文章目錄

• 數據導入
• 數據處理
• 模型訓練
• 神經網絡評估
• 效果

數據導入

#數據導入 from keras.datasets import mnist (X_train,Y_train),(X_test,Y_test) = mnist.load_data()

數據處理

#圖像降維 X_train = X_train.reshape((X_train.shape[0], X_train.shape[1] * X_train.shape[2])) X_test = X_test.reshape((X_test.shape[0], X_test.shape[1] * X_test.shape[2])) #對類別進行編碼 獨熱編碼 from sklearn.preprocessing import OneHotEncoder onehot = OneHotEncoder() Y_train = onehot.fit_transform(Y_train.reshape(Y_train.shape[0],1)) Y_test = onehot.fit_transform(Y_test.reshape(Y_test.shape[0],1)) #稀疏矩陣->密集矩陣 Y_train = Y_train.todense() Y_test = Y_test.todense()

模型訓練

#####模型訓練 from sklearn.neural_network import MLPClassifier clf = MLPClassifier(hidden_layer_sizes=(10,10),random_state = 14) clf.fit(X_train,Y_train)

神經網絡評估

#####神經網絡評估 from sklearn.metrics import f1_score Y_pred = clf.predict(X_test) score = f1_score(y_pred = Y_pred, y_true=Y_test, average = 'macro') print("the accuracy is {0:.1f}%".format(100*score))#####分類結果查看 from sklearn.metrics import classification_report print(classification_report(y_pred = Y_pred, y_true=Y_test))

效果

與50位技術專家面對面20年技術見證，附贈技術全景圖

總結

以上是生活随笔為你收集整理的手写体识别(数据挖掘入门与实践-实验11)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。