Tom's repositories
Fast-Chinese-OCR
该项目采用最前沿的AI算法,针对合同扫描文档进行识别和抽取。
ocr_onnx_cpp_paddleocr_opencv_deploy
paddleocr deploy by onnx and opencv
QT-style-template
QT-style-template
chineseocr_lite
超轻量级中文ocr,支持竖排文字识别, 支持ncnn推理 , dbnet(1.7M) + crnn(6.3M) + anglenet(1.5M) 总模型仅10M
coco2voc
Yet another coco2voc.py, convert MSCOCO json to PASCAL VOC xml in Object Detection.
ControlNet
Let us control diffusion models
dataset
医学影像数据集列表 『An Index for Medical Imaging Datasets』
DAVAR-Lab-OCR
The implementations of some works from Davar-Lab. Currently we have the code of Text Perceptron (AAAI 2020). Some works' code will be published soon, including YORO (ACMMM 2019) , TRIE (ACMMM2020), FREE(TIP 2020), SPIN (AAAI 2021), MANGO (AAAI2021), etc.
diff-pdf
Compare PDF documents using PDF Miner and print out the differences as HTML documents
element-plus
🎉 A Vue.js 3 UI Library made by Element team
fasterAPI
GIT LEARN DJANGO
InvoiceNet
Deep neural network to extract intelligent information from invoice documents.
Medcine-Chinese-CLIP
Chinese version of CLIP which achieves Chinese cross-modal retrieval and representation generation.
MiniCPM-V
MiniCPM-Llama3-V 2.5: A GPT-4V Level Multimodal LLM on Your Phone
PDF-Resume-Information-Extraction
天池比赛作品整理。实现从pdf中提取出姓名、出生年月、性别、电话、最高学历、籍贯、落户市县、政治面貌、毕业院校、工作单位、工作内容、职务、项目名称、项目责任、学位、毕业时间、工作时间、项目时间共18个字段。
pdfannots
Extracts and formats text annotations from a PDF file
PSENet-tf2
PSEnet tf2.0 reimplementation for better training and inference and ResneSt/Mobilenet/ tensorflow2 implement/ Top 6 model in MTWI 2018 Text Detection
Table-OCR
Recognize tables from images and restore them into word.
TensorflowDeployWithCpp
Using c++ load tensorflow2.0 saved_model and do inference.
TF2-albert-NER
wrapping albert via bert-for-tf2, implementing NER task
Yuan2.0-M32
Mixture-of-Experts (MoE) Language Model