paddlex 3.0.0b2__py3-none-any.whl → 3.0.0rc1__py3-none-any.whl

paddlex/configs/pipelines/PP-ChatOCRv4-doc.yaml

@@ -0,0 +1,184 @@
+
+pipeline_name: PP-ChatOCRv4-doc
+
+use_layout_parser: True
+
+use_mllm_predict: True
+
+SubModules:
+  LLM_Chat:
+    module_name: chat_bot
+    model_name: ernie-3.5-8k
+    base_url: "https://qianfan.baidubce.com/v2"
+    api_type: openai
+    api_key: "api_key" # Set this to a real API key
+
+  LLM_Retriever:
+    module_name: retriever
+    model_name: embedding-v1
+    base_url: "https://qianfan.baidubce.com/v2"
+    api_type: qianfan
+    api_key: "api_key" # Set this to a real API key
+
+  MLLM_Chat:
+    module_name: chat_bot
+    model_name: PP-DocBee
+    base_url: "http://127.0.0.1:8080/v1/chat/completions"
+    api_type: openai
+    api_key: "api_key"
+
+  PromptEngneering:
+    KIE_CommonText:
+      module_name: prompt_engneering
+
+      task_type: text_kie_prompt_v2
+
+      task_description: '你现在的任务是从OCR结果中提取问题列表中每一个问题的答案。
+          OCR的文字识别结果使用```符号包围，包含所识别出来的文字，顺序在原始图片中从左至右、从上至下。
+          我指定的问题列表使用[]符号包围。请注意OCR的文字识别结果可能存在长句子换行被切断、不合理的分词、
+          文字被错误合并等问题，你需要结合上下文语义进行综合判断，以获取准确的答案。'
+
+      output_format: '在返回结果时使用JSON格式，包含多个key-value对，key值为我指定的问题，value值为该问题对应的答案。
+          如果认为OCR识别结果中，对于问题key，没有答案，则将value赋值为"未知"。请只输出json格式的结果，
+          并做json格式校验后返回，不要包含其它多余文字！'
+
+      rules_str: '请依次确认满足下面要求。（1）每个问题的答案用OCR结果的内容回答，针对问题回答尽可能详细和完整，
+          并保持格式、数字、正负号、单位、符号和标点都与OCR结果中的内容完全一致。
+          （2）如果答案的句末有标点符号，请添加标点符号。
+          （3）对于答案中的数字，如果可以推断出单位，请补充相应的单位。'
+
+      few_shot_demo_text_content:
+
+      few_shot_demo_key_value_list:
+          
+    KIE_Table:
+      module_name: prompt_engneering
+
+      task_type: table_kie_prompt_v2
+
+      task_description: '你现在的任务是从输入的html格式的表格内容中提取问题列表中每一个问题的答案。
+          表格内容使用```符号包围，我指定的问题列表使用[]符号包围。'
+
+      output_format: '在返回结果时使用JSON格式，包含多个key-value对，key值为我指定的问题，value值为该问题对应的答案。
+          如果认为表格内容中，对于问题key，没有答案，则将value赋值为"未知"。请只输出json格式的结果，
+          并做json格式校验后返回，不要包含其它多余文字！'
+
+      rules_str: '请依次确认满足下面要求。（1）每个问题的答案用表格内容回答，针对问题回答尽可能详细和完整，
+          并保持格式、数字、正负号、单位、符号和标点都与表格内容完全一致。
+          （2）对于答案中的数字，如果可以推断出单位，请补充相应的单位。
+          （3）如果答案是百分比，请添加百分号。'
+
+      few_shot_demo_text_content:
+
+      few_shot_demo_key_value_list:
+    
+    Ensemble:
+      module_name: prompt_engneering
+
+      task_type: ensemble_prompt
+
+      task_description: '你现在的任务是，对于一个问题，对比方法A和方法B的结果，选择更准确的一个回答。
+        问题用```符号包围。'
+
+      output_format: '请返回JSON格式的结果，包含多个key-value对，key值为我指定的问题，
+        value值为`方法A`或`方法B`。如果对于问题key，没有找到答案，将value赋值为"未知"。
+        请只输出json格式的结果，并做json格式校验后返回，不要包含其它多余文字！'
+
+      rules_str: '对于涉及数字的问题，请返回与问题描述最相关且数字表述正确的答案。
+        请特别注意数字中的标点使用是否合理。'
+
+      few_shot_demo_text_content:
+
+      few_shot_demo_key_value_list:
