search

fengju514 / Expression-Net

Deep 3DMM facial expression parameter extraction
517 stars 122 forks source link

question about the image format and face bounding box #7

Open lulu1315 opened 6 years ago

lulu1315 commented 6 years ago

hello and thanks for the code! I have some questions regarding the image format -your input images are all in 720x576 format . is this mandatory ? -in your readme you say : <FACE_X, FACE_y, FACE_WIDTH, FACE_HEIGHT> is the face bounding box information, either obtained manually or by the face detector. which face detector ? can I use dlib face detector or do you recommend another one ? -your tmp (cropped) images are all 227x227 , is this mandatory ?

thanks in advance

danindiana commented 5 years ago

This is a good question, one that can frustrate persons wanting to use this software out of the box so to speak.

There appears to be another software that outputs the exact csv format, see: https://github.com/torchbox/rustface-py

Going to try and get rustface-py up and running and report back. Would be nice if there was some additional tutorial / explanation in the readme file that would clarify these issues regarding processing new datasets.