diff --git a/ppstructure/vqa/README.md b/ppstructure/vqa/README.md index 975139c7937605972dfb7051918b74c66f480555..35aa1d26080aee198d0b66e30f98a5a12b10deb1 100644 --- a/ppstructure/vqa/README.md +++ b/ppstructure/vqa/README.md @@ -136,7 +136,7 @@ wget https://paddleocr.bj.bcebos.com/dataset/XFUND.tar ```shell python3.7 train_ser.py \ --model_name_or_path "layoutxlm-base-uncased" \ - --ser_model_type "LayoutLM" \ + --ser_model_type "LayoutXLM" \ --train_data_dir "XFUND/zh_train/image" \ --train_label_path "XFUND/zh_train/xfun_normalize_train.json" \ --eval_data_dir "XFUND/zh_val/image" \ @@ -316,6 +316,7 @@ export CUDA_VISIBLE_DEVICES=0 python3.7 infer_ser_re_e2e.py \ --model_name_or_path "./PP-Layout_v1.0_ser_pretrained/" \ --re_model_name_or_path "./PP-Layout_v1.0_re_pretrained/" \ + --ser_model_type "LayoutXLM" \ --max_seq_length 512 \ --output_dir "output/ser_re_e2e/" \ --infer_imgs "images/input/zh_val_21.jpg"