如何生成自己数据的landmark文件? #98

Open
opened 2026-01-29 21:41:48 +00:00 by claunia · 5 comments
Owner

Originally created by @alexliyang on GitHub (Nov 2, 2021).

FFHQ_eye_mouth_landmarks_512.pth 这个是FFHQ的数据集的landmark,如果要训练自己的数据集,这个如何生成?比如用CeleBA 数据集

Originally created by @alexliyang on GitHub (Nov 2, 2021). FFHQ_eye_mouth_landmarks_512.pth 这个是FFHQ的数据集的landmark,如果要训练自己的数据集,这个如何生成?比如用CeleBA 数据集
Author
Owner

@jorjiang commented on GitHub (Nov 4, 2021):

你可以在inference的代码里找找 里面肯定有提取提取输入图片的landmark的部分 我之前看到过 具体不愿找了。反正是用到了facexlib这个库里的函数

@jorjiang commented on GitHub (Nov 4, 2021): 你可以在inference的代码里找找 里面肯定有提取提取输入图片的landmark的部分 我之前看到过 具体不愿找了。反正是用到了facexlib这个库里的函数
Author
Owner

@onefish51 commented on GitHub (Jul 25, 2022):

I found it on scripts/parse_landmark.py

but the face_landmarks from ffhq-dataset-v2.json, so you need to get face_landmarks by dlib for your datasets

@onefish51 commented on GitHub (Jul 25, 2022): I found it on [scripts/parse_landmark.py](https://github.com/TencentARC/GFPGAN/blob/master/scripts/parse_landmark.py) but the face_landmarks from `ffhq-dataset-v2.json`, so you need to get face_landmarks by dlib for your datasets
Author
Owner

@BrotherQi commented on GitHub (Aug 27, 2022):

您找到方法了吗

@BrotherQi commented on GitHub (Aug 27, 2022): 您找到方法了吗
Author
Owner

@onefish51 commented on GitHub (Aug 31, 2022):

you can make it by dlib or face_alignment

@onefish51 commented on GitHub (Aug 31, 2022): you can make it by dlib or face_alignment
Author
Owner

@BrotherQi commented on GitHub (Aug 31, 2022):

firstly thanks for your reply,
my error is AttributeError: 'GFPGANModel' object has no attribute 'loc_left_eyes' but i dont
see the same key 'loc_left_eyes' in scripts/parse_landmark.py
can you explain it in detail

@BrotherQi commented on GitHub (Aug 31, 2022): firstly thanks for your reply, my error is AttributeError: 'GFPGANModel' object has no attribute 'loc_left_eyes' but i dont see the same key 'loc_left_eyes' in [scripts/parse_landmark.py](https://github.com/TencentARC/GFPGAN/blob/master/scripts/parse_landmark.py) can you explain it in detail
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: TencentARC/GFPGAN#98