Thanks a lot for your repository. While reading through train.py I noticed that PASCAL VOC images are being resized to 321x321 in this line.
In the original paper they perform a random cropping on img and gt mask. Here is an example from the corresponding Tensorflow code. There mask and image are concatenated and then cropped simultaneously.
Thanks a lot for your repository. While reading through
train.py
I noticed that PASCAL VOC images are being resized to 321x321 in this line. In the original paper they perform a random cropping on img and gt mask. Here is an example from the corresponding Tensorflow code. There mask and image are concatenated and then cropped simultaneously.