神经网络 (NN) epoch 与 scikit-learn 中的 max_iter 参数有什么区别或关系?
例如,如代码中所示,从 1 到 10000 评估 max_iter 的 NN 模型并评估每次迭代的平均绝对误差可以看作是纪元?请查看下面的图片/链接!
非常感谢!
for i in range(1,10000,10):
clf = MLPRegressor(max_iter=i, solver='lbfgs', alpha=1e-6, activation='relu', # melhorou e muito o treino com relu
hidden_layer_sizes=hidden_layer_sizes, random_state=1)
clf.fit(X_train_scaled, y_train)
mae_B = cross_val_score(clf, X_train_scaled, y_train, scoring="neg_mean_absolute_error", cv=10)
print i, float(-mae_B.mean()), clf.score(X_train_scaled, y_train), clf.score(X_test_scaled, y_test)
请您参考如下方法:
max_iter 相当于您希望模型接受训练的最大轮数。它被称为最大值,因为学习可以在达到最大迭代次数之前停止,也可以根据其他终止标准 - n_iter_no_change。因此,不要使用不同的 max_iterations 循环,如果您想避免过度拟合,请尝试调整 tol 和 n_iter_no_change。
尝试以下操作并在 max_iter 中设置足够合理的 epoch,然后使用 n_iter_no_change 和 tol。引用 Doc
clf = MLPRegressor(max_iter=50, solver='lbfgs', alpha=1e-6, activation='relu',
hidden_layer_sizes=hidden_layer_sizes, random_state=1,
tol=1e-3, n_iter_no_change = 5)
clf.fit(X_train_scaled, y_train)
mae_B = cross_val_score(clf, X_train_scaled, y_train, scoring="neg_mean_absolute_error", cv=10)
print i, float(-mae_B.mean()), clf.score(X_train_scaled, y_train), clf.score(X_test_scaled, y_test)
