X=sc.fit_transform(X) my_ann.add(Dense(units=32,kernel_initializer='uniform',activation='relu',input_dim=11)) ---------------- ##add hidden layer my_ann.add(Dense(units=32,kernel_initializer='uniform',activation='relu')) ##output layer my_ann.add(Dense(units=1,kernel_initializer='uniform',activation='sigmoid')) print(my_ann.summary()) my_ann.complile(optimizer='adam',loss='binary_crossentropy',metrics=['accuracy']) from sklearn.model_selection import train_test_split [xtrain,xtest,ytrain,ytest]=train_test_split(X,Y,test_size=0.3,random_state=42) my_ann.fit(xtrain,ytrain,batch_size=10,epochs=100) ypred=my_ann.predict(xtest) ypred=(ypred>0.5) from sklearn.metrics import accuracy_score acc=accuracy_score(ytest,ypred) print(acc)
#!/usr/bin/env python3.6 """ LSTM 输入一维数组,原样输出一维数组 """ from numpy import array from keras.models import Sequential from keras.layers import Dense from keras.layers import LSTM length = 5 neurons = length epoch = 1000 seq = array([i / float(length) for i in range(length)]) xtrain = seq.reshape(len(seq), 1, 1) xtrain = seq.reshape(len(seq), 1) model = Sequential() model.add(LSTM(neurons, input_shape(1, 1))) model.add(Dense(1)) model.complile(loss='mean_sequared_error', optimizer='adam') model.fit(xtrain, ytrain, epochs=epoch, batch_size=batch) result = model.predict(xtrain, batch_size=batch) for val in result: print('%.1f' % val)