Question

** 我不知道教授如何提出这个概念。

代码中省略了第二层和第三层。

问：您有多少个权重（W）和偏差（b）？

第二季度：什么是输入数据的维度？>

Q3：如何解释这一行代码？

trainX = xy[0 : train_size, : -1]

无处可问，因为它是研究生院的内容。有点帮助，非常感谢。

**

import tensorflow as tf

import numpy as np

import matplotlib

import os

import matplotlib.pyplot as plt



def MinMaxScaler(data):

    return (data - np.min(data, 0)) / (np.max(data, 0) - np.min(data, 0))



inputDim = 15              

outputDim = 1

learning_rate = 0.008

iterations = 20000


xy = np.loadtxt('./endterm.csv', delimiter=',')

xy = MinMaxScaler(xy)       


train_size = int(len(xy) * 0.98)            

trainX = xy[0 : train_size, : -1]   

trainY = xy[0 : train_size, [-1]]   


testX =  xy[train_size :, : -1]     

testY =  xy[train_size :, [-1]]   


X = tf.placeholder(tf.float32, shape=[None, inputDim])

Y = tf.placeholder(tf.float32, shape=[None, outputDim])





W1 = tf.Variable(tf.random_normal([inputDim, 8])) 

b1 = tf.Variable(tf.random_normal([8]))

layer1 = tf.nn.relu(tf.matmul(X, W1) + b1)

W2 = tf.Variable(tf.random_normal([8, 8])) 

b2 = tf.Variable(tf.random_normal([8]))

layer1 = tf.nn.relu(tf.matmul(X, W2) + b2)



hypothesis = tf.matmul(layer2, W3) + b3





loss = tf.reduce_mean(tf.square(hypothesis - Y))

train = tf.train.GradientDescentOptimizer(learning_rate=1e-3).minimize(loss)




targets = tf.placeholder(tf.float32, [None, 1])

predictions = tf.placeholder(tf.float32, [None, 1])

rmse = tf.sqrt(tf.reduce_mean(tf.square(targets - predictions)))


with tf.Session() as sess:

    init = tf.global_variables_initializer()

    sess.run(init)


    for i in range(iterations): 

        _, step_loss = sess.run([train, loss], feed_dict={X : trainX, Y : trainY})

        print("[step: {}] loss: {}".format(i, step_loss))




    test_predict = sess.run(hypothesis, feed_dict={X: testX})

    rmse_val = sess.run(rmse, feed_dict={targets: testY, predictions: test_predict})

    print("RMSE: {}".format(rmse_val))


    plt.plot(testY)             

    plt.plot(test_predict)      

    plt.xlabel("Time Period")

    plt.ylabel("Stock Price")

    plt.show()

我正在做RNN和DNN作业，但是我不了解很多事情

0 个答案: