CUDA="11.0"
CUDNN="8"
UBUNTU="18.04"

bash install.sh
git clone https://github.com/NVIDIA/apex && cd apex
pip install -v --no-cache-dir --global-option="--cpp_ext" --global-option="--cuda_ext" ./
pip install .
# under our project root folder
pip install .

# $MODEL_PATH here is where you save the fine-tuned model.
# DATASET_NAME is FUNSD or INV-CDIP.
bash reproduce_results.sh $MODEL_PATH $DATA_DIR/DATASET_NAME

# $NUM_GPUS is the number of gpus you want to do the pretraining on. To reproduce the paper's results we recommend to use 8 gpus.
# $MODEL_PATH here is where you save the LayoutLM model.
# $PRETRAIN_DATA_FOLDER is the folder of IIT-CDIP hocr files.

python -m torch.distributed.launch --nproc_per_node=$NUM_GPUS pretraining.py \
--model_name_or_path $MODEL_PATH  --data_dir $PRETRAIN_DATA_FOLDER \
--output_dir $OUTPUT_DIR

# $MODEL_PATH is where you save the pre-trained simpleDLM model.

CUDA_VISIBLE_DEVICES=0 python run_query_value_retrieval.py --model_type simpledlm --model_name_or_path $MODEL_PATH \
--data_dir $DATA_DIR/FUNSD/ --output_dir $OUTPUT_DIR --do_train --evaluate_during_training

@article{gao2021value,
  title={Value Retrieval with Arbitrary Queries for Form-like Documents},
  author={Gao, Mingfei and Xue, Le and Ramaiah, Chetan and Xing, Chen and Xu, Ran and Xiong, Caiming},
  journal={arXiv preprint arXiv:2112.07820},
  year={2021}
}