SVHN¶
-
class
olympus.datasets.svhn.SVHN(data_path)[source]¶ Bases:
olympus.datasets.dataset.AllDatasetSVHN is a real-world image dataset for developing machine learning and object recognition algorithms with minimal requirement on data preprocessing and formatting. It can be seen as similar in flavor to MNIST (e.g., the images are of small cropped digits), but incorporates an order of magnitude more labeled data (over 600,000 digit images) and comes from a significantly harder, unsolved, real world problem (recognizing digits and numbers in natural scene images). SVHN is obtained from house numbers in Google Street View images. More on SVHN.
See also
MNISTReferences
[1] Yuval Netzer, Tao Wang, Adam Coates, Alessandro Bissacco, Bo Wu, Andrew Y. Ng. “Reading Digits in Natural Images with Unsupervised Feature Learning” NIPS Workshop on Deep Learning and Unsupervised Feature Learning 2011 Attributes: - classes: List[int]
Return the mapping between samples index and their class
- input_shape: (3, 32, 32)
Size of a sample returned after transformation
- target_shape: (10,)
The classes are numbers from 0 to 9
- train_size: 47225
Size of the train dataset
- valid_size: 26032
Size of the validation dataset
- test_size: 26032
Size of the test dataset
Methods
categories()Dataset tags so we can filter what we want depending on the task transforms()register_datapipe_as_function register_function