Digits

Optical Recognition of Handwritten Digits

ImagesCustom

The DIGITS dataset consists of 1797 8×8 grayscale images (1439 for training and 360 for testing) of handwritten digits.

Source: Differentially Private Variational Dropout Image Source: https://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_digits.html

Benchmarks

Classification/Accuracy Feature Importance/Pearson Correlation Graph Classification/Accuracy Optical Character Recognition (OCR)/F1 - macro

Related Benchmarks

DigitShapes/Time Series Classification/Accuracy DigitShapes/Time Series Classification/NLL Digits-five/Domain Adaptation/Accuracy Digits-five/Domain Generalization/Accuracy Digits-five/Single-Source Domain Generalization/Accuracy