mdai.utils package

Submodules

mdai.utils.common_utils module

mdai.utils.common_utils.hex2rgb(h)

Convert Hex color encoding to RGB color

mdai.utils.common_utils.json_to_dataframe(json_file, dataset='all_datasets', should_return_labels=False)

mdai.utils.common_utils.train_test_split(dataset, shuffle=True, validation_split=0.1)

Split image ids into training and validation sets. TODO: Need to update dataset.dataset_data! TODO: What to set for images_dir for combined dataset?

mdai.utils.keras_utils module

class mdai.utils.keras_utils.DataGenerator(dataset, batch_size=32, dim=(32, 32), n_channels=1, n_classes=10, shuffle=True, to_RGB=True, rescale=False)

Bases: keras.utils.data_utils.Sequence

on_epoch_end()

Updates indexes after each epoch

mdai.utils.tensorflow_utils module

Module contents