AdvancedLiterateMachinery
AdvancedLiterateMachinery copied to clipboard
AlibabaResearch
A collection of original, innovative ideas and algorithms towards Advanced Literate Machinery. This project is maintained by the OCR Team in the Language Technology Lab, Tongyi Lab, Alibaba Group.
I've read both Cycle-CenterNet and LORE papers and noticed that LORE uses WTW dataset for training. However, in the experimental results section, why isn't there a direct comparison with Cycle-CenterNet's...
I really appreciate your work on GeoLayoutLM. I would like to ask if there is any way to support polygon input with four points instead of only rectangular bounding boxes...
加载默认tokenizer 进行字符转换时，会出现部分字符为【UNK】 TOKENIZER = TOKENIZER = BertTokenizer.from_pretrained("bert-base-uncased", do_lower_case=True) tokenizer = TOKENIZER
Metadata
Owner
Metadata
A collection of original, innovative ideas and algorithms towards Advanced Literate Machinery. This project is maintained by the OCR Team in the Language Technology Lab, Tongyi Lab, Alibaba Group.