The OCR approach is rephrased as Segmentation Transformer: https://arxiv.org/abs/1909.11065. This is an official implementation of semantic segmentation for HRNet. https://arxiv.org/abs/1908.07919
Other
3.09k
stars
682
forks
source link
How ca I get the output of the input image size? #243
In the beginning, this net downsamples the input 4 times. So it's output image gets 1/4 width and 1/4 height. What should I do to avoid this? Change the param or delete the downsample?
In the beginning, this net downsamples the input 4 times. So it's output image gets 1/4 width and 1/4 height. What should I do to avoid this? Change the param or delete the downsample?