Skip to content

GitLab

"git@developer.sourcefind.cn:gaoqiong/migraphx.git" did not exist on "5a62e9e7661af7d132be01216420265cb8c8380a"
Unverified Commit 4ae91cb4 authored by Wei-JL's avatar Wei-JL Committed by GitHub
Browse files

Merge branch 'PaddlePaddle:dygraph' into dygraph

parents 5ce3af84 9b8f587e
Show whitespace changes
Inline Side-by-side
Showing with 1145 additions and 834 deletions
ppstructure/layout/README.md
View file @ 4ae91cb4
# 版面分析使用说明
English | [简体中文](README_ch.md)
* [1. 安装whl包](#安装whl包)
* [2. 使用](#使用)
* [3. 后处理](#后处理)
* [4. 指标](#指标)
* [5. 训练版面分析模型](#训练版面分析模型)
<a name="安装whl包"></a>
# Getting Started
## 1. 安装whl包
[1. Install whl package](#Install)
[2. Quick Start](#QuickStart)
[3. PostProcess](#PostProcess)
[4. Results](#Results)
[5. Training](#Training)
<a name="Install"></a>
## 1. Install whl package
```bash
wget https://paddleocr.bj.bcebos.com/whl/layoutparser-0.0.0-py3-none-any.whl
pip install -U layoutparser-0.0.0-py3-none-any.whl
```
<a name="使用"></a>
<a name="QuickStart"></a>
## 2. 使用
## 2. Quick Start
使用layoutparser识别给定文档的布局：
Use LayoutParser to identify the layout of a document:
```python
import cv2
import layoutparser as lp
image = cv2.imread("imags/paper-image.jpg")
image = cv2.imread("doc/table/layout.jpg")
image = image[..., ::-1]
# 加载模型
# load model
model = lp.PaddleDetectionLayoutModel(config_path="lp://PubLayNet/ppyolov2_r50vd_dcn_365e_publaynet/config",
threshold=0.5,
label_map={0: "Text", 1: "Title", 2: "List", 3:"Table", 4:"Figure"},
enforce_cpu=False,
enable_mkldnn=True)
# 检测
# detect
layout = model.detect(image)
# 显示结果
lp.draw_box(image, layout, box_width=3, show_element_type=True)
# show result
show_img = lp.draw_box(image, layout, box_width=3, show_element_type=True)
show_img.show()
```
下图展示了结果，不同颜色的检测框表示不同的类别，并通过`show_element_type`在框的左上角显示具体类别：
The following figure shows the result, with different colored detection boxes representing different categories and displaying specific categories in the upper left corner of the box with `show_element_type`
<div align="center">
<img src="../../doc/table/result_all.jpg" width = "600" />
</div>
`PaddleDetectionLayoutModel`函数参数说明如下:
| 参数 | 含义 | 默认值 | 备注 |
| :------------: | :-------------------------: | :---------: | :----------------------------------------------------------: |
| config_path | 模型配置路径 | None | 指定config_path会自动下载模型(仅第一次，之后模型存在，不会再下载) |
| model_path | 模型路径 | None | 本地模型路径，config_path和model_path必须设置一个，不能同时为None |
| threshold | 预测得分的阈值 | 0.5 | \ |
| input_shape | reshape之后图片尺寸 | [3,640,640] | \ |
| batch_size | 测试batch size | 1 | \ |
| label_map | 类别映射表 | None | 设置config_path时，可以为None，根据数据集名称自动获取label_map |
| enforce_cpu | 代码是否使用CPU运行 | False | 设置为False表示使用GPU，True表示强制使用CPU |
| enforce_mkldnn | CPU预测中是否开启MKLDNN加速 | True | \ |
| thread_num | 设置CPU线程数 | 10 | \ |
目前支持以下几种模型配置和label map，您可以通过修改 `--config_path`和 `--label_map`使用这些模型，从而检测不同类型的内容：
`PaddleDetectionLayoutModel`parameters are described as follows:
| parameter | description | default | remark |
| :------------: | :------------------------------------------------------: | :---------: | :----------------------------------------------------------: |
| config_path | model config path | None | Specify config_ path will automatically download the model (only for the first time,the model will exist and will not be downloaded again) |
| model_path | model path | None | local model path, config_ path and model_ path must be set to one, cannot be none at the same time |
| threshold | threshold of prediction score | 0.5 | \ |
| input_shape | picture size of reshape | [3,640,640] | \ |
| batch_size | testing batch size | 1 | \ |
| label_map | category mapping table | None | Setting config_ path, it can be none, and the label is automatically obtained according to the dataset name_ map |
| enforce_cpu | whether to use CPU | False | False to use GPU, and True to force the use of CPU |
| enforce_mkldnn | whether mkldnn acceleration is enabled in CPU prediction | True | \ |
| thread_num | the number of CPU threads | 10 | \ |
The following model configurations and label maps are currently supported, which you can use by modifying '--config_path' and '--label_map' to detect different types of content:
| dataset | config_path | label_map |
| ------------------------------------------------------------ | ------------------------------------------------------------ | --------------------------------------------------------- |
......@@ -66,25 +74,26 @@ lp.draw_box(image, layout, box_width=3, show_element_type=True)
| TableBank latex | lp://TableBank/ppyolov2_r50vd_dcn_365e_tableBank_latex/config | {0:"Table"} |
| [PubLayNet](https://github.com/ibm-aur-nlp/PubLayNet) | lp://PubLayNet/ppyolov2_r50vd_dcn_365e_publaynet/config | {0: "Text", 1: "Title", 2: "List", 3:"Table", 4:"Figure"} |
* TableBank word和TableBank latex分别在word文档、latex文档数据集训练；
* 下载TableBank数据集同时包含word和latex。
* TableBank word and TableBank latex are trained on datasets of word documents and latex documents respectively;
* Download TableBank dataset contains both word and latex。
<a name="后处理"></a>
<a name="PostProcess"></a>
## 3. 后处理
## 3. PostProcess
版面分析检测包含多个类别，如果只想获取指定类别(如"Text"类别)的检测框、可以使用下述代码：
Layout parser contains multiple categories, if you only want to get the detection box for a specific category (such as the "Text" category), you can use the following code:
```python
# 首先过滤特定文本类型的区域
# follow the above code
# filter areas for a specific text type
text_blocks = lp.Layout([b for b in layout if b.type=='Text'])
figure_blocks = lp.Layout([b for b in layout if b.type=='Figure'])
# 因为在图像区域内可能检测到文本区域，所以只需要删除它们
# text areas may be detected within the image area, delete these areas
text_blocks = lp.Layout([b for b in text_blocks \
if not any(b.is_in(b_fig) for b_fig in figure_blocks)])
# 对文本区域排序并分配id
# sort text areas and assign ID
h, w = image.shape[:2]
left_interval = lp.Interval(0, w/2*1.05, axis='x').put_on_canvas(image)
......@@ -95,24 +104,24 @@ left_blocks.sort(key = lambda b:b.coordinates[1])
right_blocks = [b for b in text_blocks if b not in left_blocks]
right_blocks.sort(key = lambda b:b.coordinates[1])
# 最终合并两个列表，并按顺序添加索引
# the two lists are merged and the indexes are added in order
text_blocks = lp.Layout([b.set(id = idx) for idx, b in enumerate(left_blocks + right_blocks)])
# 显示结果
lp.draw_box(image, text_blocks,
# display result
show_img = lp.draw_box(image, text_blocks,
box_width=3,
show_element_id=True)
show_img.show()
```
显示只有"Text"类别的结果：
Displays results with only the "Text" category：
<div align="center">
<img src="../../doc/table/result_text.jpg" width = "600" />
</div>
<a name="Results"></a>
<a name="指标"></a>
## 4. 指标
## 4. Results
| Dataset | mAP | CPU time cost | GPU time cost |
| --------- | ---- | ------------- | ------------- |
......@@ -125,9 +134,8 @@ lp.draw_box(image, text_blocks,
​ **GPU：** a single NVIDIA Tesla P40
<a name="训练版面分析模型"></a>
## 5. 训练版面分析模型
<a name="Training"></a>
上述模型基于[PaddleDetection](https://github.com/PaddlePaddle/PaddleDetection) 训练，如果您想训练自己的版面分析模型，请参考：[train_layoutparser_model](train_layoutparser_model.md)
## 5. Training
The above model is based on [PaddleDetection](https://github.com/PaddlePaddle/PaddleDetection). If you want to train your own layout parser model，please refer to：[train_layoutparser_model](train_layoutparser_model.md)
ppstructure/layout/README_ch.md 0 → 100644
View file @ 4ae91cb4
[English](README.md) | 简体中文
# 版面分析使用说明
[1. 安装whl包](#安装whl包)
[2. 使用](#使用)
[3. 后处理](#后处理)
[4. 指标](#指标)
[5. 训练版面分析模型](#训练版面分析模型)
<a name="安装whl包"></a>
## 1. 安装whl包
```bash
pip install -U https://paddleocr.bj.bcebos.com/whl/layoutparser-0.0.0-py3-none-any.whl
```
<a name="使用"></a>
## 2. 使用
使用layoutparser识别给定文档的布局：
```python
import cv2
import layoutparser as lp
image = cv2.imread("doc/table/layout.jpg")
image = image[..., ::-1]
# 加载模型
model = lp.PaddleDetectionLayoutModel(config_path="lp://PubLayNet/ppyolov2_r50vd_dcn_365e_publaynet/config",
threshold=0.5,
label_map={0: "Text", 1: "Title", 2: "List", 3:"Table", 4:"Figure"},
enforce_cpu=False,
enable_mkldnn=True)
# 检测
layout = model.detect(image)
# 显示结果
show_img = lp.draw_box(image, layout, box_width=3, show_element_type=True)
show_img.show()
```
下图展示了结果，不同颜色的检测框表示不同的类别，并通过`show_element_type`在框的左上角显示具体类别：
<div align="center">
<img src="../../doc/table/result_all.jpg" width = "600" />
</div>
`PaddleDetectionLayoutModel`函数参数说明如下:
| 参数 | 含义 | 默认值 | 备注 |
| :------------: | :-------------------------: | :---------: | :----------------------------------------------------------: |
| config_path | 模型配置路径 | None | 指定config_path会自动下载模型(仅第一次，之后模型存在，不会再下载) |
| model_path | 模型路径 | None | 本地模型路径，config_path和model_path必须设置一个，不能同时为None |
| threshold | 预测得分的阈值 | 0.5 | \ |
| input_shape | reshape之后图片尺寸 | [3,640,640] | \ |
| batch_size | 测试batch size | 1 | \ |
| label_map | 类别映射表 | None | 设置config_path时，可以为None，根据数据集名称自动获取label_map |
| enforce_cpu | 代码是否使用CPU运行 | False | 设置为False表示使用GPU，True表示强制使用CPU |
| enforce_mkldnn | CPU预测中是否开启MKLDNN加速 | True | \ |
| thread_num | 设置CPU线程数 | 10 | \ |
目前支持以下几种模型配置和label map，您可以通过修改 `--config_path`和 `--label_map`使用这些模型，从而检测不同类型的内容：
| dataset | config_path | label_map |
| ------------------------------------------------------------ | ------------------------------------------------------------ | --------------------------------------------------------- |
| [TableBank](https://doc-analysis.github.io/tablebank-page/index.html) word | lp://TableBank/ppyolov2_r50vd_dcn_365e_tableBank_word/config | {0:"Table"} |
| TableBank latex | lp://TableBank/ppyolov2_r50vd_dcn_365e_tableBank_latex/config | {0:"Table"} |
| [PubLayNet](https://github.com/ibm-aur-nlp/PubLayNet) | lp://PubLayNet/ppyolov2_r50vd_dcn_365e_publaynet/config | {0: "Text", 1: "Title", 2: "List", 3:"Table", 4:"Figure"} |
* TableBank word和TableBank latex分别在word文档、latex文档数据集训练；
* 下载的TableBank数据集里同时包含word和latex。
<a name="后处理"></a>
## 3. 后处理
版面分析检测包含多个类别，如果只想获取指定类别(如"Text"类别)的检测框、可以使用下述代码：
```python
# 接上面代码
# 首先过滤特定文本类型的区域
text_blocks = lp.Layout([b for b in layout if b.type=='Text'])
