Model Zoo

We provide a spectrum of pre-trained models on different datasets.

Example Usage:

importlayoutparseraslpmodel=lp.Detectron2LayoutModel(config_path='lp://PubLayNet/faster_rcnn_R_50_FPN_3x/config',# In model cataloglabel_map={0:"Text",1:"Title",2:"List",3:"Table",4:"Figure"},# In model`label_map`extra_config=["MODEL.ROI_HEADS.SCORE_THRESH_TEST",0.8]# Optional)model.detect(image)

Model Catalog

DatasetModelConfig PathEval Result (mAP)
HJDatasetfaster_rcnn_R_50_FPN_3xlp://HJDataset/faster_rcnn_R_50_FPN_3x/config
HJDatasetmask_rcnn_R_50_FPN_3xlp://HJDataset/mask_rcnn_R_50_FPN_3x/config
HJDatasetretinanet_R_50_FPN_3xlp://HJDataset/retinanet_R_50_FPN_3x/config
PubLayNetfaster_rcnn_R_50_FPN_3xlp://PubLayNet/faster_rcnn_R_50_FPN_3x/config
PubLayNetmask_rcnn_R_50_FPN_3xlp://PubLayNet/mask_rcnn_R_50_FPN_3x/config
PubLayNetmask_rcnn_X_101_32x8d_FPN_3xlp://PubLayNet/mask_rcnn_X_101_32x8d_FPN_3x/config88.98eval.csv
PrimaLayoutmask_rcnn_R_50_FPN_3xlp://PrimaLayout/mask_rcnn_R_50_FPN_3x/config69.35eval.csv
NewspaperNavigatorfaster_rcnn_R_50_FPN_3xlp://NewspaperNavigator/faster_rcnn_R_50_FPN_3x/config
TableBankfaster_rcnn_R_50_FPN_3xlp://TableBank/faster_rcnn_R_50_FPN_3x/config89.78eval.csv
TableBankfaster_rcnn_R_101_FPN_3xlp://TableBank/faster_rcnn_R_101_FPN_3x/config91.26eval.csv
Math Formula Detection(MFD)faster_rcnn_R_50_FPN_3xlp://MFD/faster_rcnn_R_50_FPN_3x/config79.68eval.csv

  • For PubLayNet models, we suggest usingmask_rcnn_X_101_32x8d_FPN_3x model as it’s trained on the whole training set, while others are only trained on the validation set (the size is only around 1/50). You could expect a 15% AP improvement using themask_rcnn_X_101_32x8d_FPN_3x model.

Modellabel_map

DatasetLabel Map
HJDataset{1:"Page Frame", 2:"Row", 3:"Title Region", 4:"Text Region", 5:"Title", 6:"Subtitle", 7:"Other"}
PubLayNet{0: "Text", 1: "Title", 2: "List", 3:"Table", 4:"Figure"}
PrimaLayout{1:"TextRegion", 2:"ImageRegion", 3:"TableRegion", 4:"MathsRegion", 5:"SeparatorRegion", 6:"OtherRegion"}
NewspaperNavigator{0: "Photograph", 1: "Illustration", 2: "Map", 3: "Comics/Cartoon", 4: "Editorial Cartoon", 5: "Headline", 6: "Advertisement"}
TableBank{0: "Table"}
MFD{1: "Equation"}