Purpose and implementation of 're-flatten' Layer in Vision Transformer

1 次查看（过去 30 天）
HK ZHOU
HK ZHOU 2023-9-21
回答： Tijue 2024-2-12
In MATLAB 2023b's Computer Vision Toolbox, there is a pre-trained vision Transformer model that includes patch embedding and re-flatten layers. What is the purpose of the re-flatten layer? Additionally, it seems that there is no "re-flatten" function in the Deep Learning Toolbox. Do I need to write this function myself?
  2 个评论
xingxingcui
xingxingcui 2024-1-4
I only see patch embedding layer,flatten layer,can't find re-flaten layers in MATLAB 2023b,can you post the re-flaten layer link?
HK ZHOU
HK ZHOU 2024-1-5
Thanks for your comment.
After executing the following codes, in the NetworkAnalyzer, the 're-flatten' function is visible, but cannot find the source code.
net = visionTransformer;
analyzeNetwork(net)

请先登录，再进行评论。

请先登录，再回答此问题。

回答（1 个）

Tijue
Tijue 2024-2-12
Hello Zhou,
You can open the "visionTransformer" function and find the "re-flatten" layer at line 67.

类别

在 Help Center 和 File Exchange 中查找有关 Deep Learning Toolbox 的更多信息

标签

产品


版本

R2023b

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by