figure_blocks = lp.Layout([b for b in layout if b.type=='Figure'])
# 因为在图像区域内可能检测到文本区域，所以只需要删除它们
text_blocks = lp.Layout([b for b in text_blocks \
if not any(b.is_in(b_fig) for b_fig in figure_blocks)])
# 对文本区域排序并分配id
h, w = image.shape[:2]
left_interval = lp.Interval(0, w/2*1.05, axis='x').put_on_canvas(image)
left_blocks = text_blocks.filter_by(left_interval, center=True)
left_blocks.sort(key = lambda b:b.coordinates[1])
right_blocks = [b for b in text_blocks if b not in left_blocks]
right_blocks.sort(key = lambda b:b.coordinates[1])
# 最终合并两个列表，并按顺序添加索引
text_blocks = lp.Layout([b.set(id = idx) for idx, b in enumerate(left_blocks + right_blocks)])
# 显示结果
show_img = lp.draw_box(image, text_blocks,
box_width=3,
show_element_id=True)
show_img.show()
```
显示只有"Text"类别的结果：
<div align="center">
<img src="../../doc/table/result_text.jpg" width = "600" />
</div>
<a name="指标"></a>
## 4. 指标
| Dataset | mAP | CPU time cost | GPU time cost |
| --------- | ---- | ------------- | ------------- |
| PubLayNet | 93.6 | 1713.7ms | 66.6ms |
| TableBank | 96.2 | 1968.4ms | 65.1ms |
**Envrionment：**
​ **CPU：** Intel(R) Xeon(R) CPU E5-2650 v4 @ 2.20GHz，24core
​ **GPU：** a single NVIDIA Tesla P40
<a name="训练版面分析模型"></a>
## 5. 训练版面分析模型
上述模型基于[PaddleDetection](https://github.com/PaddlePaddle/PaddleDetection) 训练，如果您想训练自己的版面分析模型，请参考：[train_layoutparser_model](train_layoutparser_model_ch.md)
ppstructure/layout/train_layoutparser_model.md
View file @ 4ae91cb4
# 训练版面分析
# Training layout-parse
* [1. 安装](#安装)
* [1.1 环境要求](#环境要求)
* [1.2 安装PaddleDetection](#安装PaddleDetection)
* [2. 准备数据](#准备数据)
* [3. 配置文件改动和说明](#配置文件改动和说明)
* [4. PaddleDetection训练](#训练)
* [5. PaddleDetection预测](#预测)
* [6. 预测部署](#预测部署)
* [6.1 模型导出](#模型导出)
* [6.2 layout parser预测](#layout_parser预测)
[1. Installation](#Installation)
<a name="安装"></a>
​ [1.1 Requirements](#Requirements)
## 1. 安装
​ [1.2 Install PaddleDetection](#Install PaddleDetection)
<a name="环境要求"></a>
[2. Data preparation](#Data preparation)
### 1.1 环境要求
[3. Configuration](#Configuration)
[4. Training](#Training)
[5. Prediction](#Prediction)
[6. Deployment](#Deployment)
​ [6.1 Export model](#Export model)
​ [6.2 Inference](#Inference)
<a name="Installation"></a>
## 1. Installation
<a name="Requirements"></a>
### 1.1 Requirements
- PaddlePaddle 2.1
- OS 64 bit
......@@ -26,152 +35,159 @@
- CUDA >= 10.1
- cuDNN >= 7.6
<a name="安装PaddleDetection"></a>
<a name="Install PaddleDetection"></a>
### 1.2 安装PaddleDetection
### 1.2 Install PaddleDetection
```bash
# 克隆PaddleDetection仓库
# Clone PaddleDetection repository
cd <path/to/clone/PaddleDetection>
git clone https://github.com/PaddlePaddle/PaddleDetection.git
cd PaddleDetection
# 安装其他依赖
# Install other dependencies
pip install -r requirements.txt
```
更多安装教程，请参考: [Install doc](https://github.com/PaddlePaddle/PaddleDetection/blob/release/2.1/docs/tutorials/INSTALL_cn.md)
For more installation tutorials, please refer to： [Install doc](https://github.com/PaddlePaddle/PaddleDetection/blob/release/2.1/docs/tutorials/INSTALL_cn.md)
<a name="数据准备"></a>
<a name="Data preparation"></a>
## 2. 准备数据
## 2. Data preparation
下载 [PubLayNet](https://github.com/ibm-aur-nlp/PubLayNet) 数据集：
Download the [PubLayNet](https://github.com/ibm-aur-nlp/PubLayNet) dataset
```bash
cd PaddleDetection/dataset/
mkdir publaynet
# 执行命令，下载
# execute the command，download PubLayNet
wget -O publaynet.tar.gz https://dax-cdn.cdn.appdomain.cloud/dax-publaynet/1.0.0/publaynet.tar.gz?_ga=2.104193024.1076900768.1622560733-649911202.1622560733
# 解压
# unpack
tar -xvf publaynet.tar.gz
```
解压之后PubLayNet目录结构：
PubLayNet directory structure after decompressing ：
| File or Folder | Description | num |
| :------------- | :----------------------------------------------- | ------- |
| `train/` | Images in the training subset | 335,703 |
| `val/` | Images in the validation subset | 11,245 |
| `test/` | Images in the testing subset | 11,405 |
| `train.json` | Annotations for training images | |
| `val.json` | Annotations for validation images | |
| `LICENSE.txt` | Plaintext version of the CDLA-Permissive license | |
| `README.txt` | Text file with the file names and description | |
| `train.json` | Annotations for training images | 1 |
| `val.json` | Annotations for validation images | 1 |
| `LICENSE.txt` | Plaintext version of the CDLA-Permissive license | 1 |
| `README.txt` | Text file with the file names and description | 1 |
如果使用其它数据集，请参考[准备训练数据](https://github.com/PaddlePaddle/PaddleDetection/blob/release/2.1/docs/tutorials/PrepareDataSet.md)
For other datasets，please refer to [the PrepareDataSet]((https://github.com/PaddlePaddle/PaddleDetection/blob/release/2.1/docs/tutorials/PrepareDataSet.md) )
<a name="配置文件改动和说明"></a>
<a name="Configuration"></a>
## 3. 配置文件改动和说明
## 3. Configuration
我们使用 `configs/ppyolo/ppyolov2_r50vd_dcn_365e_coco.yml`配置进行训练，配置文件摘要如下：
We use the `configs/ppyolo/ppyolov2_r50vd_dcn_365e_coco.yml` configuration for training，the configuration file is as follows
<div align='center'>
<img src='../../doc/table/PaddleDetection_config.png' width='600px'/>
</div>
```bash
_BASE_: [
'../datasets/coco_detection.yml',
'../runtime.yml',
'./_base_/ppyolov2_r50vd_dcn.yml',
'./_base_/optimizer_365e.yml',
'./_base_/ppyolov2_reader.yml',
]
snapshot_epoch: 8
weights: output/ppyolov2_r50vd_dcn_365e_coco/model_final
```
The `ppyolov2_r50vd_dcn_365e_coco.yml` configuration depends on other configuration files, in this case:
从上图看到 `ppyolov2_r50vd_dcn_365e_coco.yml` 配置需要依赖其他的配置文件，在该例子中需要依赖:
- coco_detection.yml：mainly explains the path of training data and verification data
```
coco_detection.yml：主要说明了训练数据和验证数据的路径
- runtime.yml：mainly describes the common parameters, such as whether to use the GPU and how many epoch to save model etc.
runtime.yml：主要说明了公共的运行参数，比如是否使用GPU、每多少个epoch存储checkpoint等
- optimizer_365e.yml：mainly explains the learning rate and optimizer configuration
optimizer_365e.yml：主要说明了学习率和优化器的配置
- ppyolov2_r50vd_dcn.yml：mainly describes the model and the network
ppyolov2_r50vd_dcn.yml：主要说明模型和主干网络的情况
- ppyolov2_reader.yml：mainly describes the configuration of data readers, such as batch size and number of concurrent loading child processes, and also includes post preprocessing, such as resize and data augmention etc.
ppyolov2_reader.yml：主要说明数据读取器配置，如batch size，并发加载子进程数等，同时包含读取后预处理操作，如resize、数据增强等等
```
根据实际情况，修改上述文件，比如数据集路径、batch size等。
Modify the preceding files, such as the dataset path and batch size etc.
<a name="训练"></a>
<a name="Training"></a>
## 4. PaddleDetection训练
## 4. Training
PaddleDetection提供了单卡/多卡训练模式，满足用户多种训练需求
PaddleDetection provides single-card/multi-card training mode to meet various training needs of users:
* GPU 单卡训练
* GPU single card training
```bash
export CUDA_VISIBLE_DEVICES=0 #windows和Mac下不需要执行该命令
export CUDA_VISIBLE_DEVICES=0 #Don't need to run this command on Windows and Mac
python tools/train.py -c configs/ppyolo/ppyolov2_r50vd_dcn_365e_coco.yml
```
* GPU多卡训练
* GPU multi-card training
```bash
export CUDA_VISIBLE_DEVICES=0,1,2,3
python -m paddle.distributed.launch --gpus 0,1,2,3 tools/train.py -c configs/ppyolo/ppyolov2_r50vd_dcn_365e_coco.yml --eval
```
--eval：表示边训练边验证
--eval: training while verifying
* 模型恢复训练
* Model recovery training
在日常训练过程中，有的用户由于一些原因导致训练中断，用户可以使用-r的命令恢复训练:
During the daily training, if training is interrupted due to some reasons, you can use the -r command to resume the training:
```bash
export CUDA_VISIBLE_DEVICES=0,1,2,3
python -m paddle.distributed.launch --gpus 0,1,2,3 tools/train.py -c configs/ppyolo/ppyolov2_r50vd_dcn_365e_coco.yml --eval -r output/ppyolov2_r50vd_dcn_365e_coco/10000
```
注意：如果遇到 "`Out of memory error`" 问题, 尝试在 `ppyolov2_reader.yml` 文件中调小`batch_size`
Note: If you encounter "`Out of memory error`" , try reducing `batch_size` in the `ppyolov2_reader.yml` file
<a name="预测"></a>
prediction<a name="Prediction"></a>
## 5. PaddleDetection预测
## 5. Prediction
设置参数，使用PaddleDetection预测：
Set parameters and use PaddleDetection to predict：
```bash
export CUDA_VISIBLE_DEVICES=0
python tools/infer.py -c configs/ppyolo/ppyolov2_r50vd_dcn_365e_coco.yml --infer_img=images/paper-image.jpg --output_dir=infer_output/ --draw_threshold=0.5 -o weights=output/ppyolov2_r50vd_dcn_365e_coco/model_final --use_vdl=Ture
```
`--draw_threshold` 是个可选参数. 根据 [NMS](https://ieeexplore.ieee.org/document/1699659) 的计算，不同阈值会产生不同的结果 `keep_top_k`表示设置输出目标的最大数量，默认值为100，用户可以根据自己的实际情况进行设定。
`--draw_threshold` is an optional parameter. According to the calculation of [NMS](https://ieeexplore.ieee.org/document/1699659), different threshold will produce different results, ` keep_top_k ` represent the maximum amount of output target, the default value is 10. You can set different value according to your own actual situation。
<a name="预测部署"></a>
<a name="Deployment"></a>
## 6. 预测部署
## 6. Deployment
在layout parser中使用自己训练好的模型，
Use your trained model in Layout Parser
<a name="模型导出"></a>
<a name="Export model"></a>
### 6.1 模型导出
### 6.1 Export model
在模型训练过程中保存的模型文件是包含前向预测和反向传播的过程，在实际的工业部署则不需要反向传播，因此需要将模型进行导成部署需要的模型格式。 在PaddleDetection中提供了 `tools/export_model.py`脚本来导出模型。
n the process of model training, the model file saved contains the process of forward prediction and back propagation. In the actual industrial deployment, there is no need for back propagation. Therefore, the model should be translated into the model format required by the deployment. The `tools/export_model.py` script is provided in PaddleDetection to export the model.
导出模型名称默认是`model.*`，layout parser代码模型名称是`inference.*`, 所以修改[PaddleDetection/ppdet/engine/trainer.py ](https://github.com/PaddlePaddle/PaddleDetection/blob/b87a1ea86fa18ce69e44a17ad1b49c1326f19ff9/ppdet/engine/trainer.py#L512) (点开链接查看详细代码行)，将`model`改为`inference`即可。
The exported model name defaults to `model.*`, Layout Parser's code model is `inference.*`, So change [PaddleDetection/ppdet/engine/trainer. Py ](https://github.com/PaddlePaddle/PaddleDetection/blob/b87a1ea86fa18ce69e44a17ad1b49c1326f19ff9/ppdet/engine/trainer.py# L512) (click on the link to see the detailed line of code), change 'model' to 'inference'.
