mirror of
https://github.com/openai/CLIP.git
synced 2026-11-05 01:37:26 +00:00
[GH-ISSUE #231] Clip是否由正面人脸的配对训练 #200
Labels
No labels
pull-request
No milestone
No project
No assignees
1 participant
Notifications
Due date
No due date set.
Dependencies
No dependencies set.
Reference
openai/CLIP#200
Loading…
Add table
Add a link
Reference in a new issue
No description provided.
Delete branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
Originally created by @zhou431496 on GitHub (Apr 14, 2022).
Original GitHub issue: https://github.com/openai/CLIP/issues/231
我打算使用clip做人脸正面化重建,请问clip是否可以做到使用"a frontal face"来约束图像生成正面化的人脸。期待你的回复,谢谢
@jongwook commented on GitHub (Apr 19, 2022):
Used Google Translate but not sure if I understood the question correctly. The training data likely contained images containing frontal faces, but we don't have statistics for that. Also your mileages may vary depending on which method and hyperparameters were used for generation.
@zhou431496 commented on GitHub (Apr 19, 2022):
You can don't understand my problem, if you pass the text of "a Frontal Face", some side images can be changed to a front face. The model we use is STYLECLIP