fix vq utils

ppstructure/vqa/eval_re.py

@@ -24,7 +24,7 @@ import paddle
 from paddlenlp.transformers import LayoutXLMTokenizer, LayoutXLMModel, LayoutXLMForRelationExtraction
 
 from xfun import XFUNDataset
-from utils import parse_args, get_bio_label_maps, print_arguments
+from vqa_utils import parse_args, get_bio_label_maps, print_arguments
 from data_collator import DataCollator
 from metric import re_score
 

ppstructure/vqa/eval_ser.py

@@ -33,7 +33,7 @@ from paddlenlp.transformers import LayoutLMModel, LayoutLMTokenizer, LayoutLMFor
 
 from xfun import XFUNDataset
 from losses import SERLoss
-from utils import parse_args, get_bio_label_maps, print_arguments
+from vqa_utils import parse_args, get_bio_label_maps, print_arguments
 
 from ppocr.utils.logging import get_logger
 

ppstructure/vqa/infer_re.py

@@ -15,7 +15,7 @@ import paddle
 from paddlenlp.transformers import LayoutXLMTokenizer, LayoutXLMModel, LayoutXLMForRelationExtraction
 
 from xfun import XFUNDataset
-from utils import parse_args, get_bio_label_maps, draw_re_results
+from vqa_utils import parse_args, get_bio_label_maps, draw_re_results
 from data_collator import DataCollator
 
 from ppocr.utils.logging import get_logger

ppstructure/vqa/infer_ser.py

@@ -14,6 +14,10 @@
 
 import os
 import sys
+
+__dir__ = os.path.dirname(os.path.abspath(__file__))
+sys.path.append(__dir__)
+
 import json
 import cv2
 import numpy as np
@@ -22,7 +26,7 @@ from copy import deepcopy
 import paddle
 
 # relative reference
-from utils import parse_args, get_image_file_list, draw_ser_results, get_bio_label_maps
+from vqa_utils import parse_args, get_image_file_list, draw_ser_results, get_bio_label_maps
 from paddlenlp.transformers import LayoutXLMModel, LayoutXLMTokenizer, LayoutXLMForTokenClassification
 from paddlenlp.transformers import LayoutLMModel, LayoutLMTokenizer, LayoutLMForTokenClassification
 

ppstructure/vqa/infer_ser_e2e.py

@@ -14,6 +14,10 @@
 
 import os
 import sys
+
+__dir__ = os.path.dirname(os.path.abspath(__file__))
+sys.path.append(__dir__)
+
 import json
 import cv2
 import numpy as np
@@ -25,9 +29,9 @@ from paddlenlp.transformers import LayoutXLMModel, LayoutXLMTokenizer, LayoutXLM
 from paddlenlp.transformers import LayoutLMModel, LayoutLMTokenizer, LayoutLMForTokenClassification
 
 # relative reference
-from utils import parse_args, get_image_file_list, draw_ser_results, get_bio_label_maps
+from vqa_utils import parse_args, get_image_file_list, draw_ser_results, get_bio_label_maps
 
-from utils import pad_sentences, split_page, preprocess, postprocess, merge_preds_list_with_ocr_info
+from vqa_utils import pad_sentences, split_page, preprocess, postprocess, merge_preds_list_with_ocr_info
 
 MODELS = {
     'LayoutXLM':

ppstructure/vqa/infer_ser_re_e2e.py

@@ -24,7 +24,7 @@ import paddle
 from paddlenlp.transformers import LayoutXLMModel, LayoutXLMTokenizer, LayoutXLMForRelationExtraction
 
 # relative reference
-from utils import parse_args, get_image_file_list, draw_re_results
+from vqa_utils import parse_args, get_image_file_list, draw_re_results
 from infer_ser_e2e import SerPredictor
 
 

ppstructure/vqa/train_re.py

@@ -27,7 +27,7 @@ import paddle
 from paddlenlp.transformers import LayoutXLMTokenizer, LayoutXLMModel, LayoutXLMForRelationExtraction
 
 from xfun import XFUNDataset
-from utils import parse_args, get_bio_label_maps, print_arguments, set_seed
+from vqa_utils import parse_args, get_bio_label_maps, print_arguments, set_seed
 from data_collator import DataCollator
 from eval_re import evaluate
 

ppstructure/vqa/train_ser.py

@@ -32,7 +32,7 @@ from paddlenlp.transformers import LayoutXLMModel, LayoutXLMTokenizer, LayoutXLM
 from paddlenlp.transformers import LayoutLMModel, LayoutLMTokenizer, LayoutLMForTokenClassification
 
 from xfun import XFUNDataset
-from utils import parse_args, get_bio_label_maps, print_arguments, set_seed
+from vqa_utils import parse_args, get_bio_label_maps, print_arguments, set_seed
 from eval_ser import evaluate
 from losses import SERLoss
 from ppocr.utils.logging import get_logger

ppstructure/vqa/utils.py → ppstructure/vqa/vqa_utils.py

@@ -366,9 +366,9 @@ def parse_args():
     parser.add_argument("--max_seq_length", default=512, type=int,)
     parser.add_argument("--evaluate_during_training", action="store_true",)
     parser.add_argument("--num_workers", default=8, type=int,)
-    parser.add_argument("--per_gpu_train_batch_size", default=8,
+    parser.add_argument("--per_gpu_train_batch_size", default=1,
                         type=int, help="Batch size per GPU/CPU for training.",)
-    parser.add_argument("--per_gpu_eval_batch_size", default=8,
+    parser.add_argument("--per_gpu_eval_batch_size", default=1,
                         type=int, help="Batch size per GPU/CPU for eval.",)
     parser.add_argument("--learning_rate", default=5e-5,
                         type=float, help="The initial learning rate for Adam.",)