We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
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
我看代码里面STTN的训练代码,生成器是需要输入原图和mask区域的,
实际推理使用auto_sttn的生成器是只需要输入切割好的字符区域图片即可,因为不需要精确的字幕mask,可以自动识别出要重建的字幕位置?
训练代码的生成器和实际推理的生成器好像不一致。
不知道是否是我理解错误。
The text was updated successfully, but these errors were encountered:
训练代码中的生成器需要输入原图和精确的字幕区域 mask,因为训练阶段的目标是让模型学习在已知遮挡区域的情况下进行字幕区域修复,从而优化其权重。而推理阶段的生成器,例如 auto_sttn,则只需输入切割好的字符区域图片,无需提供精确的 mask,因为模型在训练中已具备自动识别字幕位置并重建的能力。这种设计反映了训练阶段的高精度需求与推理阶段灵活性之间的差异,是为了在实际使用中减少对用户手动标注的依赖,同时确保模型的有效性和易用性。
Sorry, something went wrong.
No branches or pull requests
我看代码里面STTN的训练代码,生成器是需要输入原图和mask区域的,
实际推理使用auto_sttn的生成器是只需要输入切割好的字符区域图片即可,因为不需要精确的字幕mask,可以自动识别出要重建的字幕位置?
训练代码的生成器和实际推理的生成器好像不一致。
不知道是否是我理解错误。
The text was updated successfully, but these errors were encountered: