data_generator.py

class TripletGenerator:
    def __init__(self, datadict, hard_frac = 0.2, batch_size=256):
        self.datadict = datadict
        self._anchor_idx = np.array(list(self.datadict.keys()))
        self._hard_frac = hard_frac
        self._generator = self.generate_batch(batch_size)

    def generate_batch(self, size):
        while True:

            hards = int(size*self._hard_frac)
            anchor_ids = np.array(np.random.choice(self._anchor_idx, size, replace=False))

            anchors = self.get_anchors(anchor_ids)
            positives = self.get_positives(anchor_ids)
            negatives = np.hstack([self.get_hard_negatives(anchor_ids[:hards]),
                                   self.get_random_negatives(anchor_ids[hards:])])
            labels = np.ones((size,1))

            assert len(anchors) == len(positives) == len(negatives) == len(labels) == size

            yield [anchors, positives, negatives], labels