AdvancedLiterateMachinery

AdvancedLiterateMachinery copied to clipboard

python train_VGT.py --config-file Configs/cascade/D4LA_VGT_cascade_PTM.yaml --num-gpus 8 MODEL.WEIGHTS 'VGT_pretrain_model' OUTPUT_DIR 'D4LA_output' Traceback (most recent call last): File "train_VGT.py", line 20, in from detectron2.data import build_detection_train_loader File "/home/xia/anaconda3/envs/xia-vgt/lib/python3.8/site-packages/detectron2/data/__init__.py", line 4, in from...

1codei

cqray1990

update requirements.txt, example.py in DocXChain

1

`requirements.txt` in DocXChain is not enough to install necessary libraries. Also, I faced a minor error and inconvenience in usage. So I updated the files below. * `requirements.txt` * `example.py`...

jodog0412

Hi! I was wondering about the 'SceneVTG-benchmark' mentioned in the paper—where can I find it? I noticed that the SCUT-EnsText dataset only contains erased images, and I couldn’t locate the...

Tony-Lowe

Hi, I want to know the time that Platypus weight model will release ?

Holmes2002

Pretrained Omniparser model stage2

1

Hi , I want fine tune the omniparser model on my custom key value extraction dataset . for that I need the pretrained omniparser_stage2.pth model . if anyone having that...

RupankarNewGen

[PubTabNet-Dataset](https://github.com/ibm-aur-nlp/PubTabNet).LORE readme中说到的数据与readme中提供的标签，文件名对不上，能提供一下与标签对应的PubTabNet数据集吗，或者提供一个将PubTabNet转化为coco标签的脚本吗

18349692662

您好！在阅读了你们LISTER: Neighbor Decoding for Length-Insensitive Scene Text Recognition这篇文章后，我对于你们文章后半段对于中文数据集的处理比较感兴趣，但是目前开源的代码中貌似只有针对英文+数字的训练模型。所以想问一下你们是否用中文训练的模型以及训练代码呢？

frankmangod

First of all, thank you for making these models available—great work! I have tried several AI models that extract content from PDFs and identify its type—e.g., - text - title...

Samyssmile

Update formula_recognition.py

1

There's some bug in formula_recognition, where "LatexOCR" should be "LaTeXOCR"

EldenLordx