我正在尝试将 F1 分数定义为 TensorFlow 中的自定义指标DNNClassifier
。为此,我编写了一个函数
def metric_fn(predictions=[], labels=[], weights=[]):
P, _ = tf.contrib.metrics.streaming_precision(predictions, labels)
R, _ = tf.contrib.metrics.streaming_recall(predictions, labels)
if P + R == 0:
return 0
return 2*(P*R)/(P+R)
使用streaming_precision
and streaming_recall
从 TensorFlow 计算 F1 分数。之后我在验证指标中添加了一个新条目:
validation_metrics = {
"accuracy":
tf.contrib.learn.MetricSpec(
metric_fn=tf.contrib.metrics.streaming_accuracy,
prediction_key=tf.contrib.learn.PredictionKey.CLASSES),
"precision":
tf.contrib.learn.MetricSpec(
metric_fn=tf.contrib.metrics.streaming_precision,
prediction_key=tf.contrib.learn.PredictionKey.CLASSES),
"recall":
tf.contrib.learn.MetricSpec(
metric_fn=tf.contrib.metrics.streaming_recall,
prediction_key=tf.contrib.learn.PredictionKey.CLASSES),
"f1score":
tf.contrib.learn.MetricSpec(
metric_fn=metric_fn,
prediction_key=tf.contrib.learn.PredictionKey.CLASSES)
}
然而,尽管我得到了正确的精度和召回值,f1score
总是nan
:
INFO:tensorflow:Saving dict for global step 151: accuracy = 0.982456, accuracy/baseline_label_mean = 0.397661, accuracy/threshold_0.500000_mean = 0.982456, auc = 0.982867, f1score = nan, global_step = 151, labels/actual_label_mean = 0.397661, labels/prediction_mean = 0.406118, loss = 0.310612, precision = 0.971014, precision/positive_threshold_0.500000_mean = 0.971014, recall = 0.985294, recall/positive_threshold_0.500000_mean = 0.985294
我的有问题metric_fn
,但我无法弄清楚。
价值P
and R
获得于metric_fn
具有以下形式Tensor("precision/value:0", shape=(), dtype=float32)
。我觉得这有点奇怪。我期待一个标量张量。
任何帮助表示赞赏。