执行导出模型脚本：
Execute the script to export model:
```bash
python tools/export_model.py -c configs/ppyolo/ppyolov2_r50vd_dcn_365e_coco.yml --output_dir=./inference -o weights=output/ppyolov2_r50vd_dcn_365e_coco/model_final.pdparams
```
预测模型会导出到`inference/ppyolov2_r50vd_dcn_365e_coco`目录下，分别为`infer_cfg.yml`(预测不需要), `inference.pdiparams`, `inference.pdiparams.info`,`inference.pdmodel` 。
The prediction model is exported to `inference/ppyolov2_r50vd_dcn_365e_coco` ,including:`infer_cfg.yml`(prediction not required), `inference.pdiparams`, `inference.pdiparams.info`,`inference.pdmodel`
更多模型导出教程，请参考：[EXPORT_MODEL](https://github.com/PaddlePaddle/PaddleDetection/blob/release/2.1/deploy/EXPORT_MODEL.md)
More model export tutorials, please refer to：[EXPORT_MODEL](https://github.com/PaddlePaddle/PaddleDetection/blob/release/2.1/deploy/EXPORT_MODEL.md)
<a name="layout parser预测"></a>
<a name="Inference"></a>
### 6.2 layout_parser预测
### 6.2 Inference
`model_path`指定训练好的模型路径，使用layout parser进行预测：
`model_path` represent the trained model path, and layoutparser is used to predict:
```bash
import layoutparser as lp
......@@ -182,7 +198,6 @@ model = lp.PaddleDetectionLayoutModel(model_path="inference/ppyolov2_r50vd_dcn_3
***
更多PaddleDetection训练教程，请参考：[PaddleDetection训练](https://github.com/PaddlePaddle/PaddleDetection/blob/release/2.1/docs/tutorials/GETTING_STARTED_cn.md)
More PaddleDetection training tutorials，please reference：[PaddleDetection Training](https://github.com/PaddlePaddle/PaddleDetection/blob/release/2.1/docs/tutorials/GETTING_STARTED_cn.md)
***
ppstructure/layout/train_layoutparser_model_ch.md 0 → 100644
View file @ 4ae91cb4
# 训练版面分析
[1. 安装](#安装)
​ [1.1 环境要求](#环境要求)
​ [1.2 安装PaddleDetection](#安装PaddleDetection)
[2. 准备数据](#准备数据)
[3. 配置文件改动和说明](#配置文件改动和说明)
[4. PaddleDetection训练](#训练)
[5. PaddleDetection预测](#预测)
[6. 预测部署](#预测部署)
​ [6.1 模型导出](#模型导出)
​ [6.2 layout parser预测](#layout_parser预测)
<a name="安装"></a>
## 1. 安装
<a name="环境要求"></a>
### 1.1 环境要求
- PaddlePaddle 2.1
- OS 64 bit
- Python 3(3.5.1+/3.6/3.7/3.8/3.9)，64 bit
- pip/pip3(9.0.1+), 64 bit
- CUDA >= 10.1
- cuDNN >= 7.6
<a name="安装PaddleDetection"></a>
### 1.2 安装PaddleDetection
```bash
# 克隆PaddleDetection仓库
cd <path/to/clone/PaddleDetection>
git clone https://github.com/PaddlePaddle/PaddleDetection.git
cd PaddleDetection
# 安装其他依赖
pip install -r requirements.txt
```
更多安装教程，请参考: [Install doc](https://github.com/PaddlePaddle/PaddleDetection/blob/release/2.1/docs/tutorials/INSTALL_cn.md)
<a name="数据准备"></a>
## 2. 准备数据
下载 [PubLayNet](https://github.com/ibm-aur-nlp/PubLayNet) 数据集：
```bash
cd PaddleDetection/dataset/
mkdir publaynet
# 执行命令，下载
wget -O publaynet.tar.gz https://dax-cdn.cdn.appdomain.cloud/dax-publaynet/1.0.0/publaynet.tar.gz?_ga=2.104193024.1076900768.1622560733-649911202.1622560733
# 解压
tar -xvf publaynet.tar.gz
```
解压之后PubLayNet目录结构：
| File or Folder | Description | num |
| :------------- | :----------------------------------------------- | ------- |
| `train/` | Images in the training subset | 335,703 |
| `val/` | Images in the validation subset | 11,245 |
| `test/` | Images in the testing subset | 11,405 |
| `train.json` | Annotations for training images | 1 |
| `val.json` | Annotations for validation images | 1 |
| `LICENSE.txt` | Plaintext version of the CDLA-Permissive license | 1 |
| `README.txt` | Text file with the file names and description | 1 |
如果使用其它数据集，请参考[准备训练数据](https://github.com/PaddlePaddle/PaddleDetection/blob/release/2.1/docs/tutorials/PrepareDataSet.md)
<a name="配置文件改动和说明"></a>
## 3. 配置文件改动和说明
我们使用 `configs/ppyolo/ppyolov2_r50vd_dcn_365e_coco.yml`配置进行训练，配置文件摘要如下：
```bash
_BASE_: [
'../datasets/coco_detection.yml',
'../runtime.yml',
'./_base_/ppyolov2_r50vd_dcn.yml',
'./_base_/optimizer_365e.yml',
'./_base_/ppyolov2_reader.yml',
]
snapshot_epoch: 8
weights: output/ppyolov2_r50vd_dcn_365e_coco/model_final
```
从中可以看到 `ppyolov2_r50vd_dcn_365e_coco.yml` 配置需要依赖其他的配置文件，在该例子中需要依赖:
- coco_detection.yml：主要说明了训练数据和验证数据的路径
- runtime.yml：主要说明了公共的运行参数，比如是否使用GPU、每多少个epoch存储checkpoint等
- optimizer_365e.yml：主要说明了学习率和优化器的配置
- ppyolov2_r50vd_dcn.yml：主要说明模型和主干网络的情况
- ppyolov2_reader.yml：主要说明数据读取器配置，如batch size，并发加载子进程数等，同时包含读取后预处理操作，如resize、数据增强等等
根据实际情况，修改上述文件，比如数据集路径、batch size等。
<a name="训练"></a>
## 4. PaddleDetection训练
PaddleDetection提供了单卡/多卡训练模式，满足用户多种训练需求
* GPU 单卡训练
```bash
export CUDA_VISIBLE_DEVICES=0 #windows和Mac下不需要执行该命令
python tools/train.py -c configs/ppyolo/ppyolov2_r50vd_dcn_365e_coco.yml
```
* GPU多卡训练
```bash
export CUDA_VISIBLE_DEVICES=0,1,2,3
python -m paddle.distributed.launch --gpus 0,1,2,3 tools/train.py -c configs/ppyolo/ppyolov2_r50vd_dcn_365e_coco.yml --eval
```
--eval：表示边训练边验证
* 模型恢复训练
在日常训练过程中，有的用户由于一些原因导致训练中断，用户可以使用-r的命令恢复训练:
```bash
export CUDA_VISIBLE_DEVICES=0,1,2,3
python -m paddle.distributed.launch --gpus 0,1,2,3 tools/train.py -c configs/ppyolo/ppyolov2_r50vd_dcn_365e_coco.yml --eval -r output/ppyolov2_r50vd_dcn_365e_coco/10000
```
注意：如果遇到 "`Out of memory error`" 问题, 尝试在 `ppyolov2_reader.yml` 文件中调小`batch_size`
<a name="预测"></a>
## 5. PaddleDetection预测
设置参数，使用PaddleDetection预测：
```bash
export CUDA_VISIBLE_DEVICES=0
python tools/infer.py -c configs/ppyolo/ppyolov2_r50vd_dcn_365e_coco.yml --infer_img=images/paper-image.jpg --output_dir=infer_output/ --draw_threshold=0.5 -o weights=output/ppyolov2_r50vd_dcn_365e_coco/model_final --use_vdl=Ture
```
`--draw_threshold` 是个可选参数. 根据 [NMS](https://ieeexplore.ieee.org/document/1699659) 的计算，不同阈值会产生不同的结果 `keep_top_k`表示设置输出目标的最大数量，默认值为100，用户可以根据自己的实际情况进行设定。
<a name="预测部署"></a>
## 6. 预测部署
在layout parser中使用自己训练好的模型。
<a name="模型导出"></a>
### 6.1 模型导出
在模型训练过程中保存的模型文件是包含前向预测和反向传播的过程，在实际的工业部署则不需要反向传播，因此需要将模型进行导成部署需要的模型格式。 在PaddleDetection中提供了 `tools/export_model.py`脚本来导出模型。
导出模型名称默认是`model.*`，layout parser代码模型名称是`inference.*`, 所以修改[PaddleDetection/ppdet/engine/trainer.py ](https://github.com/PaddlePaddle/PaddleDetection/blob/b87a1ea86fa18ce69e44a17ad1b49c1326f19ff9/ppdet/engine/trainer.py#L512) (点开链接查看详细代码行)，将`model`改为`inference`即可。
执行导出模型脚本：
```bash
python tools/export_model.py -c configs/ppyolo/ppyolov2_r50vd_dcn_365e_coco.yml --output_dir=./inference -o weights=output/ppyolov2_r50vd_dcn_365e_coco/model_final.pdparams
```
预测模型会导出到`inference/ppyolov2_r50vd_dcn_365e_coco`目录下，分别为`infer_cfg.yml`(预测不需要), `inference.pdiparams`, `inference.pdiparams.info`,`inference.pdmodel` 。
更多模型导出教程，请参考：[EXPORT_MODEL](https://github.com/PaddlePaddle/PaddleDetection/blob/release/2.1/deploy/EXPORT_MODEL.md)
<a name="layout parser预测"></a>
### 6.2 layout_parser预测
`model_path`指定训练好的模型路径，使用layout parser进行预测：
```bash
import layoutparser as lp
model = lp.PaddleDetectionLayoutModel(model_path="inference/ppyolov2_r50vd_dcn_365e_coco", threshold=0.5,label_map={0: "Text", 1: "Title", 2: "List", 3:"Table", 4:"Figure"},enforce_cpu=True,enable_mkldnn=True)
```
***
更多PaddleDetection训练教程，请参考：[PaddleDetection训练](https://github.com/PaddlePaddle/PaddleDetection/blob/release/2.1/docs/tutorials/GETTING_STARTED_cn.md)
***
ppstructure/paddlestructure.py deleted 100644 → 0
View file @ 5ce3af84
# Copyright (c) 2020 PaddlePaddle Authors. All Rights Reserved.
#
# 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.
import logging
import os
import sys
__dir__ = os.path.dirname(__file__)
sys.path.append(__dir__)
sys.path.append(os.path.join(__dir__, '..'))
