,6 +29,7 @@ deploy/hubserving/ocr_system/
### 1. 准备环境
```shell
# 安装paddlehub
# paddlehub 需要 python>3.6.2
pip3 install paddlehub==2.1.0 --upgrade -i https://pypi.tuna.tsinghua.edu.cn/simple
```

1
deploy/hubserving/readme_en.md
View File

@ -30,6 +30,7 @@ The following steps take the 2-stage series service as an example. If only the d
### 1. Prepare the environment
```shell
# Install paddlehub
# python>3.6.2 is required bt paddlehub
pip3 install paddlehub==2.1.0 --upgrade -i https://pypi.tuna.tsinghua.edu.cn/simple
```

6
doc/doc_ch/detection.md
View File

@ -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：

6
doc/doc_ch/inference.md
View File

@ -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
```

2
doc/doc_ch/recognition.md
View File

@ -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:

6
doc/doc_en/inference_en.md
View File

@ -154,12 +154,12 @@ Set as `limit_type='min', det_limit_side_len=960`, it means that the shortest si
If the resolution of the input picture is relatively large and you want to use a larger resolution prediction, you can set det_limit_side_len to the desired value, such as 1216:
```
python3 tools/infer/predict_det.py --image_dir="./doc/imgs/22.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
```
If you want to use the CPU for prediction, execute the command as follows
```
python3 tools/infer/predict_det.py --image_dir="./doc/imgs/22.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_DETECTION"></a>
@ -230,7 +230,7 @@ First, convert the model saved in the SAST text detection training process into
python3 tools/export_model.py -c configs/det/det_r50_vd_sast_totaltext.yml -o Global.pretrained_model=./det_r50_vd_sast_totaltext_v2.0_train/best_accuracy Global.save_inference_dir=./inference/det_sast_tt
```
**For SAST curved text detection model inference, you need to set the parameter `--det_algorithm="SAST"` and `--det_sast_polygon=True`**, run the following command:
For SAST curved text detection model inference, you need to set the parameter `--det_algorithm="SAST"` and `--det_sast_polygon=True`, run the following command:
```
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

