8000 customized dataset · Issue #307 · borisdayma/dalle-mini · GitHub
[go: up one dir, main page]
Skip to content

Repository navigation

customized dataset #307

New issue
New issue
Open
Open
customized dataset#307

Description

@zhuang-li
zhuang-li
opened on Sep 3, 2022

Hi sorry for this naive question as I am new to computer vision and DALLE. Say if I have a folder of images and captions such as

dir/
cat.jpg
cat.txt
dog.jpg
dog.txt

how to convert the folder into the data format the DALLE-mini can accept if I want to train a new model? Is there any script in this repo?

I was using "https://github.com/lucidrains/DALLE-pytorch" the data format for their model is the above format but I am not clear what is the data format used here.

Activity

  1. borisdayma commented on Sep 4, 2022

    @borisdayma
    borisdayma
    on Sep 4, 2022
    Owner

    This is the required format: https://github.com/borisdayma/dalle-mini/blob/main/tools/dataset/encode_dataset.ipynb

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

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions
      0