yinguobing / facial-landmark-detection-hrnet

A TensorFlow implementation of HRNet for facial landmark detection.
GNU General Public License v3.0
157 stars 40 forks source link

image_size #1

Open luoww1992 opened 3 years ago

luoww1992 commented 3 years ago

i have see your work, it is beautiful ! i have do all works before training, and i have see the HRNet lib for face landmark, it seem to have different size in input and output for images at current work ?

yinguobing commented 3 years ago

Hi, @luoww1992

The current model's input size is [batch_size, 256, 256, 3], and the output is a group of heatmaps, not images, which means they do not need to be same in size.

This is a TensorFlow implementation for HRNet, please refer to the papar for more model details.