import cv2
import numpy as np
from pathlib import Path
from ppocr.utils.logging import get_logger
from ppstructure.predict_system import OCRSystem, save_res
from ppstructure.utility import init_args, draw_result
logger = get_logger()
from ppocr.utils.utility import check_and_read_gif, get_image_file_list
from ppocr.utils.network import maybe_download, download_with_progressbar, confirm_model_dir_url, is_link
__all__ = ['PaddleStructure', 'draw_result', 'save_res']
VERSION = '2.1'
BASE_DIR = os.path.expanduser("~/.paddlestructure/")
model_urls = {
'det': 'https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_det_infer.tar',
'rec': 'https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_rec_infer.tar',
'table': 'https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_structure_infer.tar'
}
def parse_args(mMain=True):
import argparse
parser = init_args()
parser.add_help = mMain
for action in parser._actions:
if action.dest in ['rec_char_dict_path', 'table_char_dict_path']:
action.default = None
if mMain:
return parser.parse_args()
else:
inference_args_dict = {}
for action in parser._actions:
inference_args_dict[action.dest] = action.default
return argparse.Namespace(**inference_args_dict)
class PaddleStructure(OCRSystem):
def __init__(self, **kwargs):
params = parse_args(mMain=False)
params.__dict__.update(**kwargs)
if not params.show_log:
logger.setLevel(logging.INFO)
params.use_angle_cls = False
# init model dir
params.det_model_dir, det_url = confirm_model_dir_url(params.det_model_dir,
os.path.join(BASE_DIR, VERSION, 'det'),
model_urls['det'])
params.rec_model_dir, rec_url = confirm_model_dir_url(params.rec_model_dir,
os.path.join(BASE_DIR, VERSION, 'rec'),
model_urls['rec'])
params.table_model_dir, table_url = confirm_model_dir_url(params.table_model_dir,
os.path.join(BASE_DIR, VERSION, 'table'),
model_urls['table'])
# download model
maybe_download(params.det_model_dir, det_url)
maybe_download(params.rec_model_dir, rec_url)
maybe_download(params.table_model_dir, table_url)
if params.rec_char_dict_path is None:
params.rec_char_type = 'EN'
if os.path.exists(str(Path(__file__).parent / 'ppocr/utils/dict/table_dict.txt')):
params.rec_char_dict_path = str(Path(__file__).parent / 'ppocr/utils/dict/table_dict.txt')
else:
params.rec_char_dict_path = str(Path(__file__).parent.parent / 'ppocr/utils/dict/table_dict.txt')
if params.table_char_dict_path is None:
if os.path.exists(str(Path(__file__).parent / 'ppocr/utils/dict/table_structure_dict.txt')):
params.table_char_dict_path = str(
Path(__file__).parent / 'ppocr/utils/dict/table_structure_dict.txt')
else:
params.table_char_dict_path = str(
Path(__file__).parent.parent / 'ppocr/utils/dict/table_structure_dict.txt')
print(params)
super().__init__(params)
def __call__(self, img):
if isinstance(img, str):
# download net image
if img.startswith('http'):
download_with_progressbar(img, 'tmp.jpg')
img = 'tmp.jpg'
image_file = img
img, flag = check_and_read_gif(image_file)
if not flag:
with open(image_file, 'rb') as f:
np_arr = np.frombuffer(f.read(), dtype=np.uint8)
img = cv2.imdecode(np_arr, cv2.IMREAD_COLOR)
if img is None:
logger.error("error in loading image:{}".format(image_file))
return None
if isinstance(img, np.ndarray) and len(img.shape) == 2:
img = cv2.cvtColor(img, cv2.COLOR_GRAY2BGR)
res = super().__call__(img)
return res
def main():
# for cmd
args = parse_args(mMain=True)
image_dir = args.image_dir
save_folder = args.output
if image_dir.startswith('http'):
download_with_progressbar(image_dir, 'tmp.jpg')
image_file_list = ['tmp.jpg']
else:
image_file_list = get_image_file_list(args.image_dir)
if len(image_file_list) == 0:
logger.error('no images find in {}'.format(args.image_dir))
return
structure_engine = PaddleStructure(**(args.__dict__))
for img_path in image_file_list:
img_name = os.path.basename(img_path).split('.')[0]
logger.info('{}{}{}'.format('*' * 10, img_path, '*' * 10))
result = structure_engine(img_path)
for item in result:
logger.info(item['res'])
save_res(result, save_folder, img_name)
logger.info('result save to {}'.format(os.path.join(save_folder, img_name)))
\ No newline at end of file
ppstructure/predict_system.py
View file @ 4ae91cb4
......@@ -26,26 +26,33 @@ import numpy as np
import time
import logging
import layoutparser as lp
from ppocr.utils.utility import get_image_file_list, check_and_read_gif
from ppocr.utils.logging import get_logger
from tools.infer.predict_system import TextSystem
from ppstructure.table.predict_table import TableSystem, to_excel
from ppstructure.utility import parse_args, draw_result
from ppstructure.utility import parse_args, draw_structure_result
logger = get_logger()
class OCRSystem(object):
def __init__(self, args):
args.det_limit_type = 'resize_long'
import layoutparser as lp
# args.det_limit_type = 'resize_long'
args.drop_score = 0
if not args.show_log:
logger.setLevel(logging.INFO)
self.text_system = TextSystem(args)
self.table_system = TableSystem(args, self.text_system.text_detector, self.text_system.text_recognizer)
self.table_layout = lp.PaddleDetectionLayoutModel("lp://PubLayNet/ppyolov2_r50vd_dcn_365e_publaynet/config",
config_path = None
model_path = None
if os.path.isdir(args.layout_path_model):
model_path = args.layout_path_model
else:
config_path = args.layout_path_model
self.table_layout = lp.PaddleDetectionLayoutModel(config_path=config_path,
model_path=model_path,
threshold=0.5, enable_mkldnn=args.enable_mkldnn,
enforce_cpu=not args.use_gpu, thread_num=args.cpu_threads)
self.use_angle_cls = args.use_angle_cls
......@@ -65,24 +72,35 @@ class OCRSystem(object):
filter_boxes, filter_rec_res = self.text_system(roi_img)
filter_boxes = [x + [x1, y1] for x in filter_boxes]
filter_boxes = [x.reshape(-1).tolist() for x in filter_boxes]
res = (filter_boxes, filter_rec_res)
res_list.append({'type': region.type, 'bbox': [x1, y1, x2, y2], 'res': res})
# remove style char
style_token = ['<strike>', '<strike>', '<sup>', '</sub>', '<b>', '</b>', '<sub>', '</sup>',
'<overline>', '</overline>', '<underline>', '</underline>', '<i>', '</i>']
filter_rec_res_tmp = []
for rec_res in filter_rec_res:
rec_str, rec_conf = rec_res
for token in style_token:
if token in rec_str:
rec_str = rec_str.replace(token, '')
filter_rec_res_tmp.append((rec_str, rec_conf))
res = (filter_boxes, filter_rec_res_tmp)
res_list.append({'type': region.type, 'bbox': [x1, y1, x2, y2], 'img': roi_img, 'res': res})
return res_list
def save_res(res, save_folder, img_name):
def save_structure_res(res, save_folder, img_name):
excel_save_folder = os.path.join(save_folder, img_name)
os.makedirs(excel_save_folder, exist_ok=True)
# save res
with open(os.path.join(excel_save_folder, 'res.txt'), 'w', encoding='utf8') as f:
for region in res:
if region['type'] == 'Table':
excel_path = os.path.join(excel_save_folder, '{}.xlsx'.format(region['bbox']))
to_excel(region['res'], excel_path)
elif region['type'] == 'Figure':
pass
if region['type'] == 'Figure':
roi_img = region['img']
img_path = os.path.join(excel_save_folder, '{}.jpg'.format(region['bbox']))
cv2.imwrite(img_path, roi_img)
else:
with open(os.path.join(excel_save_folder, 'res.txt'), 'a', encoding='utf8') as f:
for box, rec_res in zip(region['res'][0], region['res'][1]):
f.write('{}\t{}\n'.format(np.array(box).reshape(-1).tolist(), rec_res))
......@@ -108,8 +126,8 @@ def main(args):
continue
starttime = time.time()
res = structure_sys(img)
save_res(res, save_folder, img_name)
draw_img = draw_result(img, res, args.vis_font_path)
save_structure_res(res, save_folder, img_name)
draw_img = draw_structure_result(img, res, args.vis_font_path)
cv2.imwrite(os.path.join(save_folder, img_name, 'show.jpg'), draw_img)
logger.info('result save to {}'.format(os.path.join(save_folder, img_name)))
elapse = time.time() - starttime
......
ppstructure/setup.py deleted 100644 → 0
View file @ 5ce3af84
# Copyright (c) 2020 PaddlePaddle Authors. All Rights Reserved.
#
# 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.
import os
from setuptools import setup
from io import open
import shutil
with open('../requirements.txt', encoding="utf-8-sig") as f:
requirements = f.readlines()
requirements.append('tqdm')
def readme():
with open('README_ch.md', encoding="utf-8-sig") as f:
README = f.read()
return README
shutil.copytree('./table', './ppstructure/table')
shutil.copyfile('./predict_system.py', './ppstructure/predict_system.py')
shutil.copyfile('./utility.py', './ppstructure/utility.py')
shutil.copytree('../ppocr', './ppocr')
shutil.copytree('../tools', './tools')
shutil.copyfile('../LICENSE', './LICENSE')
setup(
name='paddlestructure',
packages=['paddlestructure'],
package_dir={'paddlestructure': ''},
include_package_data=True,
entry_points={"console_scripts": ["paddlestructure= paddlestructure.paddlestructure:main"]},
version='1.0',
install_requires=requirements,
license='Apache License 2.0',
description='Awesome OCR toolkits based on PaddlePaddle （8.6M ultra-lightweight pre-trained model, support training and deployment among server, mobile, embeded and IoT devices',
long_description=readme(),
long_description_content_type='text/markdown',
url='https://github.com/PaddlePaddle/PaddleOCR',
download_url='https://github.com/PaddlePaddle/PaddleOCR.git',
keywords=[
'ocr textdetection textrecognition paddleocr crnn east star-net rosetta ocrlite db chineseocr chinesetextdetection chinesetextrecognition'
],
classifiers=[
'Intended Audience :: Developers', 'Operating System :: OS Independent',
'Natural Language :: Chinese (Simplified)',
'Programming Language :: Python :: 3',
'Programming Language :: Python :: 3.2',
'Programming Language :: Python :: 3.3',
'Programming Language :: Python :: 3.4',
'Programming Language :: Python :: 3.5',
'Programming Language :: Python :: 3.6',
'Programming Language :: Python :: 3.7', 'Topic :: Utilities'
], )
shutil.rmtree('ppocr')
shutil.rmtree('tools')
shutil.rmtree('ppstructure')
os.remove('LICENSE')
ppstructure/table/README.md
View file @ 4ae91cb4
# Table structure and content prediction
# Table Recognition
## 1. pipeline
The ocr of the table mainly contains three models
The table recognition mainly contains three models
1. Single line text detection-DB
2. Single line text recognition-CRNN
3. Table structure and cell coordinate prediction-RARE
The table ocr flow chart is as follows
The table recognition flow chart is as follows
![tableocr_pipeline](../../doc/table/tableocr_pipeline_en.jpg)
......@@ -15,10 +15,39 @@ The table ocr flow chart is as follows
3. The recognition result of the cell is combined by the coordinates, recognition result of the single line and the coordinates of the cell.
4. The cell recognition result and the table structure together construct the html string of the table.
## 2. How to use
## 2. Performance
We evaluated the algorithm on the PubTabNet<sup>[1]</sup> eval dataset, and the performance is as follows:
### 2.1 Train
|Method|[TEDS(Tree-Edit-Distance-based Similarity)](https://github.com/ibm-aur-nlp/PubTabNet/tree/master/src)|
| --- | --- |
| EDD<sup>[2]</sup> | 88.3 |
| Ours | 93.32 |
## 3. How to use
### 3.1 quick start
```python
cd PaddleOCR/ppstructure
# download model
mkdir inference && cd inference
# Download the detection model of the ultra-lightweight table English OCR model and unzip it
wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_det_infer.tar && tar xf en_ppocr_mobile_v2.0_table_det_infer.tar
# Download the recognition model of the ultra-lightweight table English OCR model and unzip it
wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_rec_infer.tar && tar xf en_ppocr_mobile_v2.0_table_rec_infer.tar
# Download the ultra-lightweight English table inch model and unzip it
wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_structure_infer.tar && tar xf en_ppocr_mobile_v2.0_table_structure_infer.tar
cd ..
# run
python3 table/predict_table.py --det_model_dir=inference/en_ppocr_mobile_v2.0_table_det_infer --rec_model_dir=inference/en_ppocr_mobile_v2.0_table_rec_infer --table_model_dir=inference/en_ppocr_mobile_v2.0_table_structure_infer --image_dir=../doc/table/table.jpg --rec_char_dict_path=../ppocr/utils/ppocr_keys_v1.txt --table_char_dict_path=../ppocr/utils/dict/table_structure_dict.txt --rec_char_type=ch --det_limit_side_len=736 --det_limit_type=min --output ../output/table
```
Note: The above model is trained on the PubLayNet dataset and only supports English scanning scenarios. If you need to identify other scenarios, you need to train the model yourself and replace the three fields `det_model_dir`, `rec_model_dir`, `table_model_dir`.
After running, the excel sheet of each picture will be saved in the directory specified by the output field
### 3.2 Train
In this chapter, we only introduce the training of the table structure model, For model training of [text detection](../../doc/doc_en/detection_en.md) and [text recognition](../../doc/doc_en/recognition_en.md), please refer to the corresponding documents
......@@ -48,29 +77,40 @@ python3 tools/train.py -c configs/table/table_mv3.yml -o Global.checkpoints=./yo
**Note**: The priority of `Global.checkpoints` is higher than that of `Global.pretrain_weights`, that is, when two parameters are specified at the same time, the model specified by `Global.checkpoints` will be loaded first. If the model path specified by `Global.checkpoints` is wrong, the one specified by `Global.pretrain_weights` will be loaded.