+
+SubPipelines:
+  LayoutParser:
+    pipeline_name: layout_parsing
+
+    use_doc_preprocessor: True
+    use_general_ocr: True
+    use_seal_recognition: True
+    use_table_recognition: True
+    use_formula_recognition: False
+
+    SubModules:
+      LayoutDetection:
+        module_name: layout_detection
+        model_name: RT-DETR-H_layout_3cls
+        model_dir: null
+
+    SubPipelines:
+      DocPreprocessor:
+        pipeline_name: doc_preprocessor
+        use_doc_orientation_classify: True
+        use_doc_unwarping: True
+        SubModules:
+          DocOrientationClassify:
+            module_name: doc_text_orientation
+            model_name: PP-LCNet_x1_0_doc_ori
+            model_dir: null
+          DocUnwarping:
+            module_name: image_unwarping
+            model_name: UVDoc
+            model_dir: null
+
+      GeneralOCR:
+        pipeline_name: OCR
+        text_type: general
+        use_doc_preprocessor: False
+        use_textline_orientation: False
+        SubModules:
+          TextDetection:
+            module_name: text_detection
+            model_name: PP-OCRv4_server_det
+            model_dir: null
+            limit_side_len: 960
+            limit_type: max
+            thresh: 0.3
+            box_thresh: 0.6
+            unclip_ratio: 2.0
+            
+          TextRecognition:
+            module_name: text_recognition
+            model_name: PP-OCRv4_server_rec_doc
+            model_dir: null
+            batch_size: 6
+            score_thresh: 0.0
+
+      TableRecognition:
+        pipeline_name: table_recognition
+        use_layout_detection: False
+        use_doc_preprocessor: False
+        use_ocr_model: False
+        SubModules:
+          TableStructureRecognition:
+            module_name: table_structure_recognition
+            model_name: SLANet_plus
+            model_dir: null
+
+      SealRecognition:
+        pipeline_name: seal_recognition
+        use_layout_detection: False
+        use_doc_preprocessor: False
+        SubPipelines:
+          SealOCR:
+            pipeline_name: OCR
+            text_type: seal
+            use_doc_preprocessor: False
+            use_textline_orientation: False
+            SubModules:
+              TextDetection:
+                module_name: seal_text_detection
+                model_name: PP-OCRv4_server_seal_det
+                model_dir: null
+                limit_side_len: 736
+                limit_type: min
+                thresh: 0.2
+                box_thresh: 0.6
+                unclip_ratio: 0.5
+              TextRecognition:
+                module_name: text_recognition
+                model_name: PP-OCRv4_server_rec_doc
+                model_dir: null
+                batch_size: 1
+                score_thresh: 0

