本文將遍歷批量數(shù)據(jù)點并讓TensorFlow更新斜率和y截距。這次將使用Scikit Learn的內建iris數(shù)據(jù)集。特別地,我們將用數(shù)據(jù)點(x值代表花瓣寬度,y值代表花瓣長度)找到最優(yōu)直線。選擇這兩種特征是因為它們具有線性關系,在后續(xù)結果中將會看到。本文將使用L2正則損失函數(shù)。

# 用TensorFlow實現(xiàn)線性回歸算法
#----------------------------------
#
# This function shows how to use TensorFlow to
# solve linear regression.
# y = Ax + b
#
# We will use the iris data, specifically:
# y = Sepal Length
# x = Petal Width
import matplotlib.pyplot as plt
import numpy as np
import tensorflow as tf
from sklearn import datasets
from tensorflow.python.framework import ops
ops.reset_default_graph()
# Create graph
sess = tf.Session()
# Load the data
# iris.data = [(Sepal Length, Sepal Width, Petal Length, Petal Width)]
iris = datasets.load_iris()
x_vals = np.array([x[3] for x in iris.data])
y_vals = np.array([y[0] for y in iris.data])
# 批量大小
batch_size = 25
# Initialize 占位符
x_data = tf.placeholder(shape=[None, 1], dtype=tf.float32)
y_target = tf.placeholder(shape=[None, 1], dtype=tf.float32)
# 模型變量
A = tf.Variable(tf.random_normal(shape=[1,1]))
b = tf.Variable(tf.random_normal(shape=[1,1]))
# 增加線性模型,y=Ax+b
model_output = tf.add(tf.matmul(x_data, A), b)
# 聲明L2損失函數(shù),其為批量損失的平均值。
loss = tf.reduce_mean(tf.square(y_target - model_output))
# 聲明優(yōu)化器 學習率設為0.05
my_opt = tf.train.GradientDescentOptimizer(0.05)
train_step = my_opt.minimize(loss)
# 初始化變量
init = tf.global_variables_initializer()
sess.run(init)
# 批量訓練遍歷迭代
# 迭代100次,每25次迭代輸出變量值和損失值
loss_vec = []
for i in range(100):
rand_index = np.random.choice(len(x_vals), size=batch_size)
rand_x = np.transpose([x_vals[rand_index]])
rand_y = np.transpose([y_vals[rand_index]])
sess.run(train_step, feed_dict={x_data: rand_x, y_target: rand_y})
temp_loss = sess.run(loss, feed_dict={x_data: rand_x, y_target: rand_y})
loss_vec.append(temp_loss)
if (i+1)%25==0:
print('Step #' + str(i+1) + ' A = ' + str(sess.run(A)) + ' b = ' + str(sess.run(b)))
print('Loss = ' + str(temp_loss))
# 抽取系數(shù)
[slope] = sess.run(A)
[y_intercept] = sess.run(b)
# 創(chuàng)建最佳擬合直線
best_fit = []
for i in x_vals:
best_fit.append(slope*i+y_intercept)
# 繪制兩幅圖
# 擬合的直線
plt.plot(x_vals, y_vals, 'o', label='Data Points')
plt.plot(x_vals, best_fit, 'r-', label='Best fit line', linewidth=3)
plt.legend(loc='upper left')
plt.title('Sepal Length vs Pedal Width')
plt.xlabel('Pedal Width')
plt.ylabel('Sepal Length')
plt.show()
# Plot loss over time
# 迭代100次的L2正則損失函數(shù)
plt.plot(loss_vec, 'k-')
plt.title('L2 Loss per Generation')
plt.xlabel('Generation')
plt.ylabel('L2 Loss')
plt.show()
文章標題:TensorFlow實現(xiàn)iris數(shù)據(jù)集線性回歸-創(chuàng)新互聯(lián)
文章轉載:http://chinadenli.net/article20/peijo.html
成都網(wǎng)站建設公司_創(chuàng)新互聯(lián),為您提供軟件開發(fā)、靜態(tài)網(wǎng)站、品牌網(wǎng)站制作、做網(wǎng)站、網(wǎng)站內鏈、企業(yè)網(wǎng)站制作
聲明:本網(wǎng)站發(fā)布的內容(圖片、視頻和文字)以用戶投稿、用戶轉載內容為主,如果涉及侵權請盡快告知,我們將會在第一時間刪除。文章觀點不代表本網(wǎng)站立場,如需處理請聯(lián)系客服。電話:028-86922220;郵箱:631063699@qq.com。內容未經(jīng)允許不得轉載,或轉載時需注明來源: 創(chuàng)新互聯(lián)