vkgo / ocrautoscore Goto Github PK
View Code? Open in Web Editor NEWOCR自动化阅卷项目
License: GNU Affero General Public License v3.0
OCR自动化阅卷项目
License: GNU Affero General Public License v3.0
qq邮箱:[email protected]
我这里有很多未打标的答题卡,想问一下需要什么样的数据集标签及格式要求。
不过我们收回来的答题卡图片均为二值化,不是灰度。
我想要使用yolov8训练自己的大题检测模型,想问一下可以提供答题卡的数据集吗
@vkgo @ouguangye 项目需要丛答题卡识别相关,想和您聊聊关于项目的事情,如果您看到了可以联系我。
可以联系我的邮箱:[email protected]
提示找不到文件“load_state_dict(torch.load('./scoreblocks/MSPLM/prediction/p1/val0test1/best_total.bin'))”
我发现你在外面又单独放了一个CAN模块,这可能是为了解决scoreblocks模块单独运行candemo.py时可能会报路径错误。其实我觉得这可能是编码的时候一个bug,按照我下面展示的修改,可以让你不需要单独放置一个CAN模块
在candemo.py
self.params=load_config('./CAN/config.yaml')
改为self.params=load_config('./scoreblocks/CAN/config.yaml')
load_checkpoint(self.model,None,'./CAN/checkpoints/demo.pth')
改为load_checkpoint(self.model,None,'./scoreblocks/CAN/checkpoints/demo.pth')
在config.yaml中
word_path: './CAN/words_dict.txt'
改为word_path: './scoreblocks/CAN/words_dict.txt'
checkpoint: "./checkpoints/demo.pth"
改为checkpoint: "./scoreblocks/checkpoints/demo.pth"
之后在外部运行score.py时,只需要添加python解释器的路径就行
import sys
import os
sys.path.append(os.getcwd()+'/scoreblocks/')
非常感谢您阅读这条比较简单的问题,我算是小白,因为没有部署过此类文件,想问问有没有具体的教程或者能不能形成Releases,非常感谢
我们也想训练分割试卷的yolo模型,但是无奈正好缺少答题卡这部分的数据集,希望能有尝从您这获取^_^
您好,我看到score.py中关于选择题模型的部分为pass,在项目中也看到了关于单字母识别的模型,请问选择题是准备根据涂卡来判断还是根据手写字母来判断?想了解一下您的思路
大佬,可以教一下怎么运行嘛,可以有偿
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.