8000 预训练文本编码维度 · Issue #10 · GXNU-ZhongLab/DUTrack · GitHub
[go: up one dir, main page]

Skip to content

预训练文本编码维度 #10

Open

Description

@nie0618

文本特征的长度期望为 7,但使用的 BERT/BLIP 预训练模型输出维度是 9,这是为什么?
也不知道是不是这个原因,是否还有别的原因?
Image

Image

Activity

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

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions

      0