训练模型时，第一步“Align the face images to 112*112 according to face_align.py.”是把图片resize成112*112大小，还是需要用到face_align.py脚本进行处理

JDAI-CV / FaceX-Zoo

A PyTorch Toolbox for Face Recognition

https://arxiv.org/pdf/2101.04407.pdf

Other

1.89k stars 434 forks source link

Open tikdik opened 3 years ago

tikdik commented 3 years ago

Step1: Prepare the training data Align the face images to 112*112 according to face_align.py.

需要用face_align.py这个文件处理图片还是简简单单把图片resize成112*112呢

xturnip commented 3 years ago

您好，请问您解决图像预处理的问题了吗？我不清楚landmark怎么来的

tmhieu99 commented 3 years ago

Hi @xturnip, the landmarks probably come from here. In the Face SDK, the author uses a pfld model to produce landmarks for images.

xturnip commented 3 years ago

@tmhieu99 thank you

robbie2021 commented 3 years ago

请问一下，训练的图片尺寸必须resize成112 112大小吗？还是说其它的大小，比如96 112,也是可以的？