images, captions = [], []
bpg = bad_pair_generator(images, captions)

clfr = classifier()
data = ([(1, img, cpt) for img, cpt in zip(images, captions)] +
        [(0, img, cpt) for img, cpt in bpg.generate(N)])

for epoch in range(epochs):
    good_pairs, bad_pairs = zip(images, captions), bpg.generate(N)
    X, y = good_pairs + bad_pairs, [1]*len(good_pairs) + [0]*len(bad_pairs)

    clfr.train(X, y)

    trickiness = [yi == yi_pred for yi, yi_pred in zip(y, clfr.predict(X))]
    bpg.fit(bad_pairs, trickiness[-len(bad_pairs):])