add table layout (#2532)

* add table layout

* add layout rename

* zh to en

docs/module_usage/tutorials/ocr_modules/layout_detection.en.md

@@ -31,6 +31,14 @@ The core task of structure analysis is to parse and segment the content of input
 <td>An efficient layout area localization model trained on the PubLayNet dataset based on PicoDet-1x can locate five types of areas, including text, titles, tables, images, and lists.</td>
 </tr>
 <tr>
+<td>PicoDet_layout_1x_table</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b2/PicoDet_layout_1x_table_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PicoDet_layout_1x_table_pretrained.pdparams">Trained Model</a></td>
+<td>95.7</td>
+<td>12.623</td>
+<td>90.8934</td>
+<td>7.4 M</td>
+<td>An efficient layout area localization model trained on the PubLayNet dataset based on PicoDet-1x can locate one type of tables.</td>
+</tr>
+<tr>
 <td>PicoDet-S_layout_3cls</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b2/PicoDet-S_layout_3cls_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PicoDet-S_layout_3cls_pretrained.pdparams">Trained Model</a></td>
 <td>87.1</td>
 <td>13.5</td>

docs/module_usage/tutorials/ocr_modules/layout_detection.md

@@ -31,6 +31,14 @@ comments: true
 <td>基于PicoDet-1x在PubLayNet数据集训练的高效率版面区域定位模型，可定位包含文字、标题、表格、图片以及列表这5类区域</td>
 </tr>
 <tr>
+<td>PicoDet_layout_1x_table</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b2/PicoDet_layout_1x_table_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PicoDet_layout_1x_table_pretrained.pdparams">训练模型</a></td>
+<td>95.7</td>
+<td>12.623</td>
+<td>90.8934</td>
+<td>7.4 M</td>
+<td>基于PicoDet-1x在自建数据集训练的高效率版面区域定位模型，可定位包含表格这1类区域</td>
+</tr>
+<tr>
 <td>PicoDet-S_layout_3cls</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b2/PicoDet-S_layout_3cls_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PicoDet-S_layout_3cls_pretrained.pdparams">训练模型</a></td>
 <td>87.1</td>
 <td>13.5</td>

docs/pipeline_usage/tutorials/information_extraction_pipelines/document_scene_information_extraction.en.md

@@ -66,6 +66,14 @@ The <b>PP-ChatOCRv3-doc</b> pipeline includes modules for <b>Table Structure Rec
 <td>An efficient layout area localization model trained on the PubLayNet dataset based on PicoDet-1x can locate five types of areas, including text, titles, tables, images, and lists.</td>
 </tr>
 <tr>
+<td>PicoDet_layout_1x_table</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b2/PicoDet_layout_1x_table_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PicoDet_layout_1x_table_pretrained.pdparams">Trained Model</a></td>
+<td>95.7</td>
+<td>12.623</td>
+<td>90.8934</td>
+<td>7.4 M</td>
+<td>An efficient layout area localization model trained on the PubLayNet dataset based on PicoDet-1x can locate one type of tables.</td>
+</tr>
+<tr>
 <td>PicoDet-S_layout_3cls</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b2/PicoDet-S_layout_3cls_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PicoDet-S_layout_3cls_pretrained.pdparams">Trained Model</a></td>
 <td>87.1</td>
 <td>13.5</td>

docs/pipeline_usage/tutorials/information_extraction_pipelines/document_scene_information_extraction.md

@@ -66,6 +66,14 @@ comments: true
 <td>基于PicoDet-1x在PubLayNet数据集训练的高效率版面区域定位模型，可定位包含文字、标题、表格、图片以及列表这5类区域</td>
 </tr>
 <tr>
+<td>PicoDet_layout_1x_table</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b2/PicoDet_layout_1x_table_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PicoDet_layout_1x_table_pretrained.pdparams">训练模型</a></td>
+<td>95.7</td>
+<td>12.623</td>
+<td>90.8934</td>
+<td>7.4 M</td>
+<td>基于PicoDet-1x在自建数据集训练的高效率版面区域定位模型，可定位包含表格这1类区域</td>
+</tr>
+<tr>
 <td>PicoDet-S_layout_3cls</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b2/PicoDet-S_layout_3cls_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PicoDet-S_layout_3cls_pretrained.pdparams">训练模型</a></td>
 <td>87.1</td>
 <td>13.5</td>

