Skip to content

Issues: ypwhs/captcha_break

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Clear current search query, filters, and sorts
48 Open 18 Closed
48 Open 18 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

请问如果想使用该模型训练非captcha库内的图片，应该怎么修改呢？ 数据增强 如何使用数据增强提高模型的泛化能力 自定义数据 如何使用自定义数据
#45 opened Nov 3, 2019 by charfole
20
用keras2的api改写后，无法收敛 调优 如何提高模型的精度
#4 opened Jun 7, 2017 by camperr
18
用ctc_2019.ipynb训练的模型，预测时16个通道只有前两个和最后两个会预测，而且准确率很差？
#31 opened Aug 12, 2019 by rhypowang
16
楼主，请教 调优 如何提高模型的精度
#38 opened Oct 7, 2019 by armstrong1972
13
你好，cnn模型不加BN层不收敛 调优 如何提高模型的精度
#16 opened Jul 9, 2018 by chrisyoung2017
12
如果把模型保存下来，然后重新加载load_model报错
#22 opened Apr 9, 2019 by Times125
10
不同大小的图片不能一起训练，导致模型泛化能力很弱 调优 如何提高模型的精度
#30 opened Jul 29, 2019 by brucefeng10
9
请问ctc_2019中input_length=16, label_length=4的具体使用方法？ base_model 与 model 为什么会有两个模型
#46 opened Nov 5, 2019 by chajnoven
8
请问：DataLoader worker (pid(s) 2832, 15200, 1128, 7276, 11544, 12964, 9324, 4740, 2284, 5624, 7340, 13672) exited unexpectedly 怎么解决
#27 opened Jul 22, 2019 by airdot
8
运行winpy/main.py遇到的问题
#61 opened Aug 14, 2020 by AzureSkyHuHu
5
楼主您好，请问3500常用汉字的验证码识别，该模型大小够吗？
#52 opened Feb 25, 2020 by niujiahe
5
您可否告知下这几个文件是独立运行的吗，如何训练自己的中文验证码呢 自定义数据 如何使用自定义数据
#49 opened Nov 27, 2019 by bixueting
5
ctc_2019.ipynb中，训练完一个epoch后，就不再继续了
#28 opened Jul 22, 2019 by AemaH
5
Saw a non-null label (index >= num_classes - 1) following a null label
#7 opened Jul 23, 2017 by lxj0276
5
如果验证码最后两位相同，似乎一定识别错误
#60 opened Jul 22, 2020 by devmonkeyx
4
多行验证码如何识别呢？
#53 opened Mar 7, 2020 by MichaelGou1105
4
cnn模型构建的问题 模型结构
#36 opened Aug 30, 2019 by MgArcher
4
在ctc_pytorch的训练过程中，损失值总会变为nan Loss nan input_length 太小导致 loss nan
#29 opened Jul 22, 2019 by AemaH
4
数据生成函数为什么最后要返回一个np.ones(batch_size)？
#17 opened Dec 17, 2018 by Yogaht
4
你好，如果需要训练能识别五个字母的模型 该怎么改动参数？
#15 opened Jul 6, 2018 by ghost
4
使用CTC， 识别时不限制4个字符长度，识别率如何？
#65 opened Mar 14, 2021 by ctzhang2008
3
model variable vs base_model base_model 与 model 为什么会有两个模型
#10 opened Nov 13, 2017 by roccolocko
3
Input 0 is incompatible with layer dense_3: expected ndim=2, found ndim=3
#1 opened Mar 11, 2017 by keviswang
3
训练完了怎么用啊，纯小白
#68 opened Nov 29, 2021 by yiqingkuang
2
请问如果是不定长的验证码 可以使用吗
#64 opened Dec 2, 2020 by AzureSkyHuHu
2
ProTip! Find all open issues with in progress development work with linked:pr.