kosmos.ml.datasets.mnist_dataset¶
Classes¶
- class MNISTDataset(*, min_max_scaler: bool = True)¶
Bases:
kosmos.ml.datasets.dataset.SLDatasetMNIST handwritten digits dataset for multiclass classification.
Notes
Number of instances: 70,000 (60,000 train + 10,000 test)
Number of features: 784 numeric (28x28 pixel images, flattened)
Classes: 10 (digits 0-9, roughly balanced)
References
OpenML — MNIST dataset: https://www.openml.org/d/554
Initialize the dataset.
- Parameters:
min_max_scaler (bool) – Whether to apply min-max scaling to the features.
Properties
- property class_names¶
Return human-readable class labels of numbers 0-9.
- property input_dimension¶
Number of feature columns.
- property output_dim¶
Number of distinct classes.