Dataset Class in Semi supervised learning

[rahul-ahuja]

    def batches(self, batch_size, which_set="train"):
        x_name = which_set + "_x"
        y_name = which_set + "_y"

        num_examples = len(getattr(dataset, y_name))
        if self.shuffle:
            idx = np.arange(num_examples)
            np.random.shuffle(idx)
            setattr(dataset, x_name, getattr(dataset, x_name)[idx])
            setattr(dataset, y_name, getattr(dataset, y_name)[idx])
            if which_set == "train":
                dataset.label_mask = dataset.label_mask[idx]

        dataset_x = getattr(dataset, x_name)
        dataset_y = getattr(dataset, y_name)
        for ii in range(0, num_examples, batch_size):
            x = dataset_x[ii:ii+batch_size]
            y = dataset_y[ii:ii+batch_size]

            if which_set == "train":
                # When we use the data for training, we need to include
                # the label mask, so we can pretend we don't have access
                # to some of the labels, as an exercise of our semi-supervised
                # learning ability
                yield x, y, self.label_mask[ii:ii+batch_size]
            else:
                yield x, y

"dataset" should be replace with "self" at above batch method

Credits to Phillip Dudero https://discussions.udacity.com/t/getattr-dataset-in-dataset-batches/767950