1 GridSearchCV實際上可以看做是for循環輸入一組參數后再比較哪種情況下最優.

使用GirdSearchCV模板

# Use scikit-learn to grid search the batch size and epochs import numpy from sklearn.model_selection import GridSearchCV from keras.models import Sequential from keras.layers import Dense from keras.wrappers.scikit_learn import KerasClassifier import pandas as pd import os os.environ["CUDA_VISIBLE_DEVICES"] = "1" # Function to create model, required for KerasClassifier def create_model(optimizer='adam'):# create modelmodel = Sequential()model.add(Dense(12, input_dim=8, activation='relu'))model.add(Dense(1, activation='sigmoid'))# Compile modelmodel.compile(loss='binary_crossentropy', optimizer=optimizer, metrics=['accuracy'])return model # fix random seed for reproducibility seed = 7 numpy.random.seed(seed) # load dataset dataset = pd.read_csv('diabetes.csv', ) # split into input (X) and output (Y) variables X = dataset[['Pregnancies', 'Glucose', 'BloodPressure', 'SkinThickness','Insulin','BMI', 'DiabetesPedigreeFunction', 'Age']] Y = dataset['Outcome'] # create model model = KerasClassifier(build_fn=create_model, epochs=100, batch_size=10, verbose=0) # define the grid search parameters optimizer = ['SGD', 'RMSprop', 'Adagrad', 'Adadelta', 'Adam', 'Adamax', 'Nadam'] param_grid = dict(optimizer=optimizer) grid = GridSearchCV(estimator=model, param_grid=param_grid, n_jobs=-1) grid_result = grid.fit(X, Y) # summarize results print("Best: %f using %s" % (grid_result.best_score_, grid_result.best_params_)) print(grid_result) print('kkkk') print(grid_result.cv_results_) means = grid_result.cv_results_['mean_test_score'] stds = grid_result.cv_results_['std_test_score'] params = grid_result.cv_results_['params'] for mean, stdev, param in zip(means, stds, params):print("%f (%f) with: %r" % (mean, stdev, param)) View Code

?

參考：https://machinelearningmastery.com/grid-search-hyperparameters-deep-learning-models-python-keras/

????????? https://blog.csdn.net/weixin_41988628/article/details/83098130

2

利用隨機搜索實現鳶尾花調參,

from sklearn.datasets import load_iris # 自帶的樣本數據集 from sklearn.neighbors import KNeighborsClassifier # 要估計的是knn里面的參數，包括k的取值和樣本權重分布方式 import matplotlib.pyplot as plt # 可視化繪圖 from sklearn.model_selection import GridSearchCV,RandomizedSearchCV # 網格搜索和隨機搜索 import pandas as pd iris = pd.read_csv('../data/iris.csv', ) print(iris.head()) print(iris.columns) X = iris[['Sepal.Length', 'Sepal.Width', 'Petal.Length','Petal.Width']] # 150個樣本，4個屬性 y = iris['Species'] # 150個類標號 k_range = range(1, 31) # 優化參數k的取值范圍 weight_options = ['uniform', 'distance'] # 代估參數權重的取值范圍。uniform為統一取權值，distance表示距離倒數取權值 # 下面是構建parameter grid，其結構是key為參數名稱，value是待搜索的數值列表的一個字典結構 param_grid = {'n_neighbors':k_range,'weights':weight_options} # 定義優化參數字典，字典中的key值必須是分類算法的函數的參數名 print(param_grid)knn = KNeighborsClassifier(n_neighbors=5) # 定義分類算法。n_neighbors和weights的參數名稱和param_grid字典中的key名對應# ================================網格搜索======================================= # 這里GridSearchCV的參數形式和cross_val_score的形式差不多，其中param_grid是parameter grid所對應的參數 # GridSearchCV中的n_jobs設置為-1時，可以實現并行計算（如果你的電腦支持的情況下） grid = GridSearchCV(estimator = knn, param_grid = param_grid, cv=10, scoring='accuracy') #針對每個參數對進行了10次交叉驗證。scoring='accuracy'使用準確率為結果的度量指標。可以添加多個度量指標 grid.fit(X, y)print('網格搜索-度量記錄：',grid.cv_results_) # 包含每次訓練的相關信息 print('網格搜索-最佳度量值:',grid.best_score_) # 獲取最佳度量值 print('網格搜索-最佳參數：',grid.best_params_) # 獲取最佳度量值時的代定參數的值。是一個字典 print('網格搜索-最佳模型：',grid.best_estimator_) # 獲取最佳度量時的分類器模型# 使用獲取的最佳參數生成模型，預測數據 knn = KNeighborsClassifier(n_neighbors=grid.best_params_['n_neighbors'], weights=grid.best_params_['weights']) # 取出最佳參數進行建模 knn.fit(X, y) # 訓練模型 print(knn.predict([[3, 5, 4, 2]])) # 預測新對象# =====================================隨機搜索=========================================== rand = RandomizedSearchCV(knn, param_grid, cv=10, scoring='accuracy', n_iter=10, random_state=5) # rand.fit(X, y)print('隨機搜索-度量記錄：',grid.cv_results_) # 包含每次訓練的相關信息 print('隨機搜索-最佳度量值:',grid.best_score_) # 獲取最佳度量值 print('隨機搜索-最佳參數：',grid.best_params_) # 獲取最佳度量值時的代定參數的值。是一個字典 print('隨機搜索-最佳模型：',grid.best_estimator_) # 獲取最佳度量時的分類器模型# 使用獲取的最佳參數生成模型，預測數據 knn = KNeighborsClassifier(n_neighbors=grid.best_params_['n_neighbors'], weights=grid.best_params_['weights']) # 取出最佳參數進行建模 knn.fit(X, y) # 訓練模型 print(knn.predict([[3, 5, 4, 2]])) # 預測新對象# =====================================自定義度量=========================================== from sklearn import metrics # 自定義度量函數 def scorerfun(estimator, X, y):y_pred = estimator.predict(X)return metrics.accuracy_score(y, y_pred)rand = RandomizedSearchCV(knn, param_grid, cv=10, scoring='accuracy', n_iter=10, random_state=5) # rand.fit(X, y)print('隨機搜索-最佳度量值:',grid.best_score_) # 獲取最佳度量值 View Code

參考：https://blog.csdn.net/luanpeng825485697/article/details/79831703

轉載于:https://www.cnblogs.com/xxswkl/p/11072795.html

總結

以上是生活随笔為你收集整理的GridSearchCV和RandomizedSearchCV调参的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。