8.1.1.3.1.1. blueoil.datasets.base
¶
8.1.1.3.1.1.1. Module Contents¶
8.1.1.3.1.1.1.1. Classes¶
Dataset base class |
|
Dataset base class |
|
Dataset base class |
|
Dataset base class |
|
Make it possible to specify train, validation path. |
-
class
blueoil.datasets.base.
Base
(subset='train', batch_size=10, augmentor=None, pre_processor=None, data_format='NHWC', seed=None, **kwargs)¶ Dataset base class
-
available_subsets
= ['train', 'validation']¶
-
property
data_dir
(self)¶
-
property
classes
¶ Return the classes list in the data set.
-
property
num_classes
¶ Return the number of classes in the data set.
-
property
extend_dir
¶ Return the extend dir path of the data set.
-
property
num_per_epoch
(self)¶ Returns the number of datas in the data subset.
-
property
__getitem__
(self, i)¶ Returns the i-th item of the dataset.
-
property
__len__
(self)¶ returns the number of items in the dataset.
-
-
class
blueoil.datasets.base.
SegmentationBase
(*args, label_colors=None, **kwargs)¶ Bases:
blueoil.datasets.base.Base
Dataset base class
-
property
label_colors
(self)¶
-
property
-
class
blueoil.datasets.base.
ObjectDetectionBase
(subset='train', batch_size=10, augmentor=None, pre_processor=None, data_format='NHWC', seed=None, **kwargs)¶ Bases:
blueoil.datasets.base.Base
Dataset base class
-
abstract classmethod
count_max_boxes
(cls)¶ Count max boxes size over all subsets.
-
property
num_max_boxes
(self)¶ Return count max box size of available subsets.
-
_fill_dummy_boxes
(self, gt_boxes)¶
-
_change_gt_boxes_shape
(self, gt_boxes_list)¶ Change gt boxes list shape from [batch_size, num_boxes, 5] to [batch_size, num_max_boxes, 5].
fill dummy box when num boxes < num max boxes.
- Parameters
gt_boxes_list – python list of gt_boxes(np.ndarray). gt_boxes’s shape is [batch_size, num_boxes, 5]
- Returns
numpy ndarray [batch_size, num_max_boxes, 5].
- Return type
gt_boxes_list
-
abstract classmethod
-
class
blueoil.datasets.base.
KeypointDetectionBase
(subset='train', batch_size=10, augmentor=None, pre_processor=None, data_format='NHWC', seed=None, **kwargs)¶ Bases:
blueoil.datasets.base.Base
Dataset base class
-
static
crop_from_full_image
(full_image, box, joints)¶ Crop one example used for single-person pose estimation from a full sized image. :param full_image: a numpy array of shape (full_height, full_width, 3). :param box: a list, [x1, y1, x2, y2]. :param joints: a numpy array of shape (num_joints, 3). It has global offset.
- Returns
a numpy array cropped from full_image. It’s shape depends on box. new_joints: a numpy array of shape (num_joints, 3). It has local offset.
- Return type
cropped_image
-
static
-
class
blueoil.datasets.base.
DistributionInterface
¶ -
abstract
update_dataset
(self, indices)¶ Update own dataset by indices.
-
abstract
get_shuffle_index
(self)¶ Return list of shuffled index.
-
abstract
-
class
blueoil.datasets.base.
StoragePathCustomizable
(validation_size=0.1, *args, **kwargs)¶ Make it possible to specify train, validation path.
class.extend_dir: specify train path. class.validation_extend_dir: specify validation path.
When validation_extend_dir doesn’t set, generate validation data from train set. You should implement the validation subset split from train data with validation_size in sub class.
-
available_subsets
= ['train', 'validation']¶
-
property
_train_data_dir
(self)¶
-
property
_validation_data_dir
(self)¶
-
property
data_dir
(self)¶
-