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

SwinLSTM架构理论应该也可以处理样本维度为[N, Timestep, NumFeatures]的时间序列吗 #12

Open
ToUranus opened this issue May 10, 2024 · 2 comments

Comments

@ToUranus
Copy link

作者您好,观察该模型架构,主要是在空间上发挥比较好的特征提取能力。对于单纯的时间序列来说,单个样本的维度为[T, N],而不是类似于多帧图像的[T, C,H,W]。如何使用该架构呢?是不是将前面embedding层删除就可以实现了呢?假设多特征NumFeatures之间存在空间特征。直接增加数据维度,发现无法喂进现有网络里

@timecoderr
Copy link

您好,我看源网络的每个数据格式为B H W C格式,请问这个帧数体现在哪里呢?

@ninaoooo
Copy link

把原有时间样本在添加一维在 C 处作为 1 通道应该就可以了吧,即 B NumFeatures Timestep C

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