add layout (#6669)

* add layout

* add layout

configs/picodet/legacy_model/application/layout_analysis/README.md

+# 更多应用
+
+
+## 1. 版面分析任务
+
+版面分析指的是对图片形式的文档进行区域划分，定位其中的关键区域，如文字、标题、表格、图片等。版面分析示意图如下图所示。
+
+<div align="center">
+    <img src="images/layout_demo.png" width="800">
+</div>
+
+### 1.1 数据集
+
+训练版面分析模型时主要用到了以下几个数据集。
+
+| dataset     | 简介                 |
+| ------------------------------------------------------------ | ------------------------------------------------------------ |
+| [cTDaR2019_cTDaR](https://cndplab-founder.github.io/cTDaR2019/) | 用于表格检测(TRACKA)和表格识别(TRACKB)。图片类型包含历史数据集(以cTDaR_t0开头，如cTDaR_t00872.jpg)和现代数据集(以cTDaR_t1开头，cTDaR_t10482.jpg)。 |
+| [IIIT-AR-13K](http://cvit.iiit.ac.in/usodi/iiitar13k.php)    | 手动注释公开的年度报告中的图形或页面而构建的数据集，包含5类：table, figure, natural image, logo, and signature |
+| [CDLA](https://github.com/buptlihang/CDLA)                   | 中文文档版面分析数据集，面向中文文献类（论文）场景，包含10类：Table、Figure、Figure caption、Table、Table caption、Header、Footer、Reference、Equation |
+| [TableBank](https://github.com/doc-analysis/TableBank)       | 用于表格检测和识别大型数据集，包含Word和Latex2种文档格式     |
+| [DocBank](https://github.com/doc-analysis/DocBank)           | 使用弱监督方法构建的大规模数据集(500K文档页面)，用于文档布局分析，包含12类：Author、Caption、Date、Equation、Figure、Footer、List、Paragraph、Reference、Section、Table、Title |
+
+
+### 1.2 模型库
+
+| 模型     | 图像输入尺寸 | mAP<sup>val<br/>0.5 |  下载地址  |  配置文件  |
+| :-------- | :--------: |  :----------------: | :---------------: | ----------------- |
+| PicoDet-LCNet_x1_0 |  800*608   |   93.5    | [trained model](https://paddleocr.bj.bcebos.com/ppstructure/models/layout/picodet_lcnet_x1_0_layout.pdparams) &#124; [inference model](https://paddleocr.bj.bcebos.com/ppstructure/models/layout/picodet_lcnet_x1_0_fgd_layout_infer.tar)  | [config](./picodet_lcnet_x1_0_layout.yml) |
+| PicoDet-LCNet_x1_0 + FGD |  800*608   |   94     | [trained model](https://paddleocr.bj.bcebos.com/ppstructure/models/layout/picodet_lcnet_x1_0_fgd_layout.pdparams) &#124; [inference model](https://paddleocr.bj.bcebos.com/ppstructure/models/layout/picodet_lcnet_x1_0_layout_infer.tar)  | [teacher config](./picodet_lcnet_x2_5_layout.yml)&#124;[student config](./picodet_lcnet_x1_0_layout.yml) |
+
+### 1.3 模型推理
+
+下载模型库中的inference_model模型，版面恢复任务进行推理，可以执行如下命令：
+
+```bash
+python3 deploy/python/infer.py \
+	--model_dir=picodet_lcnet_x1_0_layout/ \
+	--image_file=docs/images/layout.jpg \
+	--device=CPU
+```
+
+可视化版面结果如下图所示：
+
+<div align="center">
+    <img src="images/layout_res.jpg" width="800">
+</div>
+

configs/picodet/legacy_model/application/layout_analysis/picodet_lcnet_x1_0_layout.yml

