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

ctc logits梯度如何推导 #2

Open

ghost opened this issue Sep 1, 2018 · 0 comments

ghost commented Sep 1, 2018 •

edited by ghost

Loading

我在km上搜到这篇文章，非常感谢，写的太好了。就是在ctc logits梯度那里，我没看明白是怎么推导的。一般sofmax的导数当i=j时，是，是如何推导得到最后一个公式呢？谢谢！
我在 CONNECTIONIST TEMPORAL CLASSIFICATION 的第七章和http://wantee.github.io/2015/02/08/rnnlib-connectionist-temporal-classification-and-transcription-layer/#mjx-eqn-eqlabelling_fwd_bwd中结合推导出了一个过程如下：

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment