import kerasimport numpy as npimport matplotlib.pyplot as pltfrom keras.models import Sequentialfrom keras.layers import Dense#维度是100 返回值为指定维度的arrayx_data=np.random.rand(100)x_data_test=np.random.rand(2,2)print(type(x_data))noise=np.random.normal(0,0.01,x_data.shape)print(type(noise))y_data=x_data*0.1+0.2+noiseplt.scatter(x_data,y_data)#plt.show()#构建一个顺序模型model=Sequential()#在模型中添加一个全连接层model.add(Dense(units=1,input_dim=1))#变异model.compile(optimizer='sgd',loss='mse')for step in range(3001):    # 每次训练一个批次    print('setp',step)    cost=model.train_on_batch(x_data,y_data)    if step % 500 == 0:        print("cost:",cost)W,b=model.layers[0].get_weights()print('W',W,'b',b)#x_data 输入网络中 得到预测值 y_predy_pred=model.predict(x_data)#显示随机点plt.scatter(x_data,y_data)plt.plot(x_data,y_pred,'r-',lw=3)#显示预测结果plt.show()