Convert image color with provided `mode`.

Load an image, returns PIL.Image.

Convert a PIL.Image to numpy array.

to_categorical. Convert class vector (integers from 0 to nb_classes) to binary class matrix, for use with categorical_crossentropy. Arg

Read a directory, and list all subdirectories files as class sample

Resize an image. Arguments: in_image: `PIL.Image`. The image to resize. new_width: `int`. The image new width. new_heigh

Load a image and return the channel of the image :param image_path: :return: the channel of the image

Creates a dictionary char:integer for each unique character

save. Saves vocabulary processor into given file. Arguments: filename: Path to output file.

shuffle. Shuffle given arrays at unison, along first axis. Arguments: *arrs: Each array to shuffle at unison. Returns:

string_to_semi_redundant_sequences. Vectorize a string and returns parsed sequences and targets, along with the associated dictionary.

Build HDF5 Image Dataset. Build an HDF5 dataset by providing either a root folder or a plain text file with images path and class id. '

featurewise_std_normalization. Scale each sample by the specified standard deviation. If no std specified, std is evaluated over all samples

featurewise_zero_center. Zero center every sample with specified mean. If not specified, the mean is evaluated over all samples. Argume

fit. Learn a vocabulary dictionary of all tokens in the raw documents. Arguments: raw_documents: An iterable which yiel

fit_transform. Learn the vocabulary dictionary and return indexies of words. Arguments: raw_documents: An iterable whic

Image PreLoader. Create a python array (`Preloader`) that loads images on the fly (from disk or url). There is two ways to provide image sam

load_csv. Load data from a CSV file. By default the labels are considered to be the last column, but it can be changed by filling 'target_co

pad_sequences. Pad each sequence to the same length: the length of the longest sequence. If maxlen is provided, any sequence longer than max

restore. Restores vocabulary processor from given file. Arguments: filename: Path to file to load from. Return

reverse. Reverses output of vocabulary mapping to words. Arguments: documents: iterable, list of class ids. Re

samplewise_std_normalization. Scale each sample with its standard deviation. Arguments: X: `array`. The batch of samples to scale.

samplewise_zero_center. Zero center each sample by subtracting it by its mean. Arguments: X: `array`. The batch of samples to cente

Vectorize Text file

transform. Transform documents to word-id matrix. Convert words to ids with vocabulary fitted with fit or the one provided