wzgwy's starred repositories
Awesome-Hacking
A collection of various awesome lists for hackers, pentesters and security researchers
Chart2Text
Chart-to-Text: Generating Natural Language Explanations for Charts by Adapting the Transformer Model
InternLM-XComposer
InternLM-XComposer2 is a groundbreaking vision-language large model (VLLM) excelling in free-form text-image composition and comprehension.
ColossalAI
Making large AI models cheaper, faster and more accessible
VisionAgent
基于InternLm chat 7B大模型基座,构建一个Agent ,可以调用 MMYOLO 工具来完成图像内视觉任务
Defect-GLM
Defect-GLM:A Large Visual-Language Model for Industrial Defect Monitoring|首个用于工业缺陷监测的开源大规模视觉语言模型
pdf_change
pdf转换为excel/word/txt
OCR_DataSet
收集并整理有关OCR的数据集并统一标注格式,以便实验需要
PytorchOCR
基于Pytorch的OCR工具库,支持常用的文字检测和识别算法
TextRecognitionDataGenerator
A synthetic data generator for text recognition
layout-parser
A Unified Toolkit for Deep Learning Based Document Image Analysis
Table-Extraction-and-Chinese-OCR
Extract the outline of the table from the paper form obtained from the photo and recognize the text content in the outline. 从拍照得到的纸质表格中检测出表格轮廓并提取出这些轮廓,对每个轮廓内的内容进行识别。
Table-OCR-based-on-DeepLearning
表格检测和表结构识别
smart-table-segmentation-recognition-enhanced-db-rare
改进DB&RARE智慧表格分割识别系统
Table_detection
基于OpenCV的图像中表格的识别(Table recognition in image based on OpenCV)
table_rec_system
中文表格OCR识别系统,支持导出excel或者word表格
Medical-table
医疗体检单表格解析,通过kmean做的表格识别