Question about preprocess_train in train_text_to_image_sdxl.py #7609
|
Why transform image_column again in precomputed_dataset in code: |
Answered by
tolgacangoz
Apr 9, 2024
Replies: 1 comment
|
Actually, the one who added it also was unsure why it was necessary. I guess the columns need rearranging. |
0 replies
Answer selected by
00why00
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Actually, the one who added it also was unsure why it was necessary. I guess the columns need rearranging.