+_BASE_: [
+  '../../../../runtime.yml',
+  '../../_base_/picodet_esnet.yml',
+  '../../_base_/optimizer_100e.yml',
+  '../../_base_/picodet_640_reader.yml',
+]
+
+pretrain_weights: https://paddledet.bj.bcebos.com/models/pretrained/LCNet_x1_0_pretrained.pdparams
+weights: output/picodet_lcnet_x1_0_layout/model_final
+find_unused_parameters: True
+use_ema: true
+cycle_epoch: 10
+snapshot_epoch: 1
+epoch: 100
+
+PicoDet:
+  backbone: LCNet
+  neck: CSPPAN
+  head: PicoHead
+
+LCNet:
+  scale: 1.0
+  feature_maps: [3, 4, 5]
+
+metric: COCO
+num_classes: 5
+
+TrainDataset:
+  !COCODataSet
+    image_dir: train
+    anno_path: train.json
+    dataset_dir: ./dataset/publaynet/
+    data_fields: ['image', 'gt_bbox', 'gt_class', 'is_crowd']
+
+EvalDataset:
+  !COCODataSet
+    image_dir: val
+    anno_path: val.json
+    dataset_dir: ./dataset/publaynet/
+
+TestDataset:
+  !ImageFolder
+    anno_path: ./dataset/publaynet/val.json
+
+
+worker_num: 8
+TrainReader:
+  sample_transforms:
+  - Decode: {}
+  - RandomCrop: {}
+  - RandomFlip: {prob: 0.5}
+  - RandomDistort: {}
+  batch_transforms:
+  - BatchRandomResize: {target_size: [[768, 576], [800, 608], [832, 640]], random_size: True, random_interp: True, keep_ratio: False}
+  - NormalizeImage: {is_scale: true, mean: [0.485,0.456,0.406], std: [0.229, 0.224,0.225]}
+  - Permute: {}
+  batch_size: 24
+  shuffle: true
+  drop_last: true
+  collate_batch: false
+
+EvalReader:
+  sample_transforms:
+  - Decode: {}
+  - Resize: {interp: 2, target_size: [800, 608], keep_ratio: False}
+  - NormalizeImage: {is_scale: true, mean: [0.485,0.456,0.406], std: [0.229, 0.224,0.225]}
+  - Permute: {}
+  batch_transforms:
+  - PadBatch: {pad_to_stride: 32}
+  batch_size: 8
+  shuffle: false
+
+
+TestReader:
+  inputs_def:
+    image_shape: [1, 3, 800, 608]
+  sample_transforms:
+  - Decode: {}
+  - Resize: {interp: 2, target_size: [800, 608], keep_ratio: False}
+  - NormalizeImage: {is_scale: true, mean: [0.485,0.456,0.406], std: [0.229, 0.224,0.225]}
+  - Permute: {}
+  batch_transforms:
+  - PadBatch: {pad_to_stride: 32}
+  batch_size: 1
+  shuffle: false

configs/picodet/legacy_model/application/layout_analysis/picodet_lcnet_x2_5_layout.yml

+_BASE_: [
+  '../../_base_/picodet_esnet.yml',
+]
+
+pretrain_weights: https://paddledet.bj.bcebos.com/models/pretrained/LCNet_x2_5_ssld_pretrained.pdparams
+weights: output/picodet_lcnet_x2_5_layout/model_final
+find_unused_parameters: True
+
+PicoDet:
+  backbone: LCNet
+  neck: CSPPAN
+  head: PicoHead
+
+LCNet:
+  scale: 2.5
+  feature_maps: [3, 4, 5]
+
+CSPPAN:
+  spatial_scales: [0.125, 0.0625, 0.03125]
+
+slim: Distill
+slim_method: FGD
+distill_loss: FGDFeatureLoss
+distill_loss_name: ['neck_f_3', 'neck_f_2', 'neck_f_1', 'neck_f_0']
+
+FGDFeatureLoss:
+  student_channels: 128
+  teacher_channels: 128
+  temp: 0.5
+  alpha_fgd: 0.001
+  beta_fgd: 0.0005
+  gamma_fgd: 0.0005
+  lambda_fgd: 0.000005