Python sklearn验证分数含义
每当我在sklearn上培训MLP模型时,我都会在这里得到以下输出:Python sklearn验证分数含义,python,scikit-learn,Python,Scikit Learn,每当我在sklearn上培训MLP模型时,我都会在这里得到以下输出: from sklearn.neural_network import MLPClassifier clf_mlp = MLPClassifier(random_state=1,\ max_iter=200,\ hidden_layer_sizes=(256,256,256),\ e
from sklearn.neural_network import MLPClassifier
clf_mlp = MLPClassifier(random_state=1,\
max_iter=200,\
hidden_layer_sizes=(256,256,256),\
early_stopping = True,\
verbose=True).fit(X, pdf_train["label"])
迭代1,损失=1.23744239
验证分数:0.649914
迭代2,损失=1.07239263
验证分数:0.652249
迭代3,损失=0.99360697
验证分数:0.652205
迭代4,损失=0.90097632
验证分数:0.646963
我对如何阅读这个日志感到困惑:“丢失”是指培训丢失还是验证丢失?“验证分数”值是准确的还是验证损失
如果您能指出在sklearn文档中解释了这一点,我也将不胜感激。看起来打印的
损失是培训损失(默认:日志损失),如所示
打印的验证分数
实际上是验证数据上的分数(默认值:准确度),如所示
这肯定应该有更好的记录,请随意。损失是在培训集()上计算的。验证分数是验证集的准确性。分数函数是根据sklearn的基础定义的
Iteration 1, loss = 1.23744239
Validation score: 0.649914
Iteration 2, loss = 1.07239263
Validation score: 0.652249
Iteration 3, loss = 0.99360697
Validation score: 0.652205
Iteration 4, loss = 0.90097632
Validation score: 0.646963
<And it goes on...>