1.加载数据数据由课程提供。第二个疗程，第三周后联系。需要百度的可以找X_train,Y_train,X_test,Y_test,classes=tf_utils.load_dataset()原始数据矩阵类型：print(X_train.shape)print(Y_train.shape)print(X_test.shape)print(Y_test.shape)所以需要重新修改矩阵shapeY_train=Y_train.TY_test=Y_test.T修改后：one-hotY_train=kerasforthelabel。utils.to_categorical(Y_train,num_classes=6)Y_test=keras.utils.to_categorical(Y_test,num_classes=6)2.构建卷积网络模型=Sequential([Conv2D(6,(5,5),activation='relu',input_shape=(64,64,3)),MaxPooling2D((2,2)),Conv2D(16,(5,5),activation='relu'),MaxPooling2D((2,2)),Flatten(),Dense(64,activation='relu'),Dense(32,activation='relu'),Dense(6,activation='softmax')])网络结构为：convolution->pooling->convolution->Pooling->Flatten（扁平化）->全连接->全连接->全连接3.配置神经网络模型.compile(optimizer='rmsprop',loss='categorical_crossentropy',metrics=['acc'])4.训练model.fit(X_train,Y_train,epochs=20,batch_size=64,verbose=1,validation_split=0.0,shuffle=True)5.评估神经网络得分=model.evaluate(X_test,Y_test,batch_size=64)
