visualize_mask_transforms

hybrid_learning.datasets.data_visualization.visualize_mask_transforms(titled_datasets, save_as=None, max_num_samples=3)[source]

Visualize difference between original and the transformed masks of datasets. Visualization results will be shown using matplotlib.pyplot.imshow() functionality and are optionally saved to a file.

Parameters

titled_datasets (Dict[str, ActivationDatasetWrapper]) – mapping of title to dataset to be visualized; datasets must have the attribute/property dataset holding the original dataset in same indexing order; the data contained in each dataset must be a sequence yielding tuples of (any, transformed mask); data.dataset must be a sequence yielding tuples of (original image, original mask);
save_as (Optional[str]) – file path to save the image under using matplotlib.pyplot.savefig(); not saved if None
max_num_samples (int) – the maximum number of samples to show for each dataset

Return type

None