I have been using the pascal voc dataset directly from the torchvision.datasets as:
dataset = torchvision.datasets.VOCSegmentation(root='drive/My Drive/VOC/',
year='2012',
image_set='trainval',
download=False,
transform=transforms.Compose([
transforms.Resize(144),
transforms.CenterCrop(128),
transforms.ToTensor()
]),
target_transform=transforms.Compose([
transforms.Resize(144),
transforms.CenterCrop(128),
transforms.ToTensor()
]),
transforms=None)
but using this I am unsuccessful to do my task since I need a colorful segment of the images, the images, and their respective layers are
how can I make those labels colorful using palette as
[(0, 0, 0),
(128, 0, 0),
(0, 128, 0),
(128, 128, 0),
(0, 0, 128),
(128, 0, 128),
(0, 128, 128),
(128, 128, 128),
(64, 0, 0),
(192, 0, 0),
(64, 128, 0),
(192, 128, 0),
(64, 0, 128),
(192, 0, 128),
(64, 128, 128),
(192, 168, 128),
(0, 64, 0),
(128, 64, 0),
(0, 192, 0),
(128, 192, 0),
(0, 64, 128)]