### 2.2 Eval
First cd to the PaddleOCR/ppstructure directory
### 3.3 Eval
The table uses TEDS (Tree-Edit-Distance-based Similarity) as the evaluation metric of the model. Before the model evaluation, the three models in the pipeline need to be exported as inference models (we have provided them), and the gt for evaluation needs to be prepared. Examples of gt are as follows:
The table uses [TEDS(Tree-Edit-Distance-based Similarity)](https://github.com/ibm-aur-nlp/PubTabNet/tree/master/src) as the evaluation metric of the model. Before the model evaluation, the three models in the pipeline need to be exported as inference models (we have provided them), and the gt for evaluation needs to be prepared. Examples of gt are as follows:
```json
{"PMC4289340_004_00.png": [["<html>", "<body>", "<table>", "<thead>", "<tr>", "<td>", "</td>", "<td>", "</td>", "<td>", "</td>", "</tr>", "</thead>", "<tbody>", "<tr>", "<td>", "</td>", "<td>", "</td>", "<td>", "</td>", "</tr>", "</tbody>", "</table>", "</body>", "</html>"], [[1, 4, 29, 13], [137, 4, 161, 13], [215, 4, 236, 13], [1, 17, 30, 27], [137, 17, 147, 27], [215, 17, 225, 27]], [["<b>", "F", "e", "a", "t", "u", "r", "e", "</b>"], ["<b>", "G", "b", "3", " ", "+", "</b>"], ["<b>", "G", "b", "3", " ", "-", "</b>"], ["<b>", "P", "a", "t", "i", "e", "n", "t", "s", "</b>"], ["6", "2"], ["4", "5"]]]}
{"PMC4289340_004_00.png": [
["<html>", "<body>", "<table>", "<thead>", "<tr>", "<td>", "</td>", "<td>", "</td>", "<td>", "</td>", "</tr>", "</thead>", "<tbody>", "<tr>", "<td>", "</td>", "<td>", "</td>", "<td>", "</td>", "</tr>", "</tbody>", "</table>", "</body>", "</html>"],
[[1, 4, 29, 13], [137, 4, 161, 13], [215, 4, 236, 13], [1, 17, 30, 27], [137, 17, 147, 27], [215, 17, 225, 27]],
[["<b>", "F", "e", "a", "t", "u", "r", "e", "</b>"], ["<b>", "G", "b", "3", " ", "+", "</b>"], ["<b>", "G", "b", "3", " ", "-", "</b>"], ["<b>", "P", "a", "t", "i", "e", "n", "t", "s", "</b>"], ["6", "2"], ["4", "5"]]
]}
```
In gt json, the key is the image name, the value is the corresponding gt, and gt is a list composed of four items, and each item is
1. HTML string list of table structure
2. The coordinates of each cell (not including the empty text in the cell)
3. The text information in each cell (not including the empty text in the cell)
4. The text information in each cell (including the empty text in the cell)
Use the following command to evaluate. After the evaluation is completed, the teds indicator will be output.
```python
cd PaddleOCR/ppstructure
python3 table/eval_table.py --det_model_dir=path/to/det_model_dir --rec_model_dir=path/to/rec_model_dir --table_model_dir=path/to/table_model_dir --image_dir=../doc/table/1.png --rec_char_dict_path=../ppocr/utils/dict/table_dict.txt --table_char_dict_path=../ppocr/utils/dict/table_structure_dict.txt --rec_char_type=EN --det_limit_side_len=736 --det_limit_type=min --gt_path=path/to/gt.json
```
If the PubLatNet eval dataset is used, it will be output
```bash
teds: 93.32
```
### 2.3 Inference
First cd to the PaddleOCR/ppstructure directory
### 3.4 Inference
```python
cd PaddleOCR/ppstructure
python3 table/predict_table.py --det_model_dir=path/to/det_model_dir --rec_model_dir=path/to/rec_model_dir --table_model_dir=path/to/table_model_dir --image_dir=../doc/table/1.png --rec_char_dict_path=../ppocr/utils/dict/table_dict.txt --table_char_dict_path=../ppocr/utils/dict/table_structure_dict.txt --rec_char_type=EN --det_limit_side_len=736 --det_limit_type=min --output ../output/table
```
After running, the excel sheet of each picture will be saved in the directory specified by the output field
Reference
1. https://github.com/ibm-aur-nlp/PubTabNet
2. https://arxiv.org/pdf/1911.10683
\ No newline at end of file
ppstructure/table/README_ch.md
View file @ 4ae91cb4
# 表格结构和内容预测
# 表格识别
## 1. pipeline
表格的ocr主要包含三个模型
## 1. 表格识别 pipeline
表格识别主要包含三个模型
1. 单行文本检测-DB
2. 单行文本识别-CRNN
3. 表格结构和cell坐标预测-RARE
......@@ -10,18 +10,50 @@
![tableocr_pipeline](../../doc/table/tableocr_pipeline.jpg)
1. 图片由单行文字检测检测模型到单行文字的坐标，然后送入识别模型拿到识别结果。
流程说明:
1. 图片由单行文字检测模型检测到单行文字的坐标，然后送入识别模型拿到识别结果。
2. 图片由表格结构和cell坐标预测模型拿到表格的结构信息和单元格的坐标信息。
3. 由单行文字的坐标、识别结果和单元格的坐标一起组合出单元格的识别结果。
4. 单元格的识别结果和表格结构一起构造表格的html字符串。
## 2. 使用
## 2. 性能
我们在 PubTabNet<sup>[1]</sup> 评估数据集上对算法进行了评估，性能如下
|算法|[TEDS(Tree-Edit-Distance-based Similarity)](https://github.com/ibm-aur-nlp/PubTabNet/tree/master/src)|
| --- | --- |
| EDD<sup>[2]</sup> | 88.3 |
| Ours | 93.32 |
## 3. 使用
### 3.1 快速开始
```python
cd PaddleOCR/ppstructure
# 下载模型
mkdir inference && cd inference
# 下载超轻量级表格英文OCR模型的检测模型并解压
wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_det_infer.tar && tar xf en_ppocr_mobile_v2.0_table_det_infer.tar
# 下载超轻量级表格英文OCR模型的识别模型并解压
wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_rec_infer.tar && tar xf en_ppocr_mobile_v2.0_table_rec_infer.tar
# 下载超轻量级英文表格英寸模型并解压
wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_structure_infer.tar && tar xf en_ppocr_mobile_v2.0_table_structure_infer.tar
cd ..
# 执行预测
python3 table/predict_table.py --det_model_dir=inference/en_ppocr_mobile_v2.0_table_det_infer --rec_model_dir=inference/en_ppocr_mobile_v2.0_table_rec_infer --table_model_dir=inference/en_ppocr_mobile_v2.0_table_structure_infer --image_dir=../doc/table/table.jpg --rec_char_dict_path=../ppocr/utils/ppocr_keys_v1.txt --table_char_dict_path=../ppocr/utils/dict/table_structure_dict.txt --rec_char_type=ch --det_limit_side_len=736 --det_limit_type=min --output ../output/table
```
运行完成后，每张图片的excel表格会保存到output字段指定的目录下
note: 上述模型是在 PubLayNet 数据集上训练的表格识别模型，仅支持英文扫描场景，如需识别其他场景需要自己训练模型后替换 `det_model_dir`,`rec_model_dir`,`table_model_dir`三个字段即可。
### 2.1 训练
### 3.2 训练
在这一章节中，我们仅介绍表格结构模型的训练，[文字检测](../../doc/doc_ch/detection.md)和[文字识别](../../doc/doc_ch/recognition.md)的模型训练请参考对应的文档。
#### 数据准备
训练数据使用公开数据集[PubTabNet](https://arxiv.org/abs/1911.10683)，可以从[官网](https://github.com/ibm-aur-nlp/PubTabNet)下载。PubTabNet数据集包含约50万张表格数据的图像，以及图像对应的html格式的注释。
训练数据使用公开数据集PubTabNet ([论文](https://arxiv.org/abs/1911.10683)，[下载地址](https://github.com/ibm-aur-nlp/PubTabNet))。PubTabNet数据集包含约50万张表格数据的图像，以及图像对应的html格式的注释。
#### 启动训练
*如果您安装的是cpu版本，请将配置文件中的 `use_gpu` 字段修改为false*
......@@ -44,29 +76,38 @@ python3 tools/train.py -c configs/table/table_mv3.yml -o Global.checkpoints=./yo
**注意**：`Global.checkpoints`的优先级高于`Global.pretrain_weights`的优先级，即同时指定两个参数时，优先加载`Global.checkpoints`指定的模型，如果`Global.checkpoints`指定的模型路径有误，会加载`Global.pretrain_weights`指定的模型。
### 2.2 评估
先cd到PaddleOCR/ppstructure目录下
### 3.3 评估
表格使用 TEDS(Tree-Edit-Distance-based Similarity) 作为模型的评估指标。在进行模型评估之前，需要将pipeline中的三个模型分别导出为inference模型(我们已经提供好)，还需要准备评估的gt， gt示例如下:
表格使用 [TEDS(Tree-Edit-Distance-based Similarity)](https://github.com/ibm-aur-nlp/PubTabNet/tree/master/src) 作为模型的评估指标。在进行模型评估之前，需要将pipeline中的三个模型分别导出为inference模型(我们已经提供好)，还需要准备评估的gt， gt示例如下:
```json
{"PMC4289340_004_00.png": [["<html>", "<body>", "<table>", "<thead>", "<tr>", "<td>", "</td>", "<td>", "</td>", "<td>", "</td>", "</tr>", "</thead>", "<tbody>", "<tr>", "<td>", "</td>", "<td>", "</td>", "<td>", "</td>", "</tr>", "</tbody>", "</table>", "</body>", "</html>"], [[1, 4, 29, 13], [137, 4, 161, 13], [215, 4, 236, 13], [1, 17, 30, 27], [137, 17, 147, 27], [215, 17, 225, 27]], [["<b>", "F", "e", "a", "t", "u", "r", "e", "</b>"], ["<b>", "G", "b", "3", " ", "+", "</b>"], ["<b>", "G", "b", "3", " ", "-", "</b>"], ["<b>", "P", "a", "t", "i", "e", "n", "t", "s", "</b>"], ["6", "2"], ["4", "5"]]]}
{"PMC4289340_004_00.png": [
["<html>", "<body>", "<table>", "<thead>", "<tr>", "<td>", "</td>", "<td>", "</td>", "<td>", "</td>", "</tr>", "</thead>", "<tbody>", "<tr>", "<td>", "</td>", "<td>", "</td>", "<td>", "</td>", "</tr>", "</tbody>", "</table>", "</body>", "</html>"],
[[1, 4, 29, 13], [137, 4, 161, 13], [215, 4, 236, 13], [1, 17, 30, 27], [137, 17, 147, 27], [215, 17, 225, 27]],
[["<b>", "F", "e", "a", "t", "u", "r", "e", "</b>"], ["<b>", "G", "b", "3", " ", "+", "</b>"], ["<b>", "G", "b", "3", " ", "-", "</b>"], ["<b>", "P", "a", "t", "i", "e", "n", "t", "s", "</b>"], ["6", "2"], ["4", "5"]]
]}
```
json 中，key为图片名，value为对于的gt，gt是一个由四个item组成的list，每个item分别为
json 中，key为图片名，value为对应的gt，gt是一个由三个item组成的list，每个item分别为
1. 表格结构的html字符串list
2. 每个cell的坐标 (不包括cell里文字为空的)
3. 每个cell里的文字信息 (不包括cell里文字为空的)
4. 每个cell里的文字信息 (包括cell里文字为空的)
准备完成后使用如下命令进行评估，评估完成后会输出teds指标。
```python
cd PaddleOCR/ppstructure
python3 table/eval_table.py --det_model_dir=path/to/det_model_dir --rec_model_dir=path/to/rec_model_dir --table_model_dir=path/to/table_model_dir --image_dir=../doc/table/1.png --rec_char_dict_path=../ppocr/utils/dict/table_dict.txt --table_char_dict_path=../ppocr/utils/dict/table_structure_dict.txt --rec_char_type=EN --det_limit_side_len=736 --det_limit_type=min --gt_path=path/to/gt.json
```
如使用PubLatNet评估数据集，将会输出
```bash
teds: 93.32
```
### 2.3 预测
先cd到PaddleOCR/ppstructure目录下
### 3.4 预测
```python
cd PaddleOCR/ppstructure
python3 table/predict_table.py --det_model_dir=path/to/det_model_dir --rec_model_dir=path/to/rec_model_dir --table_model_dir=path/to/table_model_dir --image_dir=../doc/table/1.png --rec_char_dict_path=../ppocr/utils/dict/table_dict.txt --table_char_dict_path=../ppocr/utils/dict/table_structure_dict.txt --rec_char_type=EN --det_limit_side_len=736 --det_limit_type=min --output ../output/table
```
运行完成后，每张图片的excel表格会保存到output字段指定的目录下
Reference
1. https://github.com/ibm-aur-nlp/PubTabNet
2. https://arxiv.org/pdf/1911.10683
\ No newline at end of file
ppstructure/table/eval_table.py
View file @ 4ae91cb4
......@@ -46,20 +46,20 @@ def main(gt_path, img_root, args):
pred_html = text_sys(img)
pred_htmls.append(pred_html)
gt_structures, gt_bboxes, gt_contents, contents_with_block = jsons_gt[img_name]
gt_html, gt = get_gt_html(gt_structures, contents_with_block)
gt_structures, gt_bboxes, gt_contents = jsons_gt[img_name]
gt_html, gt = get_gt_html(gt_structures, gt_contents)
gt_htmls.append(gt_html)
scores = teds.batch_evaluate_html(gt_htmls, pred_htmls)
logger.info('teds:', sum(scores) / len(scores))
def get_gt_html(gt_structures, contents_with_block):
def get_gt_html(gt_structures, gt_contents):
end_html = []
td_index = 0
for tag in gt_structures:
if '</td>' in tag:
if contents_with_block[td_index] != []:
end_html.extend(contents_with_block[td_index])
if gt_contents[td_index] != []:
end_html.extend(gt_contents[td_index])
end_html.append(tag)
td_index += 1
else:
......
