evaluation_metrics.py 文件源码

def f1_score_semeval(y_true, y_pred):
    #convert probas to 0,1
    y_pred_ones = K.zeros_like(y_true)
    #y_pred_ones[:, K.argmax(y_pred, axis=-1)] = 1

    #indices_x = K.arange(start=0, stop=y_true.get_shape()[0])
    indices_x = K.expand_dims(K.arange(start=0, stop=tf.shape(y_true, name='get_indicec_x_shape')[0], dtype='int64'), dim=-1)
    indices_y = K.expand_dims(K.argmax(y_pred, axis=-1), dim=-1)
    indices = K.concatenate((indices_x, indices_y))
    values = K.sum(K.ones_like(indices_x, dtype='float32'), axis=-1)
    shape = K.cast(tf.shape(y_pred_ones), dtype='int64')
    delta = tf.SparseTensor(indices, values, shape)

    y_pred_ones = y_pred_ones + tf.sparse_tensor_to_dense(delta)

    #where y_ture=1 and y_pred=1 -> true positive
    y_true_pred = K.sum(y_true*y_pred_ones, axis=0)

    #for each class: how many where classified as said class
    pred_cnt = K.sum(y_pred_ones, axis=0)

    #for each class: how many are true members of said class
    gold_cnt = K.sum(y_true, axis=0)

    #precision for each class
    precision = tf.select(K.equal(pred_cnt, 0), K.zeros_like(y_true_pred), y_true_pred/pred_cnt, name='precision_f1_semeval')

    #recall for each class
    recall = tf.select(K.equal(gold_cnt, 0),  K.zeros_like(y_true_pred),  y_true_pred/gold_cnt, name='racall_f1_semeval')

    #f1 for each class
    f1_class = tf.select(K.equal(precision + recall, 0),  K.zeros_like(y_true_pred),  2*(precision*recall)/(precision+recall), name='precision_f1_semeval')

    #return average f1 score over all classes
    return (f1_class[0] + f1_class[2])/2.0