ParallelImageDataGenerator

class mltk.core.preprocess.image.parallel_generator.ParallelImageDataGenerator(*, cores=0.25, debug=False, max_batches_pending=4, get_batch_function=None, preprocessing_function=None, noaug_preprocessing_function=None, validation_augmentation_enabled=True, contrast_range=None, noise=None, random_transforms_enabled=True, max_samples_per_class=- 1, disable_gpu_in_subprocesses=True, save_to_dir=None, save_prefix=None, save_format=None, batch_size=None, **kwargs)[source]

Generate batches of tensor image data with real-time data augmentation.

The data will be looped over (in batches).

This class works the exact same as the Keras ImageDataGenerator except images are processed in the background using the standard Python multiprocessing module.

The can greatly improve training times as multiple CPU cores can process batch images in the background while training is done in the foreground on the GPU(s). (The standard Keras ImageDataGenerator module processes batch images then trains serially)

From the outside, this module works the exact same as Keras ImageDataGenerator.

Parameters
  • cores – The number of CPU cores to use for spawned image batch processes. This number can be either an integer, which specifies the exact number of CPU cores, or it can be a float < 1.0. The float is the percentage of CPU cores to use for processing. A large number of CPU cores will consume more system memory.

  • debug – Use a ThreadPool rather than a Multiprocessing Pool, this allows for single-step debugging the processing function

  • max_batches_pending – This is the number of processed batches to queue. A larger number can improving training times at the expense of increased system memory usage.

  • validation_augmentation_enabled – If True, then augmentations will be applied to validation data. If False, then no augmentations will be applied to validation data.

  • featurewise_center – Boolean. Set input mean to 0 over the dataset, feature-wise.

  • samplewise_center – Boolean. Set each sample mean to 0.

  • featurewise_std_normalization – Boolean. Divide inputs by std of the dataset, feature-wise.

  • samplewise_std_normalization – Boolean. Divide each input by its std.

  • zca_epsilon – epsilon for ZCA whitening. Default is 1e-6.

  • zca_whitening – Boolean. Apply ZCA whitening.

  • rotation_range – Int. Degree range for random rotations.

  • width_shift_range

    Float, 1-D array-like or int

    • float: fraction of total width, if < 1, or pixels if >= 1.

    • 1-D array-like: random elements from the array.

    • int: integer number of pixels from interval (-width_shift_range, +width_shift_range)

    • With width_shift_range=2 possible values are integers [-1, 0, +1], same as with width_shift_range=[-1, 0, +1], while with width_shift_range=1.0 possible values are floats in the interval [-1.0, +1.0).

  • height_shift_range

    Float, 1-D array-like or int

    • float: fraction of total height, if < 1, or pixels if >= 1.

    • 1-D array-like: random elements from the array.

    • int: integer number of pixels from interval (-height_shift_range, +height_shift_range)

    • With height_shift_range=2 possible values are integers [-1, 0, +1], same as with height_shift_range=[-1, 0, +1], while with height_shift_range=1.0 possible values are floats in the interval [-1.0, +1.0).

  • brightness_range – Tuple or list of two floats. Range for picking a brightness shift value from.

  • shear_range – Float. Shear Intensity (Shear angle in counter-clockwise direction in degrees)

  • zoom_range – Float or [lower, upper]. Range for random zoom. If a float, [lower, upper] = [1-zoom_range, 1+zoom_range].

  • channel_shift_range – Float. Range for random channel shifts.

  • fill_mode

    One of {“constant”, “nearest”, “reflect” or “wrap”}. Default is ‘nearest’. Points outside the boundaries of the input are filled according to thegiven mode:

    • constant kkkkkkkk|abcd|kkkkkkkk (cval=k)

    • nearest aaaaaaaa|abcd|dddddddd

    • reflect abcddcba|abcd|dcbaabcd

    • wrap abcdabcd|abcd|abcdabcd

  • cval – Float or Int. Value used for points outside the boundaries when fill_mode = "constant".

  • horizontal_flip – Boolean. Randomly flip inputs horizontally.

  • vertical_flip – Boolean. Randomly flip inputs vertically.

  • rescale – rescaling factor. Defaults to None. If None or 0, no rescaling is applied, otherwise we multiply the data by the value provided (after applying all other transformations).

