文章目錄

• 數(shù)據(jù)導(dǎo)入
• 數(shù)據(jù)處理
• 模型訓(xùn)練
• 神經(jīng)網(wǎng)絡(luò)評(píng)估
• 效果

數(shù)據(jù)導(dǎo)入

#數(shù)據(jù)導(dǎo)入 from keras.datasets import mnist (X_train,Y_train),(X_test,Y_test) = mnist.load_data()

數(shù)據(jù)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(duì)類別進(jìn)行編碼 獨(dú)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(xùn)練

#####模型訓(xùn)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(jīng)網(wǎng)絡(luò)評(píng)估

#####神經(jīng)網(wǎng)絡(luò)評(píng)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(jié)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(shù)專家面對(duì)面20年技術(shù)見證，附贈(zèng)技術(shù)全景圖

總結(jié)

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?jī)?nèi)容，希望文章能夠幫你解決所遇到的問(wèn)題。

如果覺得生活随笔網(wǎng)站內(nèi)容還不錯(cuò)，歡迎將生活随笔推薦給好友。