為什么80%的碼農(nóng)都做不了架構(gòu)師？>>> ??

#coding:utf-8 ''' 多項式 '''import numpy as np import tensorflow as tf import matplotlib.pyplot as plt# 定義模型 def model(X,w):terms = []for i in range(num_coeffs):term = tf.multiply(w[i],tf.pow(X,i))terms.append(term)return tf.add_n(terms)# 學(xué)習(xí)速率 learning_rate = 0.01# 迭代次數(shù) training_epochs = 40# 生成模擬數(shù)據(jù) train_X = np.linspace(-1,1,101)# 設(shè)置多項式維度 num_coeffs = 6 train_Y_coeffs = [1,2,3,4,5,6] train_Y = 0 for i in range(num_coeffs):train_Y += train_Y_coeffs[i] * np.power(train_X,i)# 生成帶有噪音的數(shù)據(jù) train_Y += np.random.randn(*train_X.shape) * 1.5# 定義訓(xùn)練參數(shù) X = tf.placeholder(tf.float32) Y = tf.placeholder(tf.float32)w = tf.Variable([0.] * num_coeffs,name='parameters') y_model = model(X,w)cost = (tf.pow(Y-y_model,2)) train_op = tf.train.GradientDescentOptimizer(learning_rate).minimize(cost)sess = tf.Session() init_op = tf.global_variables_initializer()sess.run(init_op)# 訓(xùn)練 for epoch in range(training_epochs): for (x, y) in zip(train_X, train_Y): sess.run(train_op, feed_dict={X: x, Y: y})w_val = sess.run(w) print(w_val) sess.close()plt.scatter(train_X, train_Y)train_Y2 = 0 for i in range(num_coeffs):train_Y2 += w_val[i] * np.power(train_X, i) plt.plot(train_X, train_Y2, 'r') plt.show()

?

轉(zhuǎn)載于:https://my.oschina.net/wujux/blog/1801238

總結(jié)

以上是生活随笔為你收集整理的Tensorflow学习笔记：多项式拟合的全部內(nèi)容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網(wǎng)站內(nèi)容還不錯，歡迎將生活随笔推薦給好友。