active.py 文件源码

def do_batch_sampling(pp_unl, batch_size):
    """
    return batch_size number of of item, sampled by uncertainty
    each with a label sampled from prob
    """
    n = pp_unl.shape[0]
    uncertain = np.abs(pp_unl[:,0] - 0.5)
    if n < batch_size:
        batch_size = n
    sam_weight = np.exp(20 * (1-uncertain))
    items = np.random.choice(n, batch_size, replace = False, p = sam_weight*1.0 / np.sum(sam_weight) )
    labels = np.zeros_like(items)

    for (i,item) in enumerate(items):
        if np.random.random() < pp_unl[item, 1]: 
            l = 1 
        else:
            l = 0
        labels[i] = l

    return (items, labels)