结果可视化plot_result

最新推荐文章于 2024-12-29 18:00:47 发布

粉皮皮

最新推荐文章于 2024-12-29 18:00:47 发布

阅读量1.2k

点赞数

CC 4.0 BY-SA版权

分类专栏： TensorFlow

本文链接：https://blog.csdn.net/wangxf666/article/details/118419023

TensorFlow 专栏收录该内容

10 篇文章

订阅专栏

本文介绍如何使用TensorFlow 2.5.0实现自定义网络层，通过实例展示了如何添加ReLU激活函数，训练一个简单的线性回归模型，并实时展示预测结果。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

import matplotlib.pyplot as plt
import tensorflow.compat.v1 as tfc
import tensorflow as tf
import numpy as np
# tensorflow 2.5.0

# 添加层函数
def add_layer(inputs, in_size, out_size, activation_function=None):
    Weights = tf.Variable(tf.random.normal([in_size, out_size]))
    biases = tf.Variable(tf.zeros([1, out_size]) + 0.1)
    Wx_plus_b = tf.matmul(inputs, Weights) + biases # y = W*x + b
    if activation_function is None:
        outputs = Wx_plus_b
    else:
        outputs = activation_function(Wx_plus_b)
    return outputs

x_data = np.linspace(-1,1,300)[:,np.newaxis]
noise = np.random.normal(0, 0.05, x_data.shape)
y_data = np.square(x_data) - 0.5 + noise

xs = tfc.placeholder(tf.float32, [None, 1])
ys = tfc.placeholder(tf.float32, [None, 1])

# 建立网络结构
l1 = add_layer(xs, 1, 10, activation_function=tf.nn.relu)
prediction = add_layer(l1, 10, 1, activation_function=None)

# 计算loss并拟定训练参数
loss = tf.reduce_mean(tf.reduce_sum(tf.square(ys-prediction), axis=[1]))
train_step = tfc.train.GradientDescentOptimizer(0.1).minimize(loss)   # 学习率0.1

init = tfc.global_variables_initializer()    # 初始化
sess = tfc.Session()
sess.run(init)

fig = plt.figure()            # 建立空白图片框
ax = fig.add_subplot(1,1,1)   # 图片序号
ax.scatter(x_data, y_data)    # 原始数据
plt.ion()   # show了以后用于连续显示
plt.show()

for i in range(1000):
    sess.run(train_step, feed_dict={xs: x_data, ys: y_data})    # 训练网络
    if i % 50 == 0:
#         to see the step improvement
#         print(sess.run(loss, feed_dict={xs: x_data, ys: y_data}))
        try:
            ax.lines.remove(lines[0]) # 抹除上一时刻的线
        except Exception:  # 如果没有线
            pass  # 什么都不做
        prediction_value = sess.run(prediction, feed_dict={xs: x_data, ys: y_data})
        lines = ax.plot(x_data, prediction_value, 'r-', lw=5) # 重画线，红色，宽度5
        plt.pause(0.1) # 刷新的时间间隔0.1s