1
doc/doc_en/recognition_en.md
View File

@ -329,6 +329,7 @@ There are two ways to create the required configuration file:：
...
```
Italian is made up of Latin letters, so after executing the command, you will get the rec_latin_lite_train.yml.
2. Manually modify the configuration file

2
doc/doc_en/update_en.md
View File

@ -15,8 +15,6 @@
- 2020.6.8 Add [datasets](./datasets_en.md) and keep updating
- 2020.6.5 Support exporting `attention` model to `inference_model`
- 2020.6.5 Support separate prediction and recognition, output result score
- 2020.6.5 Support exporting `attention` model to `inference_model`
- 2020.6.5 Support separate prediction and recognition, output result score
- 2020.5.30 Provide Lightweight Chinese OCR online experience
- 2020.5.30 Model prediction and training support on Windows system
- 2020.5.30 Open source general Chinese OCR model

8
ppocr/data/simple_dataset.py
View File

@ -14,7 +14,6 @@
import numpy as np
import os
import random
import traceback
from paddle.io import Dataset
from .imaug import transform, create_operators
@ -105,7 +104,7 @@ class SimpleDataSet(Dataset):
data_line = self.data_lines[file_idx]
try:
data_line = data_line.decode('utf-8')
substr = data_line.strip("\n").strip("\r").split(self.delimiter)
substr = data_line.strip("\n").split(self.delimiter)
file_name = substr[0]
label = substr[1]
img_path = os.path.join(self.data_dir, file_name)
@ -117,11 +116,10 @@ class SimpleDataSet(Dataset):
data['image'] = img
data['ext_data'] = self.get_ext_data()
outs = transform(data, self.ops)
except:
error_meg = traceback.format_exc()
except Exception as e:
self.logger.error(
"When parsing line {}, error happened with msg: {}".format(
data_line, error_meg))
data_line, e))
outs = None
if outs is None:
# during evaluation, we should fix the idx to get same results for many times of evaluation.

2
ppocr/modeling/architectures/distillation_model.py
View File

@ -46,7 +46,7 @@ class DistillationModel(nn.Layer):
pretrained = model_config.pop("pretrained")
model = BaseModel(model_config)
if pretrained is not None:
model = load_pretrained_params(model, pretrained)
load_pretrained_params(model, pretrained)
if freeze_params:
for param in model.parameters():
param.trainable = False

22
ppocr/utils/gen_label.py
View File

@ -1,16 +1,16 @@
#copyright (c) 2020 PaddlePaddle Authors. All Rights Reserve.
# copyright (c) 2020 PaddlePaddle Authors. All Rights Reserve.
#
#Licensed under the Apache License, Version 2.0 (the "License");
#you may not use this file except in compliance with the License.
#You may obtain a copy of the License at
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
#Unless required by applicable law or agreed to in writing, software
#distributed under the License is distributed on an "AS IS" BASIS,
#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.
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# 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 os
import argparse
import json
@ -31,7 +31,9 @@ def gen_det_label(root_path, input_dir, out_label):
for label_file in os.listdir(input_dir):
img_path = root_path + label_file[3:-4] + ".jpg"
label = []
with open(os.path.join(input_dir, label_file), 'r') as f:
with open(
os.path.join(input_dir, label_file), 'r',
encoding='utf-8-sig') as f:
for line in f.readlines():
tmp = line.strip("\n\r").replace("\xef\xbb\xbf",
"").split(',')

35
test/ocr_rec_params.txt 100644
View File

@ -0,0 +1,35 @@
model_name:ocr_rec
python:python
gpu_list:0|0,1
Global.auto_cast:null
Global.epoch_num:10
Global.save_model_dir:./output/
Train.loader.batch_size_per_card:
Global.use_gpu:
Global.pretrained_model:null
trainer:norm|pact
norm_train:tools/train.py -c configs/rec/rec_mv3_none_bilstm_ctc.yml
quant_train:deploy/slim/quantization/quant.py -c configs/rec/rec_mv3_none_bilstm_ctc.yml
fpgm_train:null
distill_train:null
eval:tools/eval.py -c configs/rec/rec_mv3_none_bilstm_ctc.yml -o
Global.save_inference_dir:./output/
Global.pretrained_model:
norm_export:tools/export_model.py -c configs/rec/rec_mv3_none_bilstm_ctc.yml -o
quant_export:deploy/slim/quantization/export_model.py -c configs/rec/rec_mv3_none_bilstm_ctc.yml -o
fpgm_export:null
distill_export:null
inference:tools/infer/predict_rec.py
--use_gpu:True|False
--enable_mkldnn:True|False
--cpu_threads:1|6
--rec_batch_num:1
--use_tensorrt:True|False
--precision:fp32|fp16|int8
--rec_model_dir:./inference/ch_ppocr_mobile_v2.0_rec_infer/
--image_dir:./inference/rec_inference
--save_log_path:./test/output/

30
test/prepare.sh
View File

@ -29,19 +29,21 @@ train_model_list=$(func_parser_value "${lines[0]}")
trainer_list=$(func_parser_value "${lines[10]}")
# MODE be one of ['lite_train_infer' 'whole_infer' 'whole_train_infer']
MODE=$2
# prepare pretrained weights and dataset
wget -nc -P ./pretrain_models/ https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/MobileNetV3_large_x0_5_pretrained.pdparams
wget -nc -P ./pretrain_models/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_mv3_db_v2.0_train.tar
cd pretrain_models && tar xf det_mv3_db_v2.0_train.tar && cd ../
# prepare pretrained weights and dataset
if [ ${train_model_list[*]} = "ocr_det" ]; then
wget -nc -P ./pretrain_models/ https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/MobileNetV3_large_x0_5_pretrained.pdparams