paddlex/configs/pipelines/PP-ShiTuV2.yaml

@@ -0,0 +1,18 @@
+pipeline_name: PP-ShiTuV2
+
+index: None
+det_threshold: 0.5
+rec_threshold: 0.5
+rec_topk: 5
+
+SubModules:
+  Detection:
+    module_name: text_detection
+    model_name: PP-ShiTuV2_det
+    model_dir: null
+    batch_size: 1    
+  Recognition:
+    module_name: text_recognition
+    model_name: PP-ShiTuV2_rec
+    model_dir: null
+    batch_size: 1

paddlex/configs/pipelines/PP-StructureV3.yaml

@@ -0,0 +1,226 @@
+
+pipeline_name: PP-StructureV3
+
+use_doc_preprocessor: True
+use_general_ocr: True
+use_seal_recognition: True
+use_table_recognition: True
+use_formula_recognition: True
+
+SubModules:
+  LayoutDetection:
+    module_name: layout_detection
+    model_name: PP-DocLayout-L
+    model_dir: null
+    threshold: 
+      0: 0.3  # paragraph_title
+      1: 0.5  # image
+      2: 0.5  # text
+      3: 0.5  # number
+      4: 0.5  # abstract
+      5: 0.5  # content
+      6: 0.5  # figure_title
+      7: 0.3  # formula
+      8: 0.5  # table
+      9: 0.5  # table_title
+      10: 0.5 # reference
+      11: 0.5 # doc_title
+      12: 0.5 # footnote
+      13: 0.5 # header
+      14: 0.5 # algorithm
+      15: 0.5 # footer
+      16: 0.3 # seal
+      17: 0.5 # chart_title
+      18: 0.5 # chart
+      19: 0.5 # formula_number
+      20: 0.5 # header_image
+      21: 0.5 # footer_image
+      22: 0.5 # aside_text
+    layout_nms: True
+    layout_unclip_ratio:
+      0: [1.0, 1.0]  # paragraph_title
+      1: [1.0, 1.0]  # image
+      2: [1.0, 1.0]  # text
+      3: [1.0, 1.0]  # number
+      4: [1.0, 1.0]  # abstract
+      5: [1.0, 1.0]  # content
+      6: [1.0, 1.0]  # figure_title
+      7: [1.0, 1.0]  # formula
+      8: [1.0, 1.0]  # table
+      9: [1.0, 1.0]  # table_title
+      10: [1.0, 1.0] # reference
+      11: [1.0, 1.0] # doc_title
+      12: [1.0, 1.0] # footnote
+      13: [1.0, 1.0] # header
+      14: [1.0, 1.0] # algorithm
+      15: [1.0, 1.0] # footer
+      16: [1.0, 1.0] # seal
+      17: [1.0, 1.0] # chart_title
+      18: [1.0, 1.0] # chart
+      19: [1.0, 1.0] # formula_number
+      20: [1.0, 1.0] # header_image
+      21: [1.0, 1.0] # footer_image
+      22: [1.0, 1.0] # aside_text
+    layout_merge_bboxes_mode: 
+      0: "large"  # paragraph_title
+      1: "large"  # image
+      2: "union"  # text
+      3: "union"  # number
+      4: "union"  # abstract
+      5: "union"  # content
+      6: "union"  # figure_title
+      7: "large"  # formula
+      8: "union"  # table
+      9: "union"  # table_title
+      10: "union" # reference
+      11: "union" # doc_title
+      12: "union" # footnote
+      13: "union" # header
+      14: "union" # algorithm
+      15: "union" # footer
+      16: "union" # seal
+      17: "union" # chart_title
+      18: "large" # chart
+      19: "union" # formula_number
+      20: "union" # header_image
+      21: "union" # footer_image
+      22: "union" # aside_text
+
+SubPipelines:
+  DocPreprocessor:
+    pipeline_name: doc_preprocessor
+    use_doc_orientation_classify: True
+    use_doc_unwarping: True
+    SubModules:
+      DocOrientationClassify:
+        module_name: doc_text_orientation
+        model_name: PP-LCNet_x1_0_doc_ori
+        model_dir: null
+      DocUnwarping:
+        module_name: image_unwarping
+        model_name: UVDoc
+        model_dir: null
+
+  GeneralOCR:
+    pipeline_name: OCR
+    text_type: general
+    use_doc_preprocessor: False
+    use_textline_orientation: True
+    SubModules:
+      TextDetection:
