平时用的评价指标
tf.metrics.accuracy()
tf.metrics.precision()
tf.metrics.recall()
需要注意:
tf.metrics 不支持precision/recall/f1多分类效果指标的计算,其中为二分类指标
计算二分类precision/recall效果指标,可通过如下实现方式:
def metric_fn(per_example_loss, label_ids, logits):
predictions = tf.argmax(logits, axis=-1, output_type=tf.int32)
accuracy = tf.metrics.accuracy(label_ids, predictions)
recall = tf.metrics.recall(label_ids, predictions)
precision = tf.metrics.precision(label_ids, predictions)
loss = tf.metrics.mean(per_example_loss)
return {
"eval_accuracy": accuracy,
"eval_loss": loss,
"recall": recall,
"precision": precision,
}
计算多分类macro-precision/macro-recall效果指标,可通过如下实现方式:
(