DataGenerator.py

import numpy as np
from tensorflow.keras.utils import Sequence
from tensorflow.keras.utils import to_categorical

class DataGenerator(Sequence):
    'Generates data for Keras'
    def __init__(self, list_IDs, labels, batch_size=32, dim=(128, 128), n_channels=1,
                 n_classes=91, shuffle=True):
        'Initialization'
        self.dim = dim
        self.batch_size = batch_size
        self.labels = labels
        self.list_IDs = list_IDs
        self.n_channels = n_channels
        self.n_classes = n_classes
        self.shuffle = shuffle
        self.on_epoch_end()


    def __len__(self):
        'Denotes the number of batches per epoch'
        return int(np.floor(len(self.list_IDs) / self.batch_size))

    def __getitem__(self, index):
        'Generate one batch of data'
        # Generate indexes of the batch
        indexes = self.indexes[index*self.batch_size:(index+1)*self.batch_size]


        # Generate data
        X, y = self.__data_generation(indexes)

        return X, y

    def on_epoch_end(self):
        'Updates indexes after each epoch'
        self.indexes = np.arange(len(self.list_IDs))
        if self.shuffle == True:
            np.random.shuffle(self.indexes)

    def __data_generation(self, indexes):
        'Generates data containing batch_size samples' # X : (n_samples, *dim, n_channels)
        # Initialization
        X = np.empty((self.batch_size, *self.dim, self.n_channels))
        y = np.empty((self.batch_size, self.n_classes), dtype=int)


        # Generate data
        import cv2
        for i, idx in enumerate(indexes):
            # Store sample
            ID = self.list_IDs[idx]
            # print(ID)
            X[i,] = np.array(cv2.imread(ID))[:, :, 0, np.newaxis] / 255

            # Store class
            y[i] = self.labels[idx]

        return X, y