Tensorflow中Estimator中的自定义eval_metric_ops
我试图像这样在估算器的eval_metric_ops中添加r的平方:
def model_fn(features, labels, mode, params): predict = prediction(features, params, mode)
loss = my_loss_fn
eval_metric_ops = {
'rsquared': tf.subtract(1.0, tf.div(tf.reduce_sum(tf.squared_difference(label, tf.reduce_sum(tf.squared_difference(labels, tf.reduce_mean(labels)))),
name = 'rsquared')
}
train_op = tf.contrib.layers.optimize_loss(
loss = loss,
global_step = global_step,
learning_rate = 0.1,
optimizer = "Adam"
)
predictions = {"predictions": predict}
return tf.estimator.EstimatorSpec(
mode = mode,
predictions = predictions,
loss = loss,
train_op = train_op,
eval_metric_ops = eval_metric_ops
)
但我有以下错误:
TypeError:eval_metric_ops的值必须为(metric_value,update_op)元组,给定:键:rsquared的Tensor(“
rsquared:0”,shape =(),dtype = float32)
我也尝试过不使用name参数,但是没有任何改变。您知道如何创建此eval_metric_ops吗?
回答:
eval_metric_ops
需要按名称键入度量指标的字典。dict的值是调用度量函数的结果。您可以使用tf.metrics
以下指标来实现您的指标功能:
def metric_fn(labels, predict): SST, update_op1 = tf.metrics.mean_squared_error(labels, tf.reduce_mean(labels))
SSE, update_op2 = tf.metrics.mean_squared_error(labels, predictions )
return tf.subtract(1.0, tf.div(SSE, SST)), tf.group(update_op1, update_op2))
以上是 Tensorflow中Estimator中的自定义eval_metric_ops 的全部内容, 来源链接: utcz.com/qa/400426.html