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

同一个batch中相同的句子一起输入模型,在这一次正向传播中 dropout是一样的吧? #12

Open
lihaixiang opened this issue Oct 24, 2021 · 2 comments

Comments

@lihaixiang
Copy link

No description provided.

@HitAgain
Copy link

HitAgain commented Mar 1, 2022

同问,相当于正例通过的是同一个模型,这个和原论文不符合~

@Doufanfan
Copy link

Doufanfan commented Jan 7, 2023

一个batch内的dropout mask理论上是一样的,一个batch同一个句子重复两遍,经过的也是相同的dropout mask,理论上encoder输出的向量是一样的,感觉没有引入dropout noisy啊

——
尴尬😓review了一遍dropout层的实现,正常在不传入noisy_shape时,noisy_shape默认与input shape一致,即[N,xx,xx]或[N,xx],这样dropout mask是样本维度,所以重复的样本会计算不同的dropout mask,实现和原论文逻辑一致。

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

3 participants