-
after run python ./table_recognition/data_preprocess.py
then, i want to train it
sh ./table_recognition/table_text_line_recognition_dist_train.sh
but in ./configs/textrecog/master/masterv2_Resnet…
-
Hey, are the table images in Pubtabnet taken from pages in Publaynet? I'm interested in table-cell annotated images in the context of their original page, instead of just cropped table images.
-
Why does running the configuration "make experiments/r18_e2_d4_adamw/.done_train_structure" not result in an error, but running configurations within the convolutional stem, such as "EXP_cs_c384_e4_d4…
-
非常感谢您的工作！请问如何转成pubtablenet的格式？
-
I got some table images in different languages and areas. I want to annotate them and train with a structure recognition model. This model uses PubTabNet form to train. How could I annotate my tables…
-
In the ECCV 2020 paper, the size of PubTabNet is said to be 568K images + HTML. When I downloaded the v2 PubTabNet, I count 519030 image files and 509892 lines in the PubTabNet_2.0.0.jsonl file (pres…
-
我手头暂时只有一张卡，想请问下如何改动训练参数？
麻烦给个demo，谢谢！
另外，训练OCR模型的数据：
/root/DAVAR-Lab-OCR-main/demo/table_recognition/lgpma/configs/ocr_models/rcg_res32_bilstm_attn_pubtabnet_sensitive.py
ann_file='path/to/Pu…
-
Hi,
I would like to train LGPMA model and there is a question about converting annotation for validation.
When I set path of PubTabNet_2.0.0_val.jsonl for ann_file, training has stopped.
So, I …
-
i use text dect model as you supply,get PSENet detection results, TableMASTER structure recognition results and MASTER textline recognition results, and use match.py to get TEDS score.
PSENet + MASTE…
-
Hi authors,
Thank you for making this wonderful work public. Can you share code to preprocess pubtabnet or UNLV dataset to create annotations? How can we create training labels(annotations) for our o…