ppstructure/utility.py
View file @ 4ae91cb4
......@@ -27,7 +27,7 @@ def init_args():
parser.add_argument("--table_model_dir", type=str)
parser.add_argument("--table_char_type", type=str, default='en')
parser.add_argument("--table_char_dict_path", type=str, default="../ppocr/utils/dict/table_structure_dict.txt")
parser.add_argument("--layout_path_model", type=str, default="lp://PubLayNet/ppyolov2_r50vd_dcn_365e_publaynet/config")
return parser
......@@ -36,15 +36,13 @@ def parse_args():
return parser.parse_args()
def draw_result(image, result, font_path):
def draw_structure_result(image, result, font_path):
if isinstance(image, np.ndarray):
image = Image.fromarray(image)
boxes, txts, scores = [], [], []
for region in result:
if region['type'] == 'Table':
pass
elif region['type'] == 'Figure':
pass
else:
for box, rec_res in zip(region['res'][0], region['res'][1]):
boxes.append(np.array(box).reshape(-1, 2))
......
setup.py
View file @ 4ae91cb4
......@@ -14,6 +14,7 @@
from setuptools import setup
from io import open
from paddleocr import VERSION
with open('requirements.txt', encoding="utf-8-sig") as f:
requirements = f.readlines()
......@@ -32,7 +33,7 @@ setup(
package_dir={'paddleocr': ''},
include_package_data=True,
entry_points={"console_scripts": ["paddleocr= paddleocr.paddleocr:main"]},
version='2.0.6',
version=VERSION,
install_requires=requirements,
license='Apache License 2.0',
description='Awesome OCR toolkits based on PaddlePaddle （8.6M ultra-lightweight pre-trained model, support training and deployment among server, mobile, embeded and IoT devices',
......
test/ocr_rec_params.txt deleted 100644 → 0
View file @ 5ce3af84
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/
\ No newline at end of file
test/prepare.sh deleted 100644 → 0
View file @ 5ce3af84
#!/bin/bash
FILENAME=$1
# MODE be one of ['lite_train_infer' 'whole_infer' 'whole_train_infer', 'infer']
MODE=$2
dataline=$(cat ${FILENAME})
# parser params
IFS=$'\n'
lines=(${dataline})
function func_parser_key(){
strs=$1
IFS=":"
array=(${strs})
tmp=${array[0]}
echo ${tmp}
}
function func_parser_value(){
strs=$1
IFS=":"
array=(${strs})
tmp=${array[1]}
echo ${tmp}
}
IFS=$'\n'
# The training params
model_name=$(func_parser_value "${lines[0]}")
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
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
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
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
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
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
eval_batch_step=10
else
rm -rf ./train_data/icdar2015
wget -nc -P ./train_data https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/ch_det_data_50.tar
if [ ${model_name} = "ocr_det" ]; then
eval_model_name="ch_ppocr_mobile_v2.0_det_infer"
wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_infer.tar
cd ./inference && tar xf ${eval_model_name}.tar && cd ../
else
eval_model_name="ch_ppocr_mobile_v2.0_rec_train"
wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_train.tar
cd ./inference && tar xf ${eval_model_name}.tar && cd ../
fi
fi
IFS='|'
for train_model in ${train_model_list[*]}; do
if [ ${train_model} = "ocr_det" ];then
model_name="ocr_det"
yml_file="configs/det/ch_ppocr_v2.0/ch_det_mv3_db_v2.0.yml"
wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/ch_det_data_50.tar
cd ./inference && tar xf ch_det_data_50.tar && cd ../
img_dir="./inference/ch_det_data_50/all-sum-510"
data_dir=./inference/ch_det_data_50/
data_label_file=[./inference/ch_det_data_50/test_gt_50.txt]
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/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
for slim_trainer in ${trainer_list[*]}; do
if [ ${slim_trainer} = "norm" ]; then
if [ ${model_name} = "det" ]; then
eval_model_name="ch_ppocr_mobile_v2.0_det_train"
wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_train.tar
cd ./inference && tar xf ${eval_model_name}.tar && cd ../
else
eval_model_name="ch_ppocr_mobile_v2.0_rec_train"
wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_train.tar
cd ./inference && tar xf ${eval_model_name}.tar && cd ../
fi
elif [ ${slim_trainer} = "pact" ]; then
if [ ${model_name} = "det" ]; then
eval_model_name="ch_ppocr_mobile_v2.0_det_quant_train"
wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/slim/ch_ppocr_mobile_v2.0_det_quant_train.tar
cd ./inference && tar xf ${eval_model_name}.tar && cd ../
else
eval_model_name="ch_ppocr_mobile_v2.0_rec_quant_train"
wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/slim/ch_ppocr_mobile_v2.0_rec_quant_train.tar
cd ./inference && tar xf ${eval_model_name}.tar && cd ../
fi
elif [ ${slim_trainer} = "distill" ]; then
if [ ${model_name} = "det" ]; then
eval_model_name="ch_ppocr_mobile_v2.0_det_distill_train"
wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/slim/ch_ppocr_mobile_v2.0_det_distill_train.tar
cd ./inference && tar xf ${eval_model_name}.tar && cd ../
else
eval_model_name="ch_ppocr_mobile_v2.0_rec_distill_train"
wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/slim/ch_ppocr_mobile_v2.0_rec_distill_train.tar
cd ./inference && tar xf ${eval_model_name}.tar && cd ../
fi
elif [ ${slim_trainer} = "fpgm" ]; then
if [ ${model_name} = "det" ]; then
eval_model_name="ch_ppocr_mobile_v2.0_det_prune_train"
wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/slim/ch_ppocr_mobile_v2.0_det_prune_train.tar
cd ./inference && tar xf ${eval_model_name}.tar && cd ../
else
eval_model_name="ch_ppocr_mobile_v2.0_rec_prune_train"
wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/slim/ch_ppocr_mobile_v2.0_rec_prune_train.tar
cd ./inference && tar xf ${eval_model_name}.tar && cd ../
fi
fi
done
done
test/test.sh deleted 100644 → 0
View file @ 5ce3af84
#!/bin/bash
FILENAME=$1
# MODE be one of ['lite_train_infer' 'whole_infer' 'whole_train_infer', 'infer']
MODE=$2
dataline=$(cat ${FILENAME})
# parser params
IFS=$'\n'
lines=(${dataline})
function func_parser_key(){
strs=$1
IFS=":"
array=(${strs})
tmp=${array[0]}
echo ${tmp}
}
function func_parser_value(){
strs=$1
IFS=":"
array=(${strs})
tmp=${array[1]}
echo ${tmp}
}
function status_check(){
last_status=$1 # the exit code
run_command=$2
run_log=$3
if [ $last_status -eq 0 ]; then
echo -e "\033[33m Run successfully with command - ${run_command}! \033[0m" | tee -a ${run_log}
else
echo -e "\033[33m Run failed with command - ${run_command}! \033[0m" | tee -a ${run_log}
fi
}
IFS=$'\n'
# The training params
model_name=$(func_parser_value "${lines[0]}")
python=$(func_parser_value "${lines[1]}")
gpu_list=$(func_parser_value "${lines[2]}")
autocast_list=$(func_parser_value "${lines[3]}")
autocast_key=$(func_parser_key "${lines[3]}")
epoch_key=$(func_parser_key "${lines[4]}")
epoch_num=$(func_parser_value "${lines[4]}")
save_model_key=$(func_parser_key "${lines[5]}")
train_batch_key=$(func_parser_key "${lines[6]}")
train_use_gpu_key=$(func_parser_key "${lines[7]}")
pretrain_model_key=$(func_parser_key "${lines[8]}")
pretrain_model_value=$(func_parser_value "${lines[8]}")
trainer_list=$(func_parser_value "${lines[9]}")
norm_trainer=$(func_parser_value "${lines[10]}")
pact_trainer=$(func_parser_value "${lines[11]}")
fpgm_trainer=$(func_parser_value "${lines[12]}")
distill_trainer=$(func_parser_value "${lines[13]}")
eval_py=$(func_parser_value "${lines[14]}")
save_infer_key=$(func_parser_key "${lines[15]}")
export_weight=$(func_parser_key "${lines[16]}")
norm_export=$(func_parser_value "${lines[17]}")
pact_export=$(func_parser_value "${lines[18]}")
fpgm_export=$(func_parser_value "${lines[19]}")
distill_export=$(func_parser_value "${lines[20]}")
inference_py=$(func_parser_value "${lines[21]}")
use_gpu_key=$(func_parser_key "${lines[22]}")
use_gpu_list=$(func_parser_value "${lines[22]}")
use_mkldnn_key=$(func_parser_key "${lines[23]}")
use_mkldnn_list=$(func_parser_value "${lines[23]}")
cpu_threads_key=$(func_parser_key "${lines[24]}")
cpu_threads_list=$(func_parser_value "${lines[24]}")
batch_size_key=$(func_parser_key "${lines[25]}")
batch_size_list=$(func_parser_value "${lines[25]}")
use_trt_key=$(func_parser_key "${lines[26]}")
use_trt_list=$(func_parser_value "${lines[26]}")
precision_key=$(func_parser_key "${lines[27]}")
precision_list=$(func_parser_value "${lines[27]}")
infer_model_key=$(func_parser_key "${lines[28]}")
infer_model=$(func_parser_value "${lines[28]}")
image_dir_key=$(func_parser_key "${lines[29]}")
infer_img_dir=$(func_parser_value "${lines[29]}")
save_log_key=$(func_parser_key "${lines[30]}")
LOG_PATH="./test/output"
mkdir -p ${LOG_PATH}
status_log="${LOG_PATH}/results.log"
function func_inference(){
IFS='|'
_python=$1
_script=$2
_model_dir=$3
_log_path=$4
_img_dir=$5
# inference
for use_gpu in ${use_gpu_list[*]}; do
if [ ${use_gpu} = "False" ]; then
for use_mkldnn in ${use_mkldnn_list[*]}; do
for threads in ${cpu_threads_list[*]}; do
for batch_size in ${batch_size_list[*]}; do
_save_log_path="${_log_path}/infer_cpu_usemkldnn_${use_mkldnn}_threads_${threads}_batchsize_${batch_size}.log"
command="${_python} ${_script} ${use_gpu_key}=${use_gpu} ${use_mkldnn_key}=${use_mkldnn} ${cpu_threads_key}=${threads} ${infer_model_key}=${_model_dir} ${batch_size_key}=${batch_size} ${image_dir_key}=${_img_dir} ${save_log_key}=${_save_log_path} --benchmark=True"
eval $command
status_check $? "${command}" "${status_log}"
done
done
done
else
for use_trt in ${use_trt_list[*]}; do
for precision in ${precision_list[*]}; do
if [ ${use_trt} = "False" ] && [ ${precision} != "fp32" ]; then
continue
fi
for batch_size in ${batch_size_list[*]}; do
_save_log_path="${_log_path}/infer_gpu_usetrt_${use_trt}_precision_${precision}_batchsize_${batch_size}.log"
command="${_python} ${_script} ${use_gpu_key}=${use_gpu} ${use_trt_key}=${use_trt} ${precision_key}=${precision} ${infer_model_key}=${_model_dir} ${batch_size_key}=${batch_size} ${image_dir_key}=${_img_dir} ${save_log_key}=${_save_log_path} --benchmark=True"
eval $command
status_check $? "${command}" "${status_log}"
done
done
done
fi
done
}
if [ ${MODE} != "infer" ]; then
IFS="|"
for gpu in ${gpu_list[*]}; do
use_gpu=True
if [ ${gpu} = "-1" ];then
use_gpu=False
env=""
elif [ ${#gpu} -le 1 ];then
env="export CUDA_VISIBLE_DEVICES=${gpu}"
eval ${env}
elif [ ${#gpu} -le 15 ];then
IFS=","
array=(${gpu})
env="export CUDA_VISIBLE_DEVICES=${array[0]}"
IFS="|"
else
IFS=";"
array=(${gpu})
ips=${array[0]}
gpu=${array[1]}
IFS="|"
env=" "
