8.1.1.3.1.4. blueoil.datasets.camvid
¶
8.1.1.3.1.4.1. Module Contents¶
8.1.1.3.1.4.1.1. Classes¶
Base class for CamVid and the variant dataset formats. |
|
CamVid |
|
CamvidCustom |
8.1.1.3.1.4.1.2. Functions¶
|
Returns numpy array of an image |
-
blueoil.datasets.camvid.
get_image
(filename, convert_rgb=True, ignore_class_idx=None)¶ Returns numpy array of an image
-
class
blueoil.datasets.camvid.
CamvidBase
(batch_size=10, *args, **kwargs)¶ Bases:
blueoil.datasets.base.SegmentationBase
Base class for CamVid and the variant dataset formats.
http://www0.cs.ucl.ac.uk/staff/G.Brostow/papers/Brostow_2009-PRL.pdf https://github.com/alexgkendall/SegNet-Tutorial/tree/master/CamVid
-
extend_dir
= CamVid¶
-
ignore_class_idx
¶
-
property
num_per_epoch
(self)¶ Returns the number of datas in the data subset.
-
files_and_annotations
(self)¶ Return all files and gt_boxes list.
-
__getitem__
(self, i)¶ Returns the i-th item of the dataset.
-
__len__
(self)¶ returns the number of items in the dataset.
-
-
class
blueoil.datasets.camvid.
Camvid
(batch_size=10, *args, **kwargs)¶ Bases:
blueoil.datasets.camvid.CamvidBase
CamVid
Original CamVid dataset format. http://www0.cs.ucl.ac.uk/staff/G.Brostow/papers/Brostow_2009-PRL.pdf https://github.com/alexgkendall/SegNet-Tutorial/tree/master/CamVid
-
IMAGE_HEIGHT
= 360¶
-
IMAGE_WIDTH
= 480¶
-
NUM_EXAMPLES_PER_EPOCH_FOR_TRAIN
= 367¶
-
NUM_EXAMPLES_PER_EPOCH_FOR_TEST
= 101¶
-
classes
= ['sky', 'building', 'pole', 'road', 'pavement', 'tree', 'signsymbol', 'fence', 'car', 'pedestrian', 'bicyclist']¶
-
num_classes
¶
-
property
label_colors
(self)¶
-
property
files_and_annotations
(self)¶ Return all files and gt_boxes list.
-
-
class
blueoil.datasets.camvid.
CamvidCustom
(batch_size=10, *args, **kwargs)¶ Bases:
blueoil.datasets.base.StoragePathCustomizable
,blueoil.datasets.camvid.CamvidBase
CamvidCustom
CamVid base custom dataset format.
-
property
label_colors
(self)¶
-
property
classes
(self)¶ Return the classes list in the data set.
-
property
num_classes
(self)¶ Return the number of classes in the data set.
-
parse_labels
(self)¶
-
property
files_and_annotations
(self)¶ Return image and annotation file list. If there is no test dataset, then split dataset to train and test lists with specific ratio.
-
property