  • get_batch_function

    function that should return the transformed batch. If this is omitted, then iterator.get_batches_of_transformed_samples() is used. NOTE: If this is supplied, then none of the other callbacks are used. This function should have the following signature:

    def get_batches_of_transformed_samples(
       batch_index:int,
       filenames:List[str],
       classes:List[int],
       params:ParallelProcessParams
    ) -> Tuple[int, Tuple[np.ndarray, np.ndarray]]:
        ...
        return batch_index, (batch_x, batch_y)
    

  • noaug_preprocessing_function

    function that will be applied on each input. The function will run after the image is resized but before it is augmented or standardized. The function should take at least two arguments and return the processed image:

    def my_processing_func(
        params: ParallelProcessParams,
        x : np.ndarray,
        class_id: Optional[int],
        filename: Optional[str],
        batch_index: Optional[int],
        batch_class_ids: Optional[List[int]],
        batch_filenames: Optional[List[str]]
     ) -> np.ndarray:
        ...
        return processed_x
    

  • preprocessing_function

    function that will be applied on each input. The function will run after the image is resized (if interpolation != None) and augmented but before it is standardized. The function should take at least two arguments and return the processed image:

    def my_processing_func(
        params: ParallelProcessParams,
        x : np.ndarray,
        class_id: Optional[int],
        filename: Optional[str],
        batch_index: Optional[int],
        batch_class_ids: Optional[List[int]],
        batch_filenames: Optional[List[str]]
     ) -> np.ndarray:
       ...
       return processed_x
    

  • validation_split – Float. Fraction of images reserved for validation (strictly between 0 and 1).

  • dtype – Dtype to use for the generated arrays.

  • brightness_range – Tuple of two floats. Control the brightness of an image. An enhancement factor of 0.0 gives a black image. A factor of 1.0 gives the original image.

  • contrast_range – Tuple of two floats. Control the contrast of an image, similar to the contrast control on a TV set. An enhancement factor of 0.0 gives a solid grey image. A factor of 1.0 gives the original image.

  • noise

    List one one or more of the following:

    • gauss - Gaussian-distributed additive noise.

    • poisson - Poisson-distributed noise generated from the data.

    • s&p - Replaces random pixels with 0 or 1.

    • speckle - Multiplicative noise using out = image + n*image,where

      n is uniform noise with specified mean & variance.

    The noise type used will be randomly selected from the provided list per image

  • random_transforms_enabled – Enable random data augmentations. Default True

  • max_samples_per_class – The maximum number of samples to use for a given class. If -1 then use all available samples. Default -1.

  • disable_gpu_in_subprocesses – Disable GPU usage in spawned subprocesses, default: true

  • batch_size – Generated batch size. This overrides the value given to flow_from_directory() Set to -1 to set the batch size to be the number of samples

Properties

default_transform

Return default transformation parameters

__init__(*, cores=0.25, debug=False, max_batches_pending=4, get_batch_function=None, preprocessing_function=None, noaug_preprocessing_function=None, validation_augmentation_enabled=True, contrast_range=None, noise=None, random_transforms_enabled=True, max_samples_per_class=- 1, disable_gpu_in_subprocesses=True, save_to_dir=None, save_prefix=None, save_format=None, batch_size=None, **kwargs)[source]

Methods

__init__

apply_transform

Apply the given transformation to the given image

fit

Fits the data generator to some sample data.

flow

Takes data & label arrays, generates batches of augmented data.

flow_from_directory

Create the ParallelImageDataGenerator with the given dataset directory

get_random_transform

Generate a random transformation

random_transform

Applies a random transformation to an image.

standardize

Applies the normalization configuration in-place to a batch of inputs.

flow_from_directory(directory, target_size=(256, 256), color_mode='rgb', classes=None, class_mode='categorical', batch_size=32, batch_shape=None, shuffle=True, shuffle_index_dir=None, seed=None, save_to_dir=None, save_prefix=None, save_format='png', follow_links=False, subset=None, interpolation='bilinear', list_valid_filenames_in_directory_function=None, class_counts=None)[source]

Create the ParallelImageDataGenerator with the given dataset directory

Takes the path to a directory & generates batches of augmented data.

Parameters
  • directory – string, path to the target directory. It should contain one subdirectory per class. Any PNG, JPG, BMP, PPM or TIF images inside each of the subdirectories directory tree will be included in the generator.

  • target_size – Tuple of integers (height, width), defaults to (256, 256). The dimensions to which all images found will be resized.

  • color_mode – One of “grayscale”, “rgb”, “rgba”. Default: “rgb”. Whether the images will be converted to have 1, 3, or 4 channels.

  • classes – Required, list of class subdirectories (e.g. [‘dogs’, ‘cats’]).

  • class_mode

    One of “categorical”, “binary”, “sparse”, “input”, or None. Default: “categorical”. Determines the type of label arrays that are returned:

    • categorical will be 2D one-hot encoded labels,

    • binary will be 1D binary labels, “sparse” will be 1D integer labels,

    • input will be images identical to input images (mainly used to work with autoencoders).

    • None no labels are returned (the generator will only yield batches of image data, which is useful to use with model.predict()).

    Please note that in case of class_mode None, the data still needs to reside in a subdirectory of directory for it to work correctly.

  • batch_size – Size of the batches of data (default: 32).

  • batch_shape – Shape of the batches of data. If omitted, this defaults to (batch_size, target_size)

  • shuffle – Whether to shuffle the data (default: True) If set to False, sorts the data in alphanumeric order.

