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

A Question about training memory bank model #6

Open

csEylLee opened this issue Feb 3, 2023 · 1 comment

csEylLee commented Feb 3, 2023 •

edited

Loading

您好，我想问一下下面这部分代码为什么只取了一部分labels参与损失计算，而不是一个batch中全部的label进行计算？还望解答，万分感谢！

TMRNet/code/Training memory bank model/train_singlenet_phase_1fc.py

Line 492 in 6a0db47

labels_phase = labels_phase[(sequence_length - 1)::sequence_length]

Author

csEylLee commented Feb 4, 2023

我想应该是只需要每个sequence的最后一帧的预测……

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