时间戳

首页 > 解决方案 > TensorFlow 多项式回归 Nan 中的参数

tensorflow - TensorFlow 多项式回归 Nan 中的参数

问题描述

我正在遵循多项式回归模型。我正在运行以下代码：

import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt
import data_reader

learning_rate = 0.01
training_epochs = 40

freq = {}
freq = data_reader.read('311.csv', 0, '%Y-%m-%d', 2016)
trX = np.array(list(freq.keys())).astype(float)
trY = np.array(list(freq.values())).astype(float)

num_coeffs = 6


plt.scatter(trX, trY)
plt.show()
X = tf.placeholder(tf.float32)
Y = tf.placeholder(tf.float32)

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)

w = tf.Variable([0.] * num_coeffs, name="parameters")

init_op = tf.global_variables_initializer()
with tf.Session() as sess:
       sess.run(init_op) #execute init_op

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 = tf.global_variables_initializer()
sess.run(init)

for epoch in range(training_epochs):
    for (x, y) in zip(trX, trY):
        sess.run(train_op, feed_dict={X: x, Y: y})


w_val = sess.run(w)
print(w_val)

sess.close()

其中 trX 和 trY 是 52 长的数字数组。不幸的是，参数 w_val 都是 [nan nan nan nan nan]。我究竟做错了什么？

谢谢。

标签： tensorflow

解决方案

我通过标准化（0-1）X轴来解决。但是我需要标准化吗？

推荐阅读