tensorflow实现单层神经网络拟合

定义层的函数，里面有权重值、偏置值、计算和激活函数

def add_layer(inputs,in_size,out_size,activation_function=None):
        Weights = tf.Variable(tf.random_normal([in_size,out_size]),name='W')
        biases = tf.Variable(tf.zeros([1,out_size])+0.1,name='b')
        Wx_plus_b = tf.add(tf.matmul(inputs,Weights),biases)
        if activation_function is None:
            outputs = Wx_plus_b
        else:
            outputs = activation_function(Wx_plus_b)
        return outputs

加上测试数据

x_data = np.linspace(-1,1,100)[:,np.newaxis]
noise = np.random.normal(0,0.05,x_data.shape)
y_data = np.square(x_data)-0.5 + noise

xs = tf.placeholder(tf.float32,[None,1],name='x_input')
ys = tf.placeholder(tf.float32,[None,1],name='y_input')
#定义层
l1 = add_layer(xs,1,10,activation_function=tf.nn.relu)
prediction = add_layer(l1,10,1,activation_function=None)
#定义损失和优化器
loss = tf.reduce_mean(tf.reduce_sum(tf.square(ys-prediction),reduction_indices=[1]))
train_step = tf.train.GradientDescentOptimizer(0.1).minimize(loss)

定义好图后，用tf.Session()来运行它

with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    #可视化部分
    fig = plt.figure()
    ax = fig.add_subplot(1,1,1)
    ax.scatter(x_data,y_data)
    plt.ion()
    plt.show()
    #------------------
    for i in range(2000):
        sess.run(train_step,feed_dict={xs:x_data,ys:y_data})
        if i % 50==0:
            prediction_value = sess.run(prediction,feed_dict={xs:x_data})
            #可视化部分
            try:
                ax.lines.remove(lines[0])
            except Exception:
                pass
            lines = ax.plot(x_data,prediction_value,'r-',lw=5) 
            plt.pause(0.1)
            #--------------------