paddlex 3.0.0b2__py3-none-any.whl → 3.0.0rc0__py3-none-any.whl

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/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

paddlex/configs/pipelines/open_vocabulary_detection.yaml

@@ -0,0 +1,12 @@
+
+pipeline_name: open_vocabulary_detection
+
+SubModules:
+  OpenVocabularyDetection:
+    module_name: open_vocabulary_detection
+    model_name: GroundingDINO-T
+    model_dir: null
+    batch_size: 1
+    thresholds:
+      box_threshold: 0.3
+      text_threshold: 0.25

paddlex/configs/pipelines/open_vocabulary_segmentation.yaml

@@ -0,0 +1,13 @@
+pipeline_name: open_vocabulary_segmentation
+
+SubModules:
+  BoxPromptSegmentation:
+    module_name: box_prompt_segmentation
+    model_name: SAM-H_box
+    model_dir: null
+    batch_size: 1
+  PointPromptSegmentation:
+    module_name: point_prompt_segmentation
+    model_name: SAM-H_point
+    model_dir: null
+    batch_size: 1

paddlex/configs/pipelines/pedestrian_attribute_recognition.yaml

@@ -0,0 +1,15 @@
+pipeline_name: pedestrian_attribute_recognition
+
+SubModules:
+  Detection:
+    module_name: object_detection
+    model_name: PP-YOLOE-L_human
+    model_dir: null
+    batch_size: 1
+    threshold: 0.5 
+  Classification:
+    module_name: multilabel_classification
+    model_name: PP-LCNet_x1_0_pedestrian_attribute
+    model_dir: null
+    batch_size: 1
+    threshold: 0.7

paddlex/configs/pipelines/rotated_object_detection.yaml

@@ -0,0 +1,10 @@
+
+pipeline_name: rotated_object_detection
+
+SubModules:
+  RotatedObjectDetection:
+    module_name: rotated_object_detection
+    model_name: PP-YOLOE-R-L
+    model_dir: null
+    batch_size: 1
+    threshold: 0.5

paddlex/configs/pipelines/seal_recognition.yaml

@@ -0,0 +1,51 @@
+
+pipeline_name: seal_recognition
+
+use_doc_preprocessor: True
+use_layout_detection: 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"
+
+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
+  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

paddlex/configs/pipelines/semantic_segmentation.yaml

@@ -0,0 +1,10 @@
+
+pipeline_name: semantic_segmentation
+
+SubModules:
+  SemanticSegmentation:
+    module_name: semantic_segmentation
+    model_name: PP-LiteSeg-T
+    model_dir: null
+    batch_size: 1
+    target_size: None

paddlex/configs/pipelines/small_object_detection.yaml

@@ -0,0 +1,10 @@
+
+pipeline_name: small_object_detection
+
+SubModules:
+  SmallObjectDetection:
+    module_name: small_object_detection
+    model_name: PP-YOLOE_plus_SOD-L
+    model_dir: null
+    batch_size: 1
+    threshold: 0.5

paddlex/configs/pipelines/table_recognition.yaml

@@ -0,0 +1,56 @@
+
+pipeline_name: table_recognition
+
+use_doc_preprocessor: True
+use_layout_detection: True
+use_ocr_model: True
+
+SubModules:
+  LayoutDetection:
+    module_name: layout_detection
+    model_name: PP-DocLayout-L
+    model_dir: null
+
+  TableStructureRecognition:
+    module_name: table_structure_recognition
+    model_name: SLANet_plus
+    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: 1
+        score_thresh: 0