wget -nc -P ./pretrain_models/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_mv3_db_v2.0_train.tar
cd pretrain_models && tar xf det_mv3_db_v2.0_train.tar && cd ../
fi
if [ ${MODE} = "lite_train_infer" ];then
# pretrain lite train data
rm -rf ./train_data/icdar2015
wget -nc -P ./train_data/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/icdar2015_lite.tar
cd ./train_data/ && tar xf icdar2015_lite.tar
wget -nc -P ./train_data/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/ic15_data.tar # todo change to bcebos
cd ./train_data/ && tar xf icdar2015_lite.tar && tar xf ic15_data.tar
ln -s ./icdar2015_lite ./icdar2015
cd ../
epoch=10
@ -49,13 +51,15 @@ if [ ${MODE} = "lite_train_infer" ];then
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 ../
wget -nc -P ./train_data/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/ic15_data.tar
cd ./train_data/ && tar xf icdar2015.tar && tar xf ic15_data.tar && cd ../
epoch=500
eval_batch_step=200
elif [ ${MODE} = "whole_infer" ];then
rm -rf ./train_data/icdar2015
wget -nc -P ./train_data/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/icdar2015_infer.tar
cd ./train_data/ && tar xf icdar2015_infer.tar
wget -nc -P ./train_data/ https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/ic15_data.tar
cd ./train_data/ && tar xf icdar2015_infer.tar && tar xf ic15_data.tar
ln -s ./icdar2015_infer ./icdar2015
cd ../
epoch=10
@ -88,9 +92,11 @@ for train_model in ${train_model_list[*]}; do
elif [ ${train_model} = "ocr_rec" ];then
model_name="ocr_rec"
yml_file="configs/rec/rec_mv3_none_bilstm_ctc.yml"
wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/ch_rec_data_200.tar
cd ./inference && tar xf ch_rec_data_200.tar && cd ../
img_dir="./inference/ch_rec_data_200/"
wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/rec_inference.tar
cd ./inference && tar xf rec_inference.tar && cd ../
img_dir="./inference/rec_inference/"
data_dir=./inference/rec_inference
data_label_file=[./inference/rec_inference/rec_gt_test.txt]
fi
# eval

2
tools/infer/predict_cls.py
View File

@ -112,7 +112,6 @@ class TextClassifier(object):
if '180' in label and score > self.cls_thresh:
img_list[indices[beg_img_no + rno]] = cv2.rotate(
img_list[indices[beg_img_no + rno]], 1)
elapse = time.time() - starttime
return img_list, cls_res, elapse
@ -146,7 +145,6 @@ def main(args):
cls_res[ino]))
logger.info(
"The predict time about text angle classify module is as follows: ")
text_classifier.cls_times.info(average=False)
if __name__ == "__main__":

34
tools/infer/predict_rec.py
View File

@ -64,6 +64,24 @@ class TextRecognizer(object):
self.postprocess_op = build_post_process(postprocess_params)
self.predictor, self.input_tensor, self.output_tensors, self.config = \
utility.create_predictor(args, 'rec', logger)
self.benchmark = args.benchmark
if args.benchmark:
import auto_log
pid = os.getpid()
self.autolog = auto_log.AutoLogger(
model_name="rec",
model_precision=args.precision,
batch_size=args.rec_batch_num,
data_shape="dynamic",
save_path=args.save_log_path,
inference_config=self.config,
pids=pid,
process_name=None,
gpu_ids=0 if args.use_gpu else None,
time_keys=[
'preprocess_time', 'inference_time', 'postprocess_time'
],
warmup=10)
def resize_norm_img(self, img, max_wh_ratio):
imgC, imgH, imgW = self.rec_image_shape
@ -168,6 +186,8 @@ class TextRecognizer(object):
rec_res = [['', 0.0]] * img_num
batch_num = self.rec_batch_num
st = time.time()
if self.benchmark:
self.autolog.times.start()
for beg_img_no in range(0, img_num, batch_num):
end_img_no = min(img_num, beg_img_no + batch_num)
norm_img_batch = []
@ -196,6 +216,8 @@ class TextRecognizer(object):
norm_img_batch.append(norm_img[0])
norm_img_batch = np.concatenate(norm_img_batch)
norm_img_batch = norm_img_batch.copy()
if self.benchmark:
self.autolog.times.stamp()
if self.rec_algorithm == "SRN":
encoder_word_pos_list = np.concatenate(encoder_word_pos_list)
@ -222,6 +244,8 @@ class TextRecognizer(object):
for output_tensor in self.output_tensors:
output = output_tensor.copy_to_cpu()
outputs.append(output)
if self.benchmark:
self.autolog.times.stamp()
preds = {"predict": outputs[2]}
else:
self.input_tensor.copy_from_cpu(norm_img_batch)
@ -231,11 +255,14 @@ class TextRecognizer(object):
for output_tensor in self.output_tensors:
output = output_tensor.copy_to_cpu()
outputs.append(output)
if self.benchmark:
self.autolog.times.stamp()
preds = outputs[0]
rec_result = self.postprocess_op(preds)
for rno in range(len(rec_result)):
rec_res[indices[beg_img_no + rno]] = rec_result[rno]
if self.benchmark:
self.autolog.times.end(stamp=True)
return rec_res, time.time() - st
@ -251,9 +278,6 @@ def main(args):
for i in range(10):
res = text_recognizer([img])
cpu_mem, gpu_mem, gpu_util = 0, 0, 0
count = 0
for image_file in image_file_list:
img, flag = check_and_read_gif(image_file)
if not flag:
@ -273,6 +297,8 @@ def main(args):
for ino in range(len(img_list)):
logger.info("Predicts of {}:{}".format(valid_image_file_list[ino],
rec_res[ino]))
if args.benchmark:
text_recognizer.autolog.report()
if __name__ == "__main__":

3
tools/infer/utility.py
View File

@ -24,9 +24,6 @@ from paddle import inference
import time
from ppocr.utils.logging import get_logger
logger = get_logger()
def str2bool(v):
return v.lower() in ("true", "t", "1")