fi
for autocast in ${autocast_list[*]}; do
for trainer in ${trainer_list[*]}; do
if [ ${trainer} = "pact" ]; then
run_train=${pact_trainer}
run_export=${pact_export}
elif [ ${trainer} = "fpgm" ]; then
run_train=${fpgm_trainer}
run_export=${fpgm_export}
elif [ ${trainer} = "distill" ]; then
run_train=${distill_trainer}
run_export=${distill_export}
else
run_train=${norm_trainer}
run_export=${norm_export}
fi
if [ ${run_train} = "null" ]; then
continue
fi
if [ ${run_export} = "null" ]; then
continue
fi
# not set autocast when autocast is null
if [ ${autocast} = "null" ]; then
set_autocast=" "
else
set_autocast="${autocast_key}=${autocast}"
fi
# not set epoch when whole_train_infer
if [ ${MODE} != "whole_train_infer" ]; then
set_epoch="${epoch_key}=${epoch_num}"
else
set_epoch=" "
fi
# set pretrain
if [ ${pretrain_model_value} != "null" ]; then
set_pretrain="${pretrain_model_key}=${pretrain_model_value}"
else
set_pretrain=" "
fi
save_log="${LOG_PATH}/${trainer}_gpus_${gpu}_autocast_${autocast}"
if [ ${#gpu} -le 2 ];then # train with cpu or single gpu
cmd="${python} ${run_train} ${train_use_gpu_key}=${use_gpu} ${save_model_key}=${save_log} ${set_epoch} ${set_pretrain} ${set_autocast}"
elif [ ${#gpu} -le 15 ];then # train with multi-gpu
cmd="${python} -m paddle.distributed.launch --gpus=${gpu} ${run_train} ${save_model_key}=${save_log} ${set_epoch} ${set_pretrain} ${set_autocast}"
else # train with multi-machine
cmd="${python} -m paddle.distributed.launch --ips=${ips} --gpus=${gpu} ${run_train} ${save_model_key}=${save_log} ${set_pretrain} ${set_epoch} ${set_autocast}"
fi
# run train
eval $cmd
status_check $? "${cmd}" "${status_log}"
# run eval
eval_cmd="${python} ${eval_py} ${save_model_key}=${save_log} ${pretrain_model_key}=${save_log}/latest"
eval $eval_cmd
status_check $? "${eval_cmd}" "${status_log}"
# run export model
save_infer_path="${save_log}"
export_cmd="${python} ${run_export} ${save_model_key}=${save_log} ${export_weight}=${save_log}/latest ${save_infer_key}=${save_infer_path}"
eval $export_cmd
status_check $? "${export_cmd}" "${status_log}"
#run inference
eval $env
save_infer_path="${save_log}"
func_inference "${python}" "${inference_py}" "${save_infer_path}" "${LOG_PATH}" "${infer_img_dir}"
eval "unset CUDA_VISIBLE_DEVICES"
done
done
done
else
GPUID=$3
if [ ${#GPUID} -le 0 ];then
env=" "
else
env="export CUDA_VISIBLE_DEVICES=${GPUID}"
fi
echo $env
#run inference
func_inference "${python}" "${inference_py}" "${infer_model}" "${LOG_PATH}" "${infer_img_dir}"
fi
test/ocr_det_params.txt → tests/ocr_det_params.txt
View file @ 4ae91cb4
===========================train_params===========================
model_name:ocr_det
python:python3.7
gpu_list:0|0,1
Global.use_gpu:True|True
Global.auto_cast:null
Global.epoch_num:10
Global.epoch_num:lite_train_infer=2|whole_train_infer=300
Global.save_model_dir:./output/
Train.loader.batch_size_per_card:
Global.use_gpu:
Train.loader.batch_size_per_card:lite_train_infer=2|whole_train_infer=4
Global.pretrained_model:null
trainer:norm|pact
train_model_name:latest
train_infer_img_dir:./train_data/icdar2015/text_localization/ch4_test_images/
null:null
##
trainer:norm_train|pact_train
norm_train:tools/train.py -c configs/det/det_mv3_db.yml -o Global.pretrained_model=./pretrain_models/MobileNetV3_large_x0_5_pretrained
quant_train:deploy/slim/quantization/quant.py -c configs/det/det_mv3_db.yml -o Global.pretrained_model=./pretrain_models/det_mv3_db_v2.0_train/best_accuracy
pact_train:deploy/slim/quantization/quant.py -c configs/det/det_mv3_db.yml -o
fpgm_train:null
distill_train:null
null:null
null:null
##
===========================eval_params===========================
eval:tools/eval.py -c configs/det/det_mv3_db.yml -o
null:null
##
===========================infer_params===========================
Global.save_inference_dir:./output/
Global.pretrained_model:
norm_export:tools/export_model.py -c configs/det/det_mv3_db.yml -o
quant_export:deploy/slim/quantization/export_model.py -c configs/det/det_mv3_db.yml -o
fpgm_export:deploy/slim/prune/export_prune_model.py
distill_export:null
export1:null
export2:null
##
infer_model:./inference/ch_ppocr_mobile_v2.0_det_infer/
infer_export:null
infer_quant:False
inference:tools/infer/predict_det.py
--use_gpu:True|False
--enable_mkldnn:True|False
--cpu_threads:1|6
--rec_batch_num:1
--use_tensorrt:True|False
--use_tensorrt:False|True
--precision:fp32|fp16|int8
--det_model_dir:./inference/ch_ppocr_mobile_v2.0_det_infer/
--det_model_dir:
--image_dir:./inference/ch_det_data_50/all-sum-510/
--save_log_path:./test/output/
--save_log_path:null
--benchmark:True
null:null
tests/prepare.sh 0 → 100644
View file @ 4ae91cb4
#!/bin/bash
FILENAME=$1
# MODE be one of ['lite_train_infer' 'whole_infer' 'whole_train_infer', 'infer']
MODE=$2
dataline=$(cat ${FILENAME})
# parser params
IFS=$'\n'
lines=(${dataline})
function func_parser_key(){
strs=$1
IFS=":"
array=(${strs})
tmp=${array[0]}
echo ${tmp}
}
function func_parser_value(){
strs=$1
IFS=":"
array=(${strs})
tmp=${array[1]}
echo ${tmp}
}
IFS=$'\n'
# The training params
model_name=$(func_parser_value "${lines[1]}")
trainer_list=$(func_parser_value "${lines[14]}")
# MODE be one of ['lite_train_infer' 'whole_infer' 'whole_train_infer']
MODE=$2
if [ ${MODE} = "lite_train_infer" ];then
# pretrain lite train data
wget -nc -P ./pretrain_models/ https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/MobileNetV3_large_x0_5_pretrained.pdparams
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
ln -s ./icdar2015_lite ./icdar2015
cd ../
elif [ ${MODE} = "whole_train_infer" ];then
wget -nc -P ./pretrain_models/ https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/MobileNetV3_large_x0_5_pretrained.pdparams
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 ../
elif [ ${MODE} = "whole_infer" ];then
wget -nc -P ./pretrain_models/ https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/MobileNetV3_large_x0_5_pretrained.pdparams
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
ln -s ./icdar2015_infer ./icdar2015
cd ../
else
rm -rf ./train_data/icdar2015
if [[ ${model_name} = "ocr_det" ]]; then
wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/test/ch_det_data_50.tar
eval_model_name="ch_ppocr_mobile_v2.0_det_infer"
wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_infer.tar
cd ./inference && tar xf ${eval_model_name}.tar && tar xf ch_det_data_50.tar && cd ../
else
eval_model_name="ch_ppocr_mobile_v2.0_rec_train"
wget -nc -P ./inference https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_train.tar
cd ./inference && tar xf ${eval_model_name}.tar && cd ../
fi
fi
tests/test.sh 0 → 100644
View file @ 4ae91cb4
#!/bin/bash
FILENAME=$1
# MODE be one of ['lite_train_infer' 'whole_infer' 'whole_train_infer', 'infer']
MODE=$2
dataline=$(cat ${FILENAME})
# parser params
IFS=$'\n'
lines=(${dataline})
function func_parser_key(){
strs=$1
IFS=":"
array=(${strs})
tmp=${array[0]}
echo ${tmp}
}
function func_parser_value(){
strs=$1
IFS=":"
array=(${strs})
tmp=${array[1]}
echo ${tmp}
}
function func_set_params(){
key=$1
value=$2
if [ ${key} = "null" ];then
echo " "
elif [[ ${value} = "null" ]] || [[ ${value} = " " ]] || [ ${#value} -le 0 ];then
echo " "
else
echo "${key}=${value}"
fi
}
function func_parser_params(){
strs=$1
IFS=":"
array=(${strs})
key=${array[0]}
tmp=${array[1]}
IFS="|"
res=""
for _params in ${tmp[*]}; do
IFS="="
array=(${_params})
mode=${array[0]}
value=${array[1]}
if [[ ${mode} = ${MODE} ]]; then
IFS="|"
#echo $(func_set_params "${mode}" "${value}")
echo $value
break
fi
IFS="|"
done
echo ${res}
}
function status_check(){
last_status=$1 # the exit code
run_command=$2
run_log=$3
if [ $last_status -eq 0 ]; then
echo -e "\033[33m Run successfully with command - ${run_command}! \033[0m" | tee -a ${run_log}
else
echo -e "\033[33m Run failed with command - ${run_command}! \033[0m" | tee -a ${run_log}
fi
}
IFS=$'\n'
# The training params
model_name=$(func_parser_value "${lines[1]}")
python=$(func_parser_value "${lines[2]}")
gpu_list=$(func_parser_value "${lines[3]}")
train_use_gpu_key=$(func_parser_key "${lines[4]}")
train_use_gpu_value=$(func_parser_value "${lines[4]}")
autocast_list=$(func_parser_value "${lines[5]}")
autocast_key=$(func_parser_key "${lines[5]}")
epoch_key=$(func_parser_key "${lines[6]}")
epoch_num=$(func_parser_params "${lines[6]}")
save_model_key=$(func_parser_key "${lines[7]}")
train_batch_key=$(func_parser_key "${lines[8]}")
train_batch_value=$(func_parser_params "${lines[8]}")
pretrain_model_key=$(func_parser_key "${lines[9]}")
pretrain_model_value=$(func_parser_value "${lines[9]}")
train_model_name=$(func_parser_value "${lines[10]}")
train_infer_img_dir=$(func_parser_value "${lines[11]}")
train_param_key1=$(func_parser_key "${lines[12]}")
train_param_value1=$(func_parser_value "${lines[12]}")
trainer_list=$(func_parser_value "${lines[14]}")
trainer_norm=$(func_parser_key "${lines[15]}")
norm_trainer=$(func_parser_value "${lines[15]}")
pact_key=$(func_parser_key "${lines[16]}")
pact_trainer=$(func_parser_value "${lines[16]}")
fpgm_key=$(func_parser_key "${lines[17]}")
fpgm_trainer=$(func_parser_value "${lines[17]}")
distill_key=$(func_parser_key "${lines[18]}")
distill_trainer=$(func_parser_value "${lines[18]}")
trainer_key1=$(func_parser_key "${lines[19]}")
trainer_value1=$(func_parser_value "${lines[19]}")
trainer_key2=$(func_parser_key "${lines[20]}")
trainer_value2=$(func_parser_value "${lines[20]}")
eval_py=$(func_parser_value "${lines[23]}")
eval_key1=$(func_parser_key "${lines[24]}")
eval_value1=$(func_parser_value "${lines[24]}")
save_infer_key=$(func_parser_key "${lines[27]}")
export_weight=$(func_parser_key "${lines[28]}")
norm_export=$(func_parser_value "${lines[29]}")
pact_export=$(func_parser_value "${lines[30]}")
fpgm_export=$(func_parser_value "${lines[31]}")
distill_export=$(func_parser_value "${lines[32]}")
export_key1=$(func_parser_key "${lines[33]}")
export_value1=$(func_parser_value "${lines[33]}")
export_key2=$(func_parser_key "${lines[34]}")
export_value2=$(func_parser_value "${lines[34]}")
# parser inference model
infer_model_dir_list=$(func_parser_value "${lines[36]}")
infer_export_list=$(func_parser_value "${lines[37]}")
infer_is_quant=$(func_parser_value "${lines[38]}")
# parser inference
inference_py=$(func_parser_value "${lines[39]}")
use_gpu_key=$(func_parser_key "${lines[40]}")
use_gpu_list=$(func_parser_value "${lines[40]}")
