from keras.optimizers import SGD、from keras.utils import to_categorical报错

import tensorflow as tf from tensorflow.keras.models import Sequential from tensorflow.keras.layers import Dense,Dropout,Convolution2D,MaxPooling2D,Flatten from tensorflow.keras.optimizers import Adam,SGD from tensorflow.keras.utils import to_categorical import numpy as np mnist = tf.keras.datasets.mnist (x_train,y_train) ,(x_test,y_test) = mnist.load_data() x_train = x_train.reshape(x_train.shape[0],-1)/255 x_test = x_test.reshape(x_test.shape[0],-1)/255 y_train = to_categorical(y_train,num_classes=10) # convert to one hot format y_test = to_categorical(y_test,num_classes=10) model = Sequential() model.add(Dense(units=30, #输出维度，表示有几个神经元 input_dim=784, #输入尺寸 activation='sigmoid', name='lay1')) model.add(Dense(units=10, #输出维度，表示有几个神经元 activation='sigmoid', name='lay2')) # sgd = SGD(lr=0.2) from tensorflow.keras import optimizers sgd = optimizers.SGD(learning_rate=0.2) model.compile( optimizer=tf.keras.optimizers.Adam(learning_rate=0.0001), loss = 'categorical_crossentropy', metrics= ['accuracy'] ) model.fit(x_train, y_train, batch_size=64, epochs=50) loss,accuracy = model.evaluate(x_test,y_test) print(loss) print('accuracy',accuracy) weight_Dense,bias_Dense = model.get_layer('lay1').get_weights() np.savetxt('weight1.txt',weight_Dense,fmt='%.06f,') np.savetxt('bias1.txt',bias_Dense,fmt='%.06f,') # print(weight_Dense,bias_Dense) weight_Dense,bias_Dense = model.get_layer('lay2').get_weights() np.savetxt('weight2.txt',weight_Dense,fmt='%.06f,') np.savetxt('bias2.txt',bias_Dense,fmt='%.06f,') # print(weight_Dense,bias_Dense) model.save('2lays.h5') 以上代码的功能

from keras.datasets import mnist from pyexpat import model import numpy as np from keras.models import Sequential from keras.layers import Dense from keras.optimizers import SGD import matplotlib.pyplot as plt from keras.utils.np_utils import to_categorical (X_train,Y_train),(X_test,Y_test)=mnist.load_data() print("X_train.shape:"+str(X_train.shape)) print("Y_train.shape:"+str(Y_train.shape)) print("X_test.shape:"+str(X_test.shape)) print("Y_test.shape:"+str(Y_test.shape)) print(Y_train[0]) #print label plt.imshow(X_train[0],cmap='gray') plt.show() X_train=X_train.reshape(60000,784)/255.0 X_test=X_test.reshape(10000,784)/255.0 #guiyi 255huiduzuidazhi Y_train = to_categorical(Y_train,10)#durebianma Y_test= to_categorical(Y_test,10) model =Sequential() model.add(Dense(units=256,activation='relu',input_dim=784)) model.add(Dense(units=256,activation='relu')) model.add(Dense(units=256,activation='relu')) model.add(Dense(units=10,activation='softmax')) #model.add(Dense(units=1,activation='sigmoid')) model.compile(loss='categorical_crossentropy',optimizer=SGD(lr=0.05),metrics=['accuracy']) model.fit(X_train,Y_train,epochs=100,batch_size=128) loss,accuracy=model.evaluate(X_test,Y_test) print("loss"+str(loss)) print("loss"+str(accuracy))