Tensorflow：使用 CSV 数据的简单线性回归

Question

我是 tensorflow 的极端初学者，我的任务是使用包含 2 列高度和充电状态 (SoC) 的 csv 数据进行简单的线性回归，其中两个值都是浮动的。 在 CSV 文件中，Height 是第一列，而 SoC 是第二列。

我假设使用高度来预测 SoC

我完全不知道我必须在代码的“适合所有训练数据”部分添加什么。我看过其他线性回归模型，它们的代码令人难以置信，比如这个：

with tf.Session() as sess:
sess.run(init)
for epoch in range(training_epochs):
    sess.run(training_step,feed_dict={X:train_x,Y:train_y})
    cost_history = np.append(cost_history,sess.run(cost,feed_dict={X: train_x,Y: train_y}))

#calculate mean square error 
pred_y = sess.run(y_, feed_dict={X: test_x})
mse = tf.reduce_mean(tf.square(pred_y - test_y))
print("MSE: %.4f" % sess.run(mse)) 

#plot cost
plt.plot(range(len(cost_history)),cost_history)
plt.axis([0,training_epochs,0,np.max(cost_history)])
plt.show()

fig, ax = plt.subplots()
ax.scatter(test_y, pred_y)
ax.plot([test_y.min(), test_y.max()], [test_y.min(), test_y.max()], 'k--', lw=3)
ax.set_xlabel('Measured')
ax.set_ylabel('Predicted')
plt.show()

我刚刚能够使用本指南从我的 CSV 文件中正确获取数据：

TensorFlow: Reading and using data from CSV file

完整代码：

import tensorflow as tf
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
%matplotlib inline
rng = np.random

from numpy import genfromtxt
from sklearn.datasets import load_boston

# Parameters
learning_rate = 0.01
training_epochs = 1000
display_step = 50
n_samples = 221

X = tf.placeholder("float") # create symbolic variables
Y = tf.placeholder("float")

filename_queue = tf.train.string_input_producer(["battdata.csv"],shuffle=False)

reader = tf.TextLineReader(skip_header_lines=1)
key, value = reader.read(filename_queue)

# Default values, in case of empty columns. Also specifies the type of the
# decoded result.
record_defaults = [[1.], [1.]]
col1, col2= tf.decode_csv(
    value, record_defaults=record_defaults)
features = tf.stack([col1])

# Set model weights
W = tf.Variable(rng.randn(), name="weight")
b = tf.Variable(rng.randn(), name="bias")

# Construct a linear model
pred = tf.add(tf.multiply(col1, W), b) # XW + b <- y = mx + b  where W is gradient, b is intercept

# Mean squared error
cost = tf.reduce_sum(tf.pow(pred-col2, 2))/(2*n_samples)

# Gradient descent
optimizer = tf.train.GradientDescentOptimizer(learning_rate).minimize(cost)

# Initializing the variables
init = tf.global_variables_initializer()

with tf.Session() as sess:
    # Start populating the filename queue.
    coord = tf.train.Coordinator()
    threads = tf.train.start_queue_runners(coord=coord)
    sess.run(init)

    # Fit all training data
    for epoch in range(training_epochs):
        _, cost_value = sess.run([optimizer,cost])
        for (x, y) in zip(col2, col1):
                sess.run(optimizer, feed_dict={X: x, Y: y})

            #Display logs per epoch step
        if (epoch+1) % display_step == 0:
            c = sess.run(cost, feed_dict={X: col2, Y:col1})
            print( "Epoch:", '%04d' % (epoch+1), "cost=", "{:.9f}".format(c), \
                "W=", sess.run(W), "b=", sess.run(b))

        print("Optimization Finished!")
        training_cost = sess.run(cost, feed_dict={X: col2, Y: col1})
        print ("Training cost=", training_cost, "W=", sess.run(W), "b=", sess.run(b), '\n')

        #Graphic display
        plt.plot(train_X, train_Y, 'ro', label='Original data')
        plt.plot(train_X, sess.run(W) * col2 + sess.run(b), label='Fitted line')
        plt.legend()
        plt.show()

    coord.request_stop()
    coord.join(threads)

错误：

INFO:tensorflow:Error 报告给 Coordinator: ，尝试使用已关闭的 Session。 -------------------------------------------------- ------------------------- TypeError Traceback（最近一次调用 最后）在（） 8 用于范围内的纪元（training_epochs）： 9 _, cost_value = sess.run([优化器,成本]) ---> 10 for (x, y) in zip(*col1, col2): 11 sess.run（优化器，feed_dict={X: x, Y: y}） 12

C:\Users\Shiina\Anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\framework\ops.py 在 iter(自我) 514 类型错误：调用时。 第515章 --> 516 raise TypeError("'Tensor' object is not iterable.") 517 518 def bool（自我）：

TypeError: 'Tensor' 对象不可迭代。

Answer 1

错误是因为您试图迭代 for (x, y) in zip(col2, col1) 中的张量，这是不允许的。代码的另一个问题是您设置了输入管道队列，然后您还尝试通过 feed_dict{} 输入，这是错误的。您的训练部分应如下所示：

with tf.Session() as sess:
# Start populating the filename queue.
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(coord=coord)
sess.run(init)

# Fit all training data
for epoch in range(training_epochs):
    _, cost_value = sess.run([optimizer,cost])

        #Display logs per epoch step
    if (epoch+1) % display_step == 0:
        c = sess.run(cost)
        print( "Epoch:", '%04d' % (epoch+1), "cost=", "{:.9f}".format(c), \
            "W=", sess.run(W), "b=", sess.run(b))

    print("Optimization Finished!")
    training_cost = sess.run(cost)
    print ("Training cost=", training_cost, "W=", sess.run(W), "b=", sess.run(b), '\n')

#Plot data after completing training
train_X = []
train_Y = []
for i in range(input_size): #Your input data size to loop through once
    X, Y = sess.run([col1, pred]) # Call pred, to get the prediction with the updated weights
    train_X.append(X)
    train_Y.append(y)
    #Graphic display
plt.plot(train_X, train_Y, 'ro', label='Original data')
plt.legend()
plt.show()

coord.request_stop()
coord.join(threads)