docs/pipeline_usage/tutorials/ocr_pipelines/layout_parsing.en.md

@@ -64,6 +64,14 @@ The <b>General Layout Parsing Pipeline</b> includes modules for table structure
 <td>An efficient layout area localization model trained on the PubLayNet dataset based on PicoDet-1x can locate five types of areas, including text, titles, tables, images, and lists.</td>
 </tr>
 <tr>
+<td>PicoDet_layout_1x_table</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b2/PicoDet_layout_1x_table_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PicoDet_layout_1x_table_pretrained.pdparams">Trained Model</a></td>
+<td>95.7</td>
+<td>12.623</td>
+<td>90.8934</td>
+<td>7.4 M</td>
+<td>An efficient layout area localization model trained on the PubLayNet dataset based on PicoDet-1x can locate one type of tables.</td>
+</tr>
+<tr>
 <td>PicoDet-S_layout_3cls</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b2/PicoDet-S_layout_3cls_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PicoDet-S_layout_3cls_pretrained.pdparams">Trained Model</a></td>
 <td>87.1</td>
 <td>13.5</td>

docs/pipeline_usage/tutorials/ocr_pipelines/layout_parsing.md

@@ -64,6 +64,14 @@ comments: true
 <td>基于PicoDet-1x在PubLayNet数据集训练的高效率版面区域定位模型，可定位包含文字、标题、表格、图片以及列表这5类区域</td>
 </tr>
 <tr>
+<td>PicoDet_layout_1x_table</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b2/PicoDet_layout_1x_table_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PicoDet_layout_1x_table_pretrained.pdparams">训练模型</a></td>
+<td>95.7</td>
+<td>12.623</td>
+<td>90.8934</td>
+<td>7.4 M</td>
+<td>基于PicoDet-1x在自建数据集训练的高效率版面区域定位模型，可定位包含表格这1类区域</td>
+</tr>
+<tr>
 <td>PicoDet-S_layout_3cls</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b2/PicoDet-S_layout_3cls_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PicoDet-S_layout_3cls_pretrained.pdparams">训练模型</a></td>
 <td>87.1</td>
 <td>13.5</td>

docs/pipeline_usage/tutorials/ocr_pipelines/seal_recognition.en.md

@@ -36,6 +36,14 @@ The <b>Seal Recognition</b> pipeline includes a layout area analysis module, a s
 <td>An efficient layout area localization model trained on the PubLayNet dataset based on PicoDet-1x can locate five types of areas, including text, titles, tables, images, and lists.</td>
 </tr>
 <tr>
+<td>PicoDet_layout_1x_table</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b2/PicoDet_layout_1x_table_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PicoDet_layout_1x_table_pretrained.pdparams">Trained Model</a></td>
+<td>95.7</td>
+<td>12.623</td>
+<td>90.8934</td>
+<td>7.4 M</td>
+<td>An efficient layout area localization model trained on the PubLayNet dataset based on PicoDet-1x can locate one type of tables.</td>
+</tr>
+<tr>
 <td>PicoDet-S_layout_3cls</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b2/PicoDet-S_layout_3cls_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PicoDet-S_layout_3cls_pretrained.pdparams">Trained Model</a></td>
 <td>87.1</td>
 <td>13.5</td>

docs/pipeline_usage/tutorials/ocr_pipelines/seal_recognition.md

@@ -38,6 +38,14 @@ comments: true
 <td>基于PicoDet-1x在PubLayNet数据集训练的高效率版面区域定位模型，可定位包含文字、标题、表格、图片以及列表这5类区域</td>
 </tr>
 <tr>
+<td>PicoDet_layout_1x_table</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b2/PicoDet_layout_1x_table_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PicoDet_layout_1x_table_pretrained.pdparams">训练模型</a></td>
+<td>95.7</td>
+<td>12.623</td>
+<td>90.8934</td>
+<td>7.4 M</td>
+<td>基于PicoDet-1x在自建数据集训练的高效率版面区域定位模型，可定位包含表格这1类区域</td>
+</tr>
+<tr>
 <td>PicoDet-S_layout_3cls</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b2/PicoDet-S_layout_3cls_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PicoDet-S_layout_3cls_pretrained.pdparams">训练模型</a></td>
 <td>87.1</td>
 <td>13.5</td>