use_mkldnn_key=$(func_parser_key "${lines[41]}")
use_mkldnn_list=$(func_parser_value "${lines[41]}")
cpu_threads_key=$(func_parser_key "${lines[42]}")
cpu_threads_list=$(func_parser_value "${lines[42]}")
batch_size_key=$(func_parser_key "${lines[43]}")
batch_size_list=$(func_parser_value "${lines[43]}")
use_trt_key=$(func_parser_key "${lines[44]}")
use_trt_list=$(func_parser_value "${lines[44]}")
precision_key=$(func_parser_key "${lines[45]}")
precision_list=$(func_parser_value "${lines[45]}")
infer_model_key=$(func_parser_key "${lines[46]}")
image_dir_key=$(func_parser_key "${lines[47]}")
infer_img_dir=$(func_parser_value "${lines[47]}")
save_log_key=$(func_parser_key "${lines[48]}")
benchmark_key=$(func_parser_key "${lines[49]}")
benchmark_value=$(func_parser_value "${lines[49]}")
infer_key1=$(func_parser_key "${lines[50]}")
infer_value1=$(func_parser_value "${lines[50]}")
LOG_PATH="./tests/output"
mkdir -p ${LOG_PATH}
status_log="${LOG_PATH}/results.log"
function func_inference(){
IFS='|'
_python=$1
_script=$2
_model_dir=$3
_log_path=$4
_img_dir=$5
_flag_quant=$6
# inference
for use_gpu in ${use_gpu_list[*]}; do
if [ ${use_gpu} = "False" ] || [ ${use_gpu} = "cpu" ]; then
for use_mkldnn in ${use_mkldnn_list[*]}; do
if [ ${use_mkldnn} = "False" ] && [ ${_flag_quant} = "True" ]; then
continue
fi
for threads in ${cpu_threads_list[*]}; do
for batch_size in ${batch_size_list[*]}; do
_save_log_path="${_log_path}/infer_cpu_usemkldnn_${use_mkldnn}_threads_${threads}_batchsize_${batch_size}.log"
set_infer_data=$(func_set_params "${image_dir_key}" "${_img_dir}")
set_benchmark=$(func_set_params "${benchmark_key}" "${benchmark_value}")
set_batchsize=$(func_set_params "${batch_size_key}" "${batch_size}")
set_cpu_threads=$(func_set_params "${cpu_threads_key}" "${threads}")
set_model_dir=$(func_set_params "${infer_model_key}" "${_model_dir}")
set_infer_params1=$(func_set_params "${infer_key1}" "${infer_value1}")
command="${_python} ${_script} ${use_gpu_key}=${use_gpu} ${use_mkldnn_key}=${use_mkldnn} ${set_cpu_threads} ${set_model_dir} ${set_batchsize} ${set_infer_data} ${set_benchmark} ${set_infer_params1} > ${_save_log_path} 2>&1 "
eval $command
last_status=${PIPESTATUS[0]}
eval "cat ${_save_log_path}"
status_check $last_status "${command}" "${status_log}"
done
done
done
elif [ ${use_gpu} = "True" ] || [ ${use_gpu} = "gpu" ]; then
for use_trt in ${use_trt_list[*]}; do
for precision in ${precision_list[*]}; do
if [[ ${_flag_quant} = "False" ]] && [[ ${precision} =~ "int8" ]]; then
continue
fi
if [[ ${precision} =~ "fp16" || ${precision} =~ "int8" ]] && [ ${use_trt} = "False" ]; then
continue
fi
if [[ ${use_trt} = "False" || ${precision} =~ "int8" ]] && [ ${_flag_quant} = "True" ]; then
continue
fi
for batch_size in ${batch_size_list[*]}; do
_save_log_path="${_log_path}/infer_gpu_usetrt_${use_trt}_precision_${precision}_batchsize_${batch_size}.log"
set_infer_data=$(func_set_params "${image_dir_key}" "${_img_dir}")
set_benchmark=$(func_set_params "${benchmark_key}" "${benchmark_value}")
set_batchsize=$(func_set_params "${batch_size_key}" "${batch_size}")
set_tensorrt=$(func_set_params "${use_trt_key}" "${use_trt}")
set_precision=$(func_set_params "${precision_key}" "${precision}")
set_model_dir=$(func_set_params "${infer_model_key}" "${_model_dir}")
set_infer_params1=$(func_set_params "${infer_key1}" "${infer_value1}")
command="${_python} ${_script} ${use_gpu_key}=${use_gpu} ${set_tensorrt} ${set_precision} ${set_model_dir} ${set_batchsize} ${set_infer_data} ${set_benchmark} ${set_infer_params1} > ${_save_log_path} 2>&1 "
eval $command
last_status=${PIPESTATUS[0]}
eval "cat ${_save_log_path}"
status_check $last_status "${command}" "${status_log}"
done
done
done
else
echo "Does not support hardware other than CPU and GPU Currently!"
fi
done
}
if [ ${MODE} = "infer" ]; then
GPUID=$3
if [ ${#GPUID} -le 0 ];then
env=" "
else
env="export CUDA_VISIBLE_DEVICES=${GPUID}"
fi
# set CUDA_VISIBLE_DEVICES
eval $env
export Count=0
IFS="|"
infer_run_exports=(${infer_export_list})
infer_quant_flag=(${infer_is_quant})
for infer_model in ${infer_model_dir_list[*]}; do
# run export
if [ ${infer_run_exports[Count]} != "null" ];then
set_export_weight=$(func_set_params "${export_weight}" "${infer_model}")
set_save_infer_key=$(func_set_params "${save_infer_key}" "${infer_model}")
export_cmd="${python} ${norm_export} ${set_export_weight} ${set_save_infer_key}"
eval $export_cmd
status_export=$?
if [ ${status_export} = 0 ];then
status_check $status_export "${export_cmd}" "${status_log}"
fi
fi
#run inference
is_quant=${infer_quant_flag[Count]}
func_inference "${python}" "${inference_py}" "${infer_model}" "${LOG_PATH}" "${infer_img_dir}" ${is_quant}
Count=$(($Count + 1))
done
else
IFS="|"
export Count=0
USE_GPU_KEY=(${train_use_gpu_value})
for gpu in ${gpu_list[*]}; do
use_gpu=${USE_GPU_KEY[Count]}
Count=$(($Count + 1))
if [ ${gpu} = "-1" ];then
env=""
elif [ ${#gpu} -le 1 ];then
env="export CUDA_VISIBLE_DEVICES=${gpu}"
eval ${env}
elif [ ${#gpu} -le 15 ];then
IFS=","
array=(${gpu})
env="export CUDA_VISIBLE_DEVICES=${array[0]}"
IFS="|"
else
IFS=";"
array=(${gpu})
ips=${array[0]}
gpu=${array[1]}
IFS="|"
env=" "
fi
for autocast in ${autocast_list[*]}; do
for trainer in ${trainer_list[*]}; do
flag_quant=False
if [ ${trainer} = ${pact_key} ]; then
run_train=${pact_trainer}
run_export=${pact_export}
flag_quant=True
elif [ ${trainer} = "${fpgm_key}" ]; then
run_train=${fpgm_trainer}
run_export=${fpgm_export}
elif [ ${trainer} = "${distill_key}" ]; then
run_train=${distill_trainer}
run_export=${distill_export}
elif [ ${trainer} = ${trainer_key1} ]; then
run_train=${trainer_value1}
run_export=${export_value1}
elif [[ ${trainer} = ${trainer_key2} ]]; then
run_train=${trainer_value2}
run_export=${export_value2}
else
run_train=${norm_trainer}
run_export=${norm_export}
fi
if [ ${run_train} = "null" ]; then
continue
fi
set_autocast=$(func_set_params "${autocast_key}" "${autocast}")
set_epoch=$(func_set_params "${epoch_key}" "${epoch_num}")
set_pretrain=$(func_set_params "${pretrain_model_key}" "${pretrain_model_value}")
set_batchsize=$(func_set_params "${train_batch_key}" "${train_batch_value}")
set_train_params1=$(func_set_params "${train_param_key1}" "${train_param_value1}")
set_use_gpu=$(func_set_params "${train_use_gpu_key}" "${use_gpu}")
save_log="${LOG_PATH}/${trainer}_gpus_${gpu}_autocast_${autocast}"
# load pretrain from norm training if current trainer is pact or fpgm trainer
if [ ${trainer} = ${pact_key} ] || [ ${trainer} = ${fpgm_key} ]; then
set_pretrain="${load_norm_train_model}"
fi
set_save_model=$(func_set_params "${save_model_key}" "${save_log}")
if [ ${#gpu} -le 2 ];then # train with cpu or single gpu
cmd="${python} ${run_train} ${set_use_gpu} ${set_save_model} ${set_epoch} ${set_pretrain} ${set_autocast} ${set_batchsize} ${set_train_params1} "
elif [ ${#gpu} -le 15 ];then # train with multi-gpu
cmd="${python} -m paddle.distributed.launch --gpus=${gpu} ${run_train} ${set_save_model} ${set_epoch} ${set_pretrain} ${set_autocast} ${set_batchsize} ${set_train_params1}"
else # train with multi-machine
cmd="${python} -m paddle.distributed.launch --ips=${ips} --gpus=${gpu} ${run_train} ${set_save_model} ${set_pretrain} ${set_epoch} ${set_autocast} ${set_batchsize} ${set_train_params1}"
fi
# run train
eval "unset CUDA_VISIBLE_DEVICES"
eval $cmd
status_check $? "${cmd}" "${status_log}"
set_eval_pretrain=$(func_set_params "${pretrain_model_key}" "${save_log}/${train_model_name}")
# save norm trained models to set pretrain for pact training and fpgm training
if [ ${trainer} = ${trainer_norm} ]; then
load_norm_train_model=${set_eval_pretrain}
fi
# run eval
if [ ${eval_py} != "null" ]; then
set_eval_params1=$(func_set_params "${eval_key1}" "${eval_value1}")
eval_cmd="${python} ${eval_py} ${set_eval_pretrain} ${set_use_gpu} ${set_eval_params1}"
eval $eval_cmd
status_check $? "${eval_cmd}" "${status_log}"
fi
# run export model
if [ ${run_export} != "null" ]; then
# run export model
save_infer_path="${save_log}"
set_export_weight=$(func_set_params "${export_weight}" "${save_log}/${train_model_name}")
set_save_infer_key=$(func_set_params "${save_infer_key}" "${save_infer_path}")
export_cmd="${python} ${run_export} ${set_export_weight} ${set_save_infer_key}"
eval $export_cmd
status_check $? "${export_cmd}" "${status_log}"
#run inference
eval $env
save_infer_path="${save_log}"
func_inference "${python}" "${inference_py}" "${save_infer_path}" "${LOG_PATH}" "${train_infer_img_dir}" "${flag_quant}"
eval "unset CUDA_VISIBLE_DEVICES"
fi
done # done with: for trainer in ${trainer_list[*]}; do
done # done with: for autocast in ${autocast_list[*]}; do
done # done with: for gpu in ${gpu_list[*]}; do
fi # end if [ ${MODE} = "infer" ]; then
tools/infer/predict_det.py
View file @ 4ae91cb4
......@@ -106,7 +106,7 @@ class TextDetector(object):
model_precision=args.precision,
batch_size=1,
data_shape="dynamic",
save_path=args.save_log_path,
save_path=None,
inference_config=self.config,
pids=pid,
process_name=None,
......@@ -114,7 +114,8 @@ class TextDetector(object):
time_keys=[
'preprocess_time', 'inference_time', 'postprocess_time'
],
warmup=10)
warmup=2,
logger=logger)
def order_points_clockwise(self, pts):
"""
......@@ -236,7 +237,7 @@ if __name__ == "__main__":
if args.warmup:
img = np.random.uniform(0, 255, [640, 640, 3]).astype(np.uint8)
for i in range(10):
for i in range(2):
res = text_detector(img)
if not os.path.exists(draw_img_save):
......
tools/infer/predict_rec.py
View file @ 4ae91cb4
......@@ -73,7 +73,7 @@ class TextRecognizer(object):
model_precision=args.precision,
batch_size=args.rec_batch_num,
data_shape="dynamic",
save_path=args.save_log_path,
save_path=None, #args.save_log_path,
inference_config=self.config,
pids=pid,
process_name=None,
......@@ -81,7 +81,8 @@ class TextRecognizer(object):
time_keys=[
'preprocess_time', 'inference_time', 'postprocess_time'
],
warmup=10)
warmup=2,
logger=logger)
def resize_norm_img(self, img, max_wh_ratio):
imgC, imgH, imgW = self.rec_image_shape
......@@ -272,10 +273,10 @@ def main(args):
valid_image_file_list = []
img_list = []
# warmup 10 times
# warmup 2 times
if args.warmup:
img = np.random.uniform(0, 255, [32, 320, 3]).astype(np.uint8)
for i in range(10):
for i in range(2):
res = text_recognizer([img])
for image_file in image_file_list:
......
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