Closed ThomasDelteil closed 6 years ago
@zhanghang1989
The reason is because the training images are augmented by default. Discussed with @hetong007 about that and in my opinion, there should be a flag to disable the default augmentation, or default augmentation should be passed by default to the transform argument. Right now you would need to do
trainset = gluoncv.data.VOCSegmentation(split='train')
trainset.mode = 'test'
in order to get training images without data augmentation.
the artefact happen also on validation set, root cause was a bug in denormalize https://github.com/dmlc/gluon-cv/pull/181
Thanks for reporting! There was a bug in denormalization.
Using
gluoncv 0.2
this is the output I get when running the image segmentation tutorial:Is this the expected output? The mask looks strange and the denormalized image has artefact.