places205Dataset#
- class places205Dataset(classes=201, path='places205_data', **kwards)#
Bases:
DatasetWrapper
A wrapper to the places205 dataset, available at http://places.csail.mit.edu/. The current wrapper class supplyes the required transformations, and also implements the required DatasetWrapper methods.
- __init__(classes=201, path='places205_data', **kwards)#
Initializes the places205Dataset wrapper, providing an interface for handling the Places205 dataset. This class is registered under the name ‘Places205’ in the DSFactory.
- Parameters:
classes (int, optional) – The number of classes in the dataset. Defaults to 201.
path (str, optional) – The directory where the dataset is stored. Defaults to ‘places205_data’.
**kwargs – Unused keyword arguments, included for compatibility with other dataset constructors.
Methods
__init__
([classes, path])Initializes the places205Dataset wrapper, providing an interface for handling the Places205 dataset.
get_approximation_set
()returns the approximation data set, to be used for range approximation
get_class_labels_dict
()Returns the class_name to index mapping
get_samples_per_class
(dataset)Returns the number of samples in each class or None (if the dataset is balanced - None is equivalent to a list with equal numbers) :param dataset: the dataset split :type dataset: Dataset
Returns the test data
Returns the training data
get_train_pipe_ffcv
(args)Returns the Dictionary defining for each field the sequence of ffcv Decoders and transforms to apply.
Returns the validation data
Always returns False - places205 dataset is balanced
- get_test_data()#
Returns the test data
- get_train_data()#
Returns the training data
- get_val_data()#
Returns the validation data
- is_imbalanced()#
Always returns False - places205 dataset is balanced