"""Pascal VOC Semantic Segmentation Dataset."""
import os
import numpy as np
from PIL import Image
from ..segbase import SegmentationDataset
[docs]class VOCSegmentation(SegmentationDataset):
"""Pascal VOC Semantic Segmentation Dataset.
Parameters
----------
root : string
Path to VOCdevkit folder. Default is '$(HOME)/mxnet/datasets/ade'
split: string
'train', 'val' or 'test'
transform : callable, optional
A function that transforms the image
Examples
--------
>>> from mxnet.gluon.data.vision import transforms
>>> # Transforms for Normalization
>>> input_transform = transforms.Compose([
>>> transforms.ToTensor(),
>>> transforms.Normalize([.485, .456, .406], [.229, .224, .225]),
>>> ])
>>> # Create Dataset
>>> trainset = gluonvision.data.VOCSegmentation(split='train', transform=input_transform)
>>> # Create Training Loader
>>> train_data = gluon.data.DataLoader(
>>> trainset, 4, shuffle=True, last_batch='rollover',
>>> num_workers=4)
"""
BASE_DIR = 'VOC2012'
def __init__(self, root=os.path.expanduser('~/.mxnet/datasets/voc'),
split='train', transform=None):
super(VOCSegmentation, self).__init__(root)
self.root = root
_voc_root = os.path.join(self.root, self.BASE_DIR)
_mask_dir = os.path.join(_voc_root, 'SegmentationClass')
_image_dir = os.path.join(_voc_root, 'JPEGImages')
self.transform = transform
self.train = split
# train/val/test splits are pre-cut
_splits_dir = os.path.join(_voc_root, 'ImageSets/Segmentation')
if self.train == 'train':
_split_f = os.path.join(_splits_dir, 'trainval.txt')
elif self.train == 'val':
_split_f = os.path.join(_splits_dir, 'val.txt')
elif self.train == 'test':
_split_f = os.path.join(_splits_dir, 'test.txt')
else:
raise RuntimeError('Unknown dataset split.')
self.images = []
self.masks = []
with open(os.path.join(_split_f), "r") as lines:
for line in lines:
_image = os.path.join(_image_dir, line.rstrip('\n')+".jpg")
assert os.path.isfile(_image)
self.images.append(_image)
if self.train != 'test':
_mask = os.path.join(_mask_dir, line.rstrip('\n')+".png")
assert os.path.isfile(_mask)
self.masks.append(_mask)
if self.train != 'test':
assert (len(self.images) == len(self.masks))
def __getitem__(self, index):
img = Image.open(self.images[index]).convert('RGB')
if self.train == 'test':
img = self._img_transform(img)
if self.transform is not None:
img = self.transform(img)
return img, os.path.basename(self.images[index])
timg = Image.open(self.masks[index])
target = np.array(timg, dtype=np.uint8)
target[target == 255] = -1
target = Image.fromarray(target)
# synchrosized transform
if self.train == 'train':
img, target = self._sync_transform(img, target)
elif self.train == 'val':
img, target = self._val_sync_transform(img, target)
else:
raise RuntimeError('unknown mode for dataloader: {}'.format(self.mode))
# general resize, normalize and toTensor
if self.transform is not None:
img = self.transform(img)
return img, target
def __len__(self):
return len(self.images)
@property
def classes(self):
"""Category names."""
return ('background', 'airplane', 'bicycle', 'bird', 'boat', 'bottle',
'bus', 'car', 'cat', 'chair', 'cow', 'diningtable', 'dog', 'horse',
'motorcycle', 'person', 'potted-plant', 'sheep', 'sofa', 'train',
'tv', 'ambiguous')