docs/pipeline_usage/tutorials/ocr_pipelines/table_recognition.en.md

@@ -70,6 +70,14 @@ SLANet_plus is an enhanced version of SLANet, a table structure recognition mode
 <td>An efficient layout area localization model trained on the PubLayNet dataset based on PicoDet-1x can locate five types of areas, including text, titles, tables, images, and lists.</td>
 </tr>
 <tr>
+<td>PicoDet_layout_1x_table</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b2/PicoDet_layout_1x_table_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PicoDet_layout_1x_table_pretrained.pdparams">Trained Model</a></td>
+<td>95.7</td>
+<td>12.623</td>
+<td>90.8934</td>
+<td>7.4 M</td>
+<td>An efficient layout area localization model trained on the PubLayNet dataset based on PicoDet-1x can locate one type of tables.</td>
+</tr>
+<tr>
 <td>PicoDet-S_layout_3cls</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b2/PicoDet-S_layout_3cls_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PicoDet-S_layout_3cls_pretrained.pdparams">Trained Model</a></td>
 <td>87.1</td>
 <td>13.5</td>

docs/pipeline_usage/tutorials/ocr_pipelines/table_recognition.md

@@ -65,6 +65,14 @@ comments: true
 <td>基于PicoDet-1x在PubLayNet数据集训练的高效率版面区域定位模型，可定位包含文字、标题、表格、图片以及列表这5类区域</td>
 </tr>
 <tr>
+<td>PicoDet_layout_1x_table</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b2/PicoDet_layout_1x_table_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PicoDet_layout_1x_table_pretrained.pdparams">训练模型</a></td>
+<td>95.7</td>
+<td>12.623</td>
+<td>90.8934</td>
+<td>7.4 M</td>
+<td>基于PicoDet-1x在自建数据集训练的高效率版面区域定位模型，可定位包含表格这1类区域</td>
+</tr>
+<tr>
 <td>PicoDet-S_layout_3cls</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b2/PicoDet-S_layout_3cls_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PicoDet-S_layout_3cls_pretrained.pdparams">训练模型</a></td>
 <td>87.1</td>
 <td>13.5</td>

docs/practical_tutorials/document_scene_information_extraction(layout_detection)_tutorial.en.md

@@ -109,6 +109,14 @@ PaddleX provides 4 end-to-end layout detection models, which can be referenced i
 <td>An efficient layout area localization model trained on the PubLayNet dataset based on PicoDet-1x can locate five types of areas, including text, titles, tables, images, and lists.</td>
 </tr>
 <tr>
+<td>PicoDet_layout_1x_table</td>
+<td>95.7</td>
+<td>12.623</td>
+<td>90.8934</td>
+<td>7.4 M</td>
+<td>An efficient layout area localization model trained on the PubLayNet dataset based on PicoDet-1x can locate one type of tables.</td>
+</tr>
+<tr>
 <td>PicoDet-S_layout_3cls</td>
 <td>87.1</td>
 <td>13.5</td>

docs/practical_tutorials/document_scene_information_extraction(layout_detection)_tutorial.md

@@ -114,6 +114,14 @@ PaddleX 提供了 4 个端到端的版面区域定位模型，具体可参考 [
 <td>基于PicoDet-1x在PubLayNet数据集训练的高效率版面区域定位模型，可定位包含文字、标题、表格、图片以及列表这5类区域</td>
 </tr>
 <tr>
+<td>PicoDet_layout_1x_table</td>
+<td>95.7</td>
+<td>12.623</td>
+<td>90.8934</td>
+<td>7.4 M</td>
+<td>基于PicoDet-1x在自建数据集训练的高效率版面区域定位模型，可定位包含表格1个类别</td>
+</tr>
+<tr>
 <td>PicoDet-S_layout_3cls</td>
 <td>87.1</td>
 <td>13.5</td>

docs/support_list/models_list.en.md

@@ -1963,6 +1963,14 @@ PaddleX incorporates multiple pipelines, each containing several modules, and ea
 <td><a href="https://github.com/PaddlePaddle/PaddleX/blob/develop/paddlex/configs/layout_detection/PicoDet_layout_1x.yaml">PicoDet_layout_1x.yaml</a></td>
 <td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b2/PicoDet_layout_1x_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PicoDet_layout_1x_pretrained.pdparams">Trained Model</a></td></tr>
 <tr>
+<td>PicoDet_layout_1x_table</td>
+<td>95.7</td>
+<td>12.623</td>
+<td>90.8934</td>
+<td>7.4 M</td>
+<td><a href="https://github.com/PaddlePaddle/PaddleX/blob/develop/paddlex/configs/layout_detection/PicoDet_layout_1x_table.yaml">PicoDet_layout_1x_table.yaml</a></td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b2/PicoDet_layout_1x_table_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PicoDet_layout_1x_table_pretrained.pdparams">Trained Model</a></td></tr>
+<tr>
 <td>PicoDet-S_layout_3cls</td>
 <td>87.1</td>
 <td>13.521</td>

