Skip to content
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.

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

修改版本:https://github.com/pprp/captcha_identify.torch #28

Open
pprp opened this issue Oct 23, 2019 · 0 comments
Open

修改版本:https://github.com/pprp/captcha_identify.torch #28

pprp opened this issue Oct 23, 2019 · 0 comments

Comments

@pprp
Copy link

pprp commented Oct 23, 2019

@dee1024 感谢您的工作,我研究了以下您的代码,针对您的库中的不足之处进行了部分改进和个性化处理。
这是链接:https://github.com/pprp/captcha_identify.torch
使用您的库:

training set : 10k
test set: 1k

达不到96%的要求,请教您具体是哪个地方有问题?

另外,我主要的改动的点在以下几个方面:

  • 添加了更多torchvision中支持的模型
  • 改了一下文件的名称
  • 支持了GPU,当然cpu也可以
  • 添加了以下功能:训练完成一个epoch之后进行测试,(需要保证test和train中的模型一致)
  • 添加了以下功能:将每次得到的测试结果写入results.txt文件,运行torch_util.py得到results.png可视化准确率。
  • RES152为基础网络进行训练,混合数字和大写字符只能达到94%,还达不到原作者的识别率,希望得到赐教

目前最好的是RES101,RES152为基础的网络,可以达到94%。

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant