how to train on ADE20K?
Closed this issue · 5 comments
what should I do if I want to train the network on the ADE20K?
Do I need to write a ADE20K_train.h5 file like the cityscapes_train.h5? And the rescale script like the resize_cityscapes.sh?
Looking forward to your response~
To train on ADE20K the authors resize the width of each image to 512 px. Then specify the -ds ADE20k
flag while training. The reason for this is that the encoder reduces the image width and height by a factor of 16, so the dimensions of the input image need to be cropped to the nearest multiple of 16.
The code you release didn't provide the part of resizing the width, did you?
And, if I want to use the conditional gan, the original image and semantic image both need to be resized?
Yes, but resizing is trivial using imagemagick:
for f in ./**/*.png; do
convert $f -resize 512x $f
done
Okay, Thank you very much for your reply~