Init

biapy.data.generators.create_train_val_augmentors(cfg, X_train, Y_train, X_val, Y_val, world_size, global_rank, dist=False)[source]

Create training and validation generators.

Parameters:

  • cfg (YACS CN object) – Configuration.

  • X_train (4D/5D Numpy array) – Training data. E.g. (num_of_images, y, x, channels) for 2D or (num_of_images, z, y, x, channels) for 3D.

  • Y_train (4D/5D Numpy array) – Training data mask/class. E.g. (num_of_images, y, x, channels) for 2D or (num_of_images, z, y, x, channels) for 3D in all the workflows except classification. For this last the shape is (num_of_images, class) for both 2D and 3D.

  • X_val (4D/5D Numpy array) – Validation data mask/class. E.g. (num_of_images, y, x, channels) for 2D or (num_of_images, z, y, x, channels) for 3D.

  • Y_val (4D/5D Numpy array) – Validation data mask/class. E.g. (num_of_images, y, x, channels) for 2D or (num_of_images, z, y, x, channels) for 3D in all the workflows except classification. For this last the shape is (num_of_images, class) for both 2D and 3D.

Returns:

  • train_generator (Pair2DImageDataGenerator/Single2DImageDataGenerator (2D) or Pair3DImageDataGenerator/Single3DImageDataGenerator (3D)) – Training data generator.

  • val_generator (Pair2DImageDataGenerator/Single2DImageDataGenerator (2D) or Pair3DImageDataGenerator/Single3DImageDataGenerator (3D)) – Validation data generator.

biapy.data.generators.create_test_augmentor(cfg, X_test, Y_test, cross_val_samples_ids)[source]

Create test data generator.

Parameters:

  • cfg (YACS CN object) – Configuration.

  • X_test (4D Numpy array) – Test data. E.g. (num_of_images, y, x, channels) for 2D or (num_of_images, z, y, x, channels) for 3D.

  • Y_test (4D Numpy array) – Test data mask/class. E.g. (num_of_images, y, x, channels) for 2D or (num_of_images, z, y, x, channels) for 3D in all the workflows except classification. For this last the shape is (num_of_images, class) for both 2D and 3D.

  • cross_val_samples_ids (List of ints, optional) – When cross validation is used training data samples’ id are passed.

Returns:

test_generator – Test data generator.

Return type:

test_pair_data_generator

biapy.data.generators.check_generator_consistence(gen, data_out_dir, mask_out_dir, filenames=None)[source]

Save all data of a generator in the given path.

Parameters:

  • gen (Pair2DImageDataGenerator/Single2DImageDataGenerator (2D) or Pair3DImageDataGenerator/Single3DImageDataGenerator (3D)) – Generator to extract the data from.

  • data_out_dir (str) – Path to store the generator data samples.

  • mask_out_dir (str) – Path to store the generator data mask samples.

  • Filenames (List, optional) – Filenames that should be used when saving each image.

class biapy.data.generators.MultiEpochsDataLoader(*args, **kwargs)[source]

Bases: DataLoader