Closed eugene123tw closed 4 years ago
yep,ferplus is a image dataset,as claimed in our paper, we aim to solve the occlusion and large pose problem of FER. Therefore, we crop several region of a face and fed the regions and original face into a CNN
video path is just a variable name.
As far as I know FER+ provides images not videos. That being said, I don't quite understand why each face is represented as video in
part_attention_sample.py
. I'm gussing, If fixed position cropping is used, does this meanvideo_path
contains 6 images with different part + original image? Or how do you get the videos and extract frames?