README.md

metadata

tags:
  - Tensorflow
license: apache-2.0
datasets:
  - Publaynet

Tensorpacks Cascade-RCNN with FPN and Group Normalization on ResNext32xd4-50 trained on Publaynet for Document Layout Analysis

The model and its training code has been mainly taken from: Tensorpack .

Please check: Xu Zhong et. all. - PubLayNet: largest dataset ever for document layout analysis.

This model is different from the model used the paper.

The code has been adapted so that it can be used in a deepdoctection pipeline.

How this model can be used

This model can be used with the deepdoctection in a full pipeline, along with table recognition and OCR. Check the general instruction following this Get_started tutorial.

How this model was trained.

To recreate the model run on the deepdoctection framework, run:

>>> import os
>>> from deep_doctection.datasets import DatasetRegistry
>>> from deep_doctection.eval import MetricRegistry
>>> from deep_doctection.utils import get_configs_dir_path
>>> from deep_doctection.train import train_faster_rcnn
publaynet = DatasetRegistry.get_dataset("publaynet")
path_config_yaml=os.path.join(get_configs_dir_path(),"tp/layout/conf_frcnn_layout.yaml")
path_weights = ""
dataset_train = publaynet
config_overwrite=["TRAIN.STEPS_PER_EPOCH=500","TRAIN.EVAL_PERIOD=200","TRAIN.STARTING_EPOCH=1",
                  "PREPROC.TRAIN_SHORT_EDGE_SIZE=[800,1200]","TRAIN.CHECKPOINT_PERIOD=50",
                  "BACKBONE.FREEZE_AT=0"]
build_train_config=["max_datapoints=335703"]
dataset_val = publaynet
build_val_config = ["max_datapoints=2000"]
    
coco_metric = MetricRegistry.get_metric("coco")

How to fine-tune this model

To fine tune this model, please check this Fine-tune tutorial.