docs/support_list/models_list.md

@@ -1961,6 +1961,14 @@ PaddleX 内置了多条产线，每条产线都包含了若干模块，每个模
 <td><a href="https://github.com/PaddlePaddle/PaddleX/blob/develop/paddlex/configs/layout_detection/PicoDet_layout_1x.yaml">PicoDet_layout_1x.yaml</a></td>
 <td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b2/PicoDet_layout_1x_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PicoDet_layout_1x_pretrained.pdparams">训练模型</a></td></tr>
 <tr>
+<td>PicoDet_layout_1x_table</td>
+<td>95.7</td>
+<td>12.623</td>
+<td>90.8934</td>
+<td>7.4 M</td>
+<td><a href="https://github.com/PaddlePaddle/PaddleX/blob/develop/paddlex/configs/layout_detection/PicoDet_layout_1x_table.yaml">PicoDet_layout_1x_table.yaml</a></td>
+<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b2/PicoDet_layout_1x_table_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PicoDet_layout_1x_table_pretrained.pdparams">训练模型</a></td></tr>
+<tr>
 <td>PicoDet-S_layout_3cls</td>
 <td>87.1</td>
 <td>13.521</td>

paddlex/configs/layout_detection/PicoDet_layout_1x_table.yaml

@@ -0,0 +1,40 @@
+Global:
+  model: PicoDet_layout_1x_table
+  mode: check_dataset # check_dataset/train/evaluate/predict
+  dataset_dir: "/paddle/dataset/paddlex/layout/det_layout_examples"
+  device: gpu:0,1,2,3
+  output: "output"
+
+CheckDataset:
+  convert:
+    enable: False
+    src_dataset_type: null
+  split:
+    enable: False
+    train_percent: null
+    val_percent: null
+
+Train:
+  num_classes: 11
+  epochs_iters: 50
+  batch_size: 24
+  learning_rate: 0.4
+  pretrain_weight_path: https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PicoDet_layout_1x_table_pretrained.pdparams
+  warmup_steps: 100
+  resume_path: null
+  log_interval: 1
+  eval_interval: 1
+
+Evaluate:
+  weight_path: "output/best_model/best_model.pdparams"
+  log_interval: 10
+
+Export:
+  weight_path: https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PicoDet_layout_1x_table_pretrained.pdparams
+
+Predict:
+  batch_size: 1
+  model_dir: "output/best_model/inference"
+  input: "https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/layout.jpg"
+  kernel_option:
+    run_mode: paddle

paddlex/inference/utils/official_models.py

@@ -211,6 +211,7 @@ PP-LCNet_x1_0_pedestrian_attribute_infer.tar",
     "PP-LCNet_x1_0_vehicle_attribute": "https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b2/\
 PP-LCNet_x1_0_vehicle_attribute_infer.tar",
     "PicoDet_layout_1x": "https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b2/PicoDet_layout_1x_infer.tar",
+    "PicoDet_layout_1x_table": "https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b2/PicoDet_layout_1x_table_infer.tar",
     "SLANet": "https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b2/SLANet_infer.tar",
     "SLANet_plus": "https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b2/SLANet_plus_infer.tar",
     "LaTeX_OCR_rec": "https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0b2/LaTeX_OCR_rec_infer.tar",

paddlex/modules/object_detection/model_list.py

@@ -26,6 +26,7 @@ MODELS = [
     "RT-DETR-R50",
     "RT-DETR-X",
     "PicoDet_layout_1x",
+    "PicoDet_layout_1x_table",
     "PicoDet-S_layout_3cls",
     "PicoDet-S_layout_17cls",
     "PicoDet-L_layout_3cls",

paddlex/pipelines/table_recognition.yaml

@@ -3,7 +3,7 @@ Global:
   input: https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/table_recognition.jpg
   
 Pipeline:
-  layout_model: PicoDet_layout_1x
+  layout_model: PicoDet_layout_1x_table
   table_model: SLANet_plus
   text_det_model: PP-OCRv4_mobile_det
   text_rec_model: PP-OCRv4_mobile_rec

paddlex/repo_apis/PaddleDetection_api/configs/PicoDet_layout_1x_table.yaml

@@ -0,0 +1,159 @@
+# Runtime
+epoch: 50
+log_iter: 1
+find_unused_parameters: true
+use_gpu: true
+use_xpu: false
+use_mlu: false
+use_npu: false
+use_ema: true
+save_dir: output
+snapshot_epoch: 1
+cycle_epoch: 10
+print_flops: false
+print_params: false
+
+# Dataset
+metric: COCO
+num_classes: 5
+
+worker_num: 8
+
+TrainDataset:
+  name: COCODetDataset
+  image_dir: images
+  anno_path: annotations/instance_train.json
+  dataset_dir: datasets/COCO
+  data_fields: ['image', 'gt_bbox', 'gt_class', 'is_crowd']
+
+EvalDataset:
+  name: COCODetDataset
+  image_dir: images
+  anno_path: annotations/instance_val.json
+  dataset_dir: datasets/COCO
+  allow_empty: true
+
+TestDataset:
+  name: ImageFolder
+  anno_path: annotations/instance_val.json
+  dataset_dir: datasets/COCO
+
+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: [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
+
+# Model
+architecture: PicoDet
+pretrain_weights: https://paddleocr.bj.bcebos.com/ppstructure/models/layout/picodet_lcnet_x1_0_fgd_layout.pdparams
+
+PicoDet:
+  backbone: LCNet
+  neck: CSPPAN
+  head: PicoHead
+  nms_cpu: true
+
+LCNet:
+  scale: 1.0
+  feature_maps: [3, 4, 5]
+
+CSPPAN:
+  out_channels: 128
+  use_depthwise: True
+  num_csp_blocks: 1
+  num_features: 4
+
+PicoHead:
+  conv_feat:
+    name: PicoFeat
+    feat_in: 128
+    feat_out: 128
+    num_convs: 4
+    num_fpn_stride: 4
+    norm_type: bn
+    share_cls_reg: True
+  fpn_stride: [8, 16, 32, 64]
+  feat_in_chan: 128
+  prior_prob: 0.01
+  reg_max: 7
+  cell_offset: 0.5
+  loss_class:
+    name: VarifocalLoss
+    use_sigmoid: True
+    iou_weighted: True
+    loss_weight: 1.0
+  loss_dfl:
+    name: DistributionFocalLoss
+    loss_weight: 0.25
+  loss_bbox:
+    name: GIoULoss
+    loss_weight: 2.0
+  assigner:
+    name: SimOTAAssigner
+    candidate_topk: 10
+    iou_weight: 6
+  nms:
+    name: MultiClassNMS
+    nms_top_k: 1000
+    keep_top_k: 100
+    score_threshold: 0.025
+    nms_threshold: 0.6
+
+# Optimizer
+LearningRate:
+  base_lr: 0.4
+  schedulers:
+  - name: CosineDecay
+    max_epochs: 100
+  - name: LinearWarmup
+    start_factor: 0.1
+    steps: 100
+
+OptimizerBuilder:
+  optimizer:
+    momentum: 0.9
+    type: Momentum
+  regularizer:
+    factor: 0.00004
+    type: L2
+
+# Export
+export:
+  post_process: true
+  nms: true
+  benchmark: false
+  fuse_conv_bn: false

paddlex/repo_apis/PaddleDetection_api/object_det/official_categories.py

@@ -25,6 +25,9 @@ official_categories = {
         {"name": "Table", "id": 3},
         {"name": "Figure", "id": 4},
     ],
+    "PicoDet_layout_1x_table": [
+        {"name": "Table", "id": 0},
+    ],
     "PicoDet-S_layout_3cls": [
         {"name": "image", "id": 0},
         {"name": "table", "id": 1},

paddlex/repo_apis/PaddleDetection_api/object_det/register.py

@@ -219,6 +219,21 @@ register_model_info(
 
 register_model_info(
     {
+        "model_name": "PicoDet_layout_1x_table",
+        "suite": "Det",
+        "config_path": osp.join(PDX_CONFIG_DIR, "PicoDet_layout_1x_table.yaml"),
+        "supported_apis": ["train", "evaluate", "predict", "export"],
+        "supported_dataset_types": ["COCODetDataset"],
+        "supported_train_opts": {
+            "device": ["cpu", "gpu_nxcx", "xpu", "npu", "mlu"],
+            "dy2st": False,
+            "amp": ["OFF"],
+        },
+    }
+)
+
+register_model_info(
+    {
         "model_name": "YOLOv3-DarkNet53",
         "suite": "Det",
         "config_path": osp.join(PDX_CONFIG_DIR, "YOLOv3-DarkNet53.yaml"),