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.

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

Jump to bottom

求教：为什么Resampler后，还可以做OCR识别，感觉已经在压缩的过程中，丢失了信息，做OCR识别任务会降低精度 #684

Open
alphanlp opened this issue Nov 30, 2024 · 1 comment
Open

求教：为什么Resampler后，还可以做OCR识别，感觉已经在压缩的过程中，丢失了信息，做OCR识别任务会降低精度 #684

alphanlp opened this issue Nov 30, 2024 · 1 comment

Comments

@alphanlp
Copy link

为什么Resampler后，还可以做OCR识别，感觉已经在压缩的过程中，丢失了信息，做OCR识别任务会降低精度
@LDLINGLINGLING
Copy link
Collaborator

LDLINGLINGLING commented Dec 3, 2024 •
edited
Loading

你好，以下是个人理解，在resampler过程中确实会丢失信息，但是由于以下两点：
1.图片本身信息冗余量就非常大
2.由于反向传播的梯度更新将会导致模型能够抽取大量的有效信息，从而保留，丢失的可能是无效信息

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@alphanlp @LDLINGLINGLING