+        module_name: text_detection
+        model_name: PP-OCRv4_server_det
+        model_dir: null
+        limit_side_len: 736
+        limit_type: min
+        thresh: 0.3
+        box_thresh: 0.6
+        unclip_ratio: 1.5
+      TextLineOrientation:
+        module_name: textline_orientation
+        model_name: PP-LCNet_x0_25_textline_ori
+        model_dir: null
+        batch_size: 1 
+      TextRecognition:
+        module_name: text_recognition
+        model_name: PP-OCRv4_server_rec_doc
+        model_dir: null
+        batch_size: 6
+        score_thresh: 0.0
+ 
+
+  TableRecognition:
+    pipeline_name: table_recognition_v2
+    use_layout_detection: False
+    use_doc_preprocessor: False
+    use_ocr_model: False
+    SubModules:  
+      TableClassification:
+        module_name: table_classification
+        model_name: PP-LCNet_x1_0_table_cls
+        model_dir: null
+
+      WiredTableStructureRecognition:
+        module_name: table_structure_recognition
+        model_name: SLANeXt_wired
+        model_dir: null
+      
+      WirelessTableStructureRecognition:
+        module_name: table_structure_recognition
+        model_name: SLANet_plus
+        model_dir: null
+      
+      WiredTableCellsDetection:
+        module_name: table_cells_detection
+        model_name: RT-DETR-L_wired_table_cell_det
+        model_dir: null
+      
+      WirelessTableCellsDetection:
+        module_name: table_cells_detection
+        model_name: RT-DETR-L_wireless_table_cell_det
+        model_dir: null
+    SubPipelines:
+      GeneralOCR:
+        pipeline_name: OCR
+        text_type: general
+        use_doc_preprocessor: False
+        use_textline_orientation: True
+        SubModules:
+          TextDetection:
+            module_name: text_detection
+            model_name: PP-OCRv4_server_det
+            model_dir: null
+            limit_side_len: 736
+            limit_type: min
+            thresh: 0.3
+            box_thresh: 0.4
+            unclip_ratio: 2.0
+          TextLineOrientation:
+            module_name: textline_orientation
+            model_name: PP-LCNet_x0_25_textline_ori
+            model_dir: null
+            batch_size: 1 
+          TextRecognition:
+            module_name: text_recognition
+            model_name: PP-OCRv4_server_rec_doc
+            model_dir: null
+            batch_size: 6
+        score_thresh: 0.0
+
+  SealRecognition:
+    pipeline_name: seal_recognition
+    use_layout_detection: False
+    use_doc_preprocessor: False
+    SubPipelines:
+      SealOCR:
+        pipeline_name: OCR
+        text_type: seal
+        use_doc_preprocessor: False
+        use_textline_orientation: False
+        SubModules:
+          TextDetection:
+            module_name: seal_text_detection
+            model_name: PP-OCRv4_server_seal_det
+            model_dir: null
+            limit_side_len: 736
+            limit_type: min
+            thresh: 0.2
+            box_thresh: 0.6
+            unclip_ratio: 0.5
+          TextRecognition:
+            module_name: text_recognition
+            model_name: PP-OCRv4_server_rec
+            model_dir: null
+            batch_size: 1
+            score_thresh: 0
+    
+  FormulaRecognition:
+    pipeline_name: formula_recognition
+    use_layout_detection: False
+    use_doc_preprocessor: False
+    SubModules:
+      FormulaRecognition:
+        module_name: formula_recognition
+        model_name: PP-FormulaNet-L
+        model_dir: null
+        batch_size: 5

paddlex/configs/pipelines/anomaly_detection.yaml

@@ -0,0 +1,8 @@
+pipeline_name: anomaly_detection
+
+SubModules:
+  AnomalyDetection:
+    module_name: anomaly_detection
+    model_name: STFPM
+    model_dir: null
+    batch_size: 1   

paddlex/configs/pipelines/doc_preprocessor.yaml

@@ -0,0 +1,15 @@
+
+pipeline_name: doc_preprocessor
+
+use_doc_orientation_classify: True
+use_doc_unwarping: True
+
+SubModules:
+  DocOrientationClassify:
+    module_name: doc_text_orientation
+    model_name: PP-LCNet_x1_0_doc_ori
+    model_dir: null
+  DocUnwarping:
+    module_name: image_unwarping
+    model_name: UVDoc
+    model_dir: null

paddlex/configs/pipelines/doc_understanding.yaml

@@ -0,0 +1,9 @@
+
+pipeline_name: doc_understanding
+
+SubModules:
+  DocUnderstanding:
+    module_name: doc_vlm
+    model_name: PP-DocBee-2B
+    model_dir: null
+    batch_size: 1

paddlex/configs/pipelines/face_recognition.yaml

@@ -0,0 +1,18 @@
+pipeline_name: face_recognition
+
+index: None
+det_threshold: 0.6
+rec_threshold: 0.4
+rec_topk: 5
+
+SubModules:
+  Detection:
+    module_name: face_detection
+    model_name: PP-YOLOE_plus-S_face
+    model_dir: null
+    batch_size: 1 
+  Recognition:
+    module_name: face_feature
+    model_name: ResNet50_face
+    model_dir: null
+    batch_size: 1

paddlex/configs/pipelines/formula_recognition.yaml

@@ -0,0 +1,39 @@
+
+pipeline_name: formula_recognition
+
+use_layout_detection: True
+use_doc_preprocessor: True
+
+SubModules:
+  LayoutDetection:
+    module_name: layout_detection
+    model_name: PP-DocLayout-L
+    model_dir: null
+    threshold: 0.5
+    layout_nms: True
+    layout_unclip_ratio: 1.0
+    layout_merge_bboxes_mode: "large"
+    batch_size: 1
+
+  FormulaRecognition:
+    module_name: formula_recognition
+    model_name: PP-FormulaNet-L
+    model_dir: null
+    batch_size: 5
+
+SubPipelines:
+  DocPreprocessor:
+    pipeline_name: doc_preprocessor
+    use_doc_orientation_classify: True
+    use_doc_unwarping: True
+    SubModules:
+      DocOrientationClassify:
+        module_name: doc_text_orientation
+        model_name: PP-LCNet_x1_0_doc_ori
+        model_dir: null
+        batch_size: 1
+      DocUnwarping:
+        module_name: image_unwarping
+        model_name: UVDoc
+        model_dir: null
+        batch_size: 1

paddlex/configs/pipelines/human_keypoint_detection.yaml

@@ -0,0 +1,17 @@
+pipeline_name: human_keypoint_detection
+
+SubModules:
+  ObjectDetection:
+    module_name: object_detection
+    model_name: PP-YOLOE-S_human
+    model_dir: null
+    batch_size: 1
+    threshold: null
+    img_size: null
+  KeypointDetection:
+    module_name: keypoint_detection
+    model_name: PP-TinyPose_128x96
+    model_dir: null
+    batch_size: 1
+    flip: False
+    use_udp: null

paddlex/configs/pipelines/image_classification.yaml

@@ -0,0 +1,10 @@
+
+pipeline_name: image_classification
+
+SubModules:
+  ImageClassification:
+    module_name: image_classification
+    model_name: PP-LCNet_x0_5
+    model_dir: null
+    batch_size: 4
+    topk: 5 

paddlex/configs/pipelines/image_multilabel_classification.yaml

@@ -0,0 +1,9 @@
+
+pipeline_name: image_multilabel_classification
+
+SubModules:
+  ImageMultiLabelClassification:
+    module_name: image_multilabel_classification
+    model_name: PP-HGNetV2-B6_ML
+    model_dir: null
+    batch_size: 4    

paddlex/configs/pipelines/instance_segmentation.yaml

@@ -0,0 +1,10 @@
+
+pipeline_name: instance_segmentation
+
+SubModules:
+  InstanceSegmentation:
+    module_name: instance_segmentation
+    model_name: Mask-RT-DETR-S
+    model_dir: null
+    batch_size: 1
+    threshold: 0.5

paddlex/configs/pipelines/layout_parsing.yaml

@@ -0,0 +1,101 @@
+
+pipeline_name: layout_parsing
+
+use_doc_preprocessor: True
+use_general_ocr: True
+use_seal_recognition: True
+use_table_recognition: True
+use_formula_recognition: False
+
+SubModules:
+  LayoutDetection:
+    module_name: layout_detection
+    model_name: RT-DETR-H_layout_17cls
+    model_dir: null
+
+SubPipelines:
+  DocPreprocessor:
+    pipeline_name: doc_preprocessor
+    use_doc_orientation_classify: True
+    use_doc_unwarping: True
+    SubModules:
+      DocOrientationClassify:
+        module_name: doc_text_orientation
+        model_name: PP-LCNet_x1_0_doc_ori
+        model_dir: null
+      DocUnwarping:
+        module_name: image_unwarping
+        model_name: UVDoc
+        model_dir: null
+
+  GeneralOCR:
+    pipeline_name: OCR
+    text_type: general
+    use_doc_preprocessor: False
+    use_textline_orientation: False
+    SubModules:
+      TextDetection:
+        module_name: text_detection
+        model_name: PP-OCRv4_server_det
+        model_dir: null
+        limit_side_len: 960
+        limit_type: max
+        thresh: 0.3
+        box_thresh: 0.6
+        unclip_ratio: 2.0
+        
+      TextRecognition:
+        module_name: text_recognition
+        model_name: PP-OCRv4_server_rec
+        model_dir: null
+        batch_size: 6
+        score_thresh: 0
+
+  TableRecognition:
+    pipeline_name: table_recognition
+    use_layout_detection: False
+    use_doc_preprocessor: False
+    use_ocr_model: False
+    SubModules:
+      TableStructureRecognition:
+        module_name: table_structure_recognition
+        model_name: SLANet_plus
+        model_dir: null
+
+  SealRecognition:
+    pipeline_name: seal_recognition
+    use_layout_detection: False
+    use_doc_preprocessor: False
+    SubPipelines:
+      SealOCR:
+        pipeline_name: OCR
+        text_type: seal
+        use_doc_preprocessor: False
+        use_textline_orientation: False
+        SubModules:
+          TextDetection:
+            module_name: seal_text_detection
+            model_name: PP-OCRv4_server_seal_det
+            model_dir: null
+            limit_side_len: 736
+            limit_type: min
+            thresh: 0.2
+            box_thresh: 0.6
+            unclip_ratio: 0.5
+          TextRecognition:
+            module_name: text_recognition
+            model_name: PP-OCRv4_server_rec
+            model_dir: null
+            batch_size: 1
+            score_thresh: 0
+    
+  FormulaRecognition:
+    pipeline_name: formula_recognition
+    use_layout_detection: False
+    use_doc_preprocessor: False
+    SubModules:
+      FormulaRecognition:
+        module_name: formula_recognition
+        model_name: PP-FormulaNet-L
+        model_dir: null
+        batch_size: 5

paddlex/configs/pipelines/multilingual_speech_recognition.yaml

@@ -0,0 +1,9 @@
+
+pipeline_name: multilingual_speech_recognition
+
+SubModules:
+  MultilingualSpeechRecognition:
+    module_name: multilingual_speech_recognition
+    model_name: whisper_large
+    model_dir: null
+    batch_size: 1   

paddlex/configs/pipelines/object_detection.yaml

@@ -0,0 +1,10 @@
+pipeline_name: object_detection
+
+SubModules:
+  ObjectDetection:
+    module_name: object_detection
+    model_name: PicoDet-S
+    model_dir: null
+    batch_size: 1
+    img_size: null
+    threshold: null