  • shuffle_index_dir – If given, the dataset directory will be shuffled the first time it is processed and and an index file containing the shuffled file names is generated at the directory specified by shuffle_index_dir. The index file is reused to maintain the shuffled order for subsequent processing. If None, then the dataset samples are sorted alphabetically and saved to an index file in the dataset directory. The alphabetical index file is used for subsequent processing. Default: None

  • seed – Optional random seed for shuffling and transformations.

  • follow_links – Whether to follow symlinks inside class subdirectories (default: False).

  • subset – Subset of data (“training” or “validation”) if validation_split is set in ParallelAudioDataGenerator.

  • interpolation – Interpolation method used to resample the image if the target size is different from that of the loaded image. Supported methods are none, nearest, bilinear, bicubic, lanczos, box, and hamming. If none is used, then the image is not automatically resized. By default, bilinear is used.

  • list_valid_filenames_in_directory_function

    This is a custom function called for each class, that should return a list of valid file names for the given class. It has the following function signature:

    def list_valid_filenames_in_directory(
        base_directory:str,
        search_class:str,
        white_list_formats:List[str],
        split:float,
        follow_links:bool,
        shuffle_index_directory:str
    ) -> Tuple[str, List[str]]
        ...
        return search_class, filenames
    

  • Returns – A DirectoryIterator yielding tuples of (x, y) where x is a numpy array containing a batch of images with shape (batch_size, target_size, channels) and y is a numpy array of corresponding labels.

flow(x, y=None, batch_size=32, shuffle=True, sample_weight=None, seed=None, save_to_dir=None, save_prefix='', save_format='png', subset=None)[source]

Takes data & label arrays, generates batches of augmented data.

Parameters
  • x – Input data. Numpy array of rank 4 or a tuple. If tuple, the first element should contain the images and the second element another numpy array or a list of numpy arrays that gets passed to the output without any modifications. Can be used to feed the model miscellaneous data along with the images. In case of grayscale data, the channels axis of the image array should have value 1, in case of RGB data, it should have value 3, and in case of RGBA data, it should have value 4.

  • y – Labels.

  • batch_size – Int (default: 32).

  • shuffle – Boolean (default: True).

  • sample_weight – Sample weights.

  • seed – Int (default: None).

  • save_to_dir – None or str (default: None). This allows you to optionally specify a directory to which to save the augmented pictures being generated (useful for visualizing what you are doing).

  • save_prefix – Str (default: ''). Prefix to use for filenames of saved pictures (only relevant if save_to_dir is set).

  • save_format – one of “png”, “jpeg”, “bmp”, “pdf”, “ppm”, “gif”, “tif”, “jpg” (only relevant if save_to_dir is set). Default: “png”.

  • subset – Subset of data ("training" or "validation") if validation_split is set in ImageDataGenerator.

Returns

An Iterator yielding tuples of (x, y)

where x is a numpy array of image data (in the case of a single image input) or a list of numpy arrays (in the case with additional inputs) and y is a numpy array of corresponding labels. If ‘sample_weight’ is not None, the yielded tuples are of the form (x, y, sample_weight). If y is None, only the numpy array x is returned.

Raises

ValueError – If the Value of the argument, subset is other than “training” or “validation”.

property default_transform: dict

Return default transformation parameters

Return type

dict

get_random_transform(img_shape, seed=None)[source]

Generate a random transformation

Return type

dict

apply_transform(x, transform_parameters)[source]

Apply the given transformation to the given image

fit(x, augment=False, rounds=1, seed=None)

Fits the data generator to some sample data.

This computes the internal data stats related to the data-dependent transformations, based on an array of sample data.

Only required if featurewise_center or featurewise_std_normalization or zca_whitening are set to True.

When rescale is set to a value, rescaling is applied to sample data before computing the internal data stats.

# Arguments
x: Sample data. Should have rank 4.

In case of grayscale data, the channels axis should have value 1, in case of RGB data, it should have value 3, and in case of RGBA data, it should have value 4.

augment: Boolean (default: False).

Whether to fit on randomly augmented samples.

rounds: Int (default: 1).

If using data augmentation (augment=True), this is how many augmentation passes over the data to use.

seed: Int (default: None). Random seed.

random_transform(x, seed=None)

Applies a random transformation to an image.

# Arguments

x: 3D tensor, single image. seed: Random seed.

# Returns

A randomly transformed version of the input (same shape).

standardize(x)

Applies the normalization configuration in-place to a batch of inputs.

x is changed in-place since the function is mainly used internally to standardize images and feed them to your network. If a copy of x would be created instead it would have a significant performance cost. If you want to apply this method without changing the input in-place you can call the method creating a copy before:

standardize(np.copy(x))

# Arguments

x: Batch of inputs to be normalized.